diff --git "a/logs/main/main_log.txt" "b/logs/main/main_log.txt" new file mode 100644--- /dev/null +++ "b/logs/main/main_log.txt" @@ -0,0 +1,9337 @@ +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +[default0]:Offline mode: forcing local_files_only=True +[default0]:Could not locate the tokenizer configuration file, will try to use the model config instead. +[default0]:Offline mode: forcing local_files_only=True +[default0]:loading configuration file config.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/config.json +[default0]:using world size: 64, data-parallel-size: 32, tensor-model-parallel size: 2, pipeline-model-parallel size: 1 +[default0]:WARNING: overriding default arguments for tokenizer_type:GPT2BPETokenizer with tokenizer_type:PretrainedFromHF +[default0]:using torch.float16 for parameters ... +[default0]:------------------------ arguments ------------------------ +[default0]: abort_on_unmet_fused_kernel_constraints ......... True +[default0]: accumulate_allreduce_grads_in_fp32 .............. False +[default0]: adam_beta1 ...................................... 0.9 +[default0]: adam_beta2 ...................................... 0.95 +[default0]: adam_eps ........................................ 1e-08 +[default0]: adlr_autoresume ................................. False +[default0]: adlr_autoresume_interval ........................ 1000 +[default0]: apply_query_key_layer_scaling ................... True +[default0]: apply_residual_connection_post_layernorm ........ False +[default0]: attention_dropout ............................... 0.1 +[default0]: attention_softmax_in_fp32 ....................... False +[default0]: bert_binary_head ................................ True +[default0]: bert_load ....................................... None +[default0]: bf16 ............................................ False +[default0]: bias_dropout_fusion ............................. True +[default0]: bias_gelu_fusion ................................ True +[default0]: biencoder_projection_dim ........................ 0 +[default0]: biencoder_shared_query_context_model ............ False +[default0]: block_data_path ................................. None +[default0]: checkpoint_activations .......................... True +[default0]: checkpoint_in_cpu ............................... False +[default0]: checkpoint_num_layers ........................... 1 +[default0]: clip_grad ....................................... 1.0 +[default0]: codecarbon_dir .................................. None +[default0]: consumed_train_samples .......................... 0 +[default0]: consumed_train_tokens ........................... 0 +[default0]: consumed_valid_samples .......................... 0 +[default0]: contigious_checkpointing ........................ False +[default0]: cpu_optimizer ................................... False +[default0]: cpu_torch_adam .................................. False +[default0]: curriculum_learning ............................. False +[default0]: data_impl ....................................... mmap +[default0]: data_parallel_size .............................. 32 +[default0]: data_path ....................................... ['/gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document'] +[default0]: dataloader_type ................................. single +[default0]: DDP_impl ........................................ local +[default0]: decoder_seq_length .............................. None +[default0]: deepscale ....................................... False +[default0]: deepscale_config ................................ None +[default0]: deepspeed ....................................... True +[default0]: deepspeed_activation_checkpointing .............. True +[default0]: deepspeed_config ................................ ./ds_config.1219022.json +[default0]: deepspeed_mpi ................................... False +[default0]: distribute_checkpointed_activations ............. False +[default0]: distributed_backend ............................. nccl +[default0]: embed_layernorm ................................. True +[default0]: embedding_path .................................. None +[default0]: encoder_seq_length .............................. 2048 +[default0]: eod_mask_loss ................................... False +[default0]: eval_interval ................................... 1000 +[default0]: eval_iters ...................................... 1 +[default0]: eval_only ....................................... None +[default0]: evidence_data_path .............................. None +[default0]: exit_duration_in_mins ........................... 1190 +[default0]: exit_interval ................................... None +[default0]: ffn_hidden_size ................................. 10240 +[default0]: finetune ........................................ False +[default0]: fp16 ............................................ True +[default0]: fp16_lm_cross_entropy ........................... False +[default0]: fp32_residual_connection ........................ False +[default0]: gigaflos_no_embeds .............................. 0 +[default0]: global_batch_size ............................... 512 +[default0]: glu_activation .................................. None +[default0]: hidden_dropout .................................. 0.1 +[default0]: hidden_size ..................................... 2560 +[default0]: hysteresis ...................................... 2 +[default0]: ict_head_size ................................... None +[default0]: ict_load ........................................ None +[default0]: img_dim ......................................... 224 +[default0]: indexer_batch_size .............................. 128 +[default0]: indexer_log_interval ............................ 1000 +[default0]: inference ....................................... False +[default0]: init_method_std ................................. 0.1 +[default0]: init_method_xavier_uniform ...................... False +[default0]: initial_loss_scale .............................. 4294967296 +[default0]: kill_switch_path ................................ None +[default0]: kv_channels ..................................... 80 +[default0]: layernorm_epsilon ............................... 1e-05 +[default0]: lazy_mpu_init ................................... None +[default0]: load ............................................ /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: local_rank ...................................... None +[default0]: log_batch_size_to_tensorboard ................... True +[default0]: log_interval .................................... 1 +[default0]: log_learning_rate_to_tensorboard ................ True +[default0]: log_level ....................................... None +[default0]: log_level_replica ............................... None +[default0]: log_loss_scale_to_tensorboard ................... True +[default0]: log_num_zeros_in_grad ........................... False +[default0]: log_params_norm ................................. False +[default0]: log_path ........................................ None +[default0]: log_timers_to_tensorboard ....................... True +[default0]: log_validation_ppl_to_tensorboard ............... True +[default0]: loss_on_targets_only ............................ False +[default0]: loss_scale ...................................... None +[default0]: loss_scale_window ............................... 1000 +[default0]: lr .............................................. 0.0017 +[default0]: lr_decay_iters .................................. None +[default0]: lr_decay_samples ................................ 1953125 +[default0]: lr_decay_style .................................. cosine +[default0]: lr_decay_tokens ................................. None +[default0]: lr_warmup_fraction .............................. None +[default0]: lr_warmup_iters ................................. 0 +[default0]: lr_warmup_samples ............................... 183105 +[default0]: make_vocab_size_divisible_by .................... 128 +[default0]: mask_prob ....................................... 0.15 +[default0]: masked_softmax_fusion ........................... True +[default0]: max_position_embeddings ......................... 2048 +[default0]: mean_noise_span_length .......................... None +[default0]: memory_centric_tiled_linear ..................... False +[default0]: merge_file ...................................... None +[default0]: micro_batch_size ................................ 16 +[default0]: min_loss_scale .................................. 1.0 +[default0]: min_lr .......................................... 0.0 +[default0]: mmap_warmup ..................................... False +[default0]: mup ............................................. True +[default0]: mup_attn_mult ................................... 10.0 +[default0]: mup_base_ffn_hidden_size ........................ 256 +[default0]: mup_base_hidden_size ............................ 64 +[default0]: mup_coord_check ................................. False +[default0]: mup_input_mult .................................. 10.0 +[default0]: mup_output_mult ................................. 10.0 +[default0]: no_load_optim ................................... None +[default0]: no_load_rng ..................................... None +[default0]: no_save_optim ................................... None +[default0]: no_save_rng ..................................... None +[default0]: noise_density ................................... None +[default0]: num_attention_heads ............................. 32 +[default0]: num_channels .................................... 3 +[default0]: num_classes ..................................... 1000 +[default0]: num_layers ...................................... 32 +[default0]: num_layers_per_virtual_pipeline_stage ........... None +[default0]: num_workers ..................................... 2 +[default0]: onnx_safe ....................................... None +[default0]: openai_gelu ..................................... False +[default0]: optimizer ....................................... adam +[default0]: override_lr_scheduler ........................... False +[default0]: pad_vocab_size_to ............................... 51200 +[default0]: params_dtype .................................... torch.float16 +[default0]: partition_activations ........................... False +[default0]: patch_dim ....................................... 16 +[default0]: pipeline_model_parallel_size .................... 1 +[default0]: position_embedding_type ......................... PositionEmbeddingType.alibi +[default0]: pp_partition_method ............................. type:transformer +[default0]: profile_backward ................................ False +[default0]: query_in_block_prob ............................. 0.1 +[default0]: rampup_batch_size ............................... None +[default0]: rank ............................................ 0 +[default0]: remote_device ................................... none +[default0]: reset_attention_mask ............................ False +[default0]: reset_position_ids .............................. False +[default0]: retriever_report_topk_accuracies ................ [] +[default0]: retriever_score_scaling ......................... False +[default0]: retriever_seq_length ............................ 256 +[default0]: reweight_loss_based_on_position_frequency ....... False +[default0]: sample_rate ..................................... 1.0 +[default0]: save ............................................ /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: save_interval ................................... 250 +[default0]: scatter_gather_tensors_in_pipeline .............. True +[default0]: scattered_embeddings ............................ False +[default0]: seed ............................................ 42 +[default0]: seq_length ...................................... 2048 +[default0]: sgd_momentum .................................... 0.9 +[default0]: short_seq_prob .................................. 0.1 +[default0]: skip_train_iteration_range ...................... None +[default0]: split ........................................... 969, 30, 1 +[default0]: split_transformers .............................. False +[default0]: sync_tp_duplicated_parameters ................... False +[default0]: synchronize_each_layer .......................... False +[default0]: tensor_model_parallel_size ...................... 2 +[default0]: tensorboard_dir ................................. /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/tr14-2B7-test-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/tensorboard/main +[default0]: tensorboard_log_interval ........................ 1 +[default0]: tensorboard_queue_size .......................... 5 +[default0]: test_weighted_split_names ....................... None +[default0]: test_weighted_split_paths ....................... None +[default0]: test_weighted_split_paths_path .................. None +[default0]: test_weighted_split_splits ...................... None +[default0]: test_weighted_split_weights ..................... None +[default0]: tile_factor ..................................... 1 +[default0]: titles_data_path ................................ None +[default0]: tokenizer_name_or_path .......................... t5-small +[default0]: tokenizer_type .................................. PretrainedFromHF +[default0]: train_iters ..................................... None +[default0]: train_samples ................................... 1953125 +[default0]: train_tokens .................................... None +[default0]: train_weighted_split_paths ...................... None +[default0]: train_weighted_split_paths_path ................. None +[default0]: universal_checkpoint ............................ False +[default0]: use_bnb_optimizer ............................... False +[default0]: use_checkpoint_lr_scheduler ..................... False +[default0]: use_contiguous_buffers_in_ddp ................... False +[default0]: use_cpu_initialization .......................... None +[default0]: use_one_sent_docs ............................... False +[default0]: use_pin_memory .................................. False +[default0]: valid_num_workers ............................... 2 +[default0]: valid_weighted_split_names ...................... None +[default0]: valid_weighted_split_paths ...................... None +[default0]: valid_weighted_split_paths_path ................. None +[default0]: valid_weighted_split_splits ..................... None +[default0]: valid_weighted_split_weights .................... None +[default0]: virtual_pipeline_model_parallel_size ............ None +[default0]: vocab_extra_ids ................................. 0 +[default0]: vocab_file ...................................... None +[default0]: weight_decay .................................... 0.1 +[default0]: world_size ...................................... 64 +[default0]: zero_allgather_bucket_size ...................... 0.0 +[default0]: zero_contigious_gradients ....................... False +[default0]: zero_reduce_bucket_size ......................... 0.0 +[default0]: zero_reduce_scatter ............................. False +[default0]: zero_stage ...................................... 1 +[default0]:-------------------- end of arguments --------------------- +[default0]:setting number of micro-batches to constant 1 +[default0]:> building PretrainedFromHF tokenizer ... +[default0]: vocab file is un-used. loading tokenizer from pre-trained model +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]: warnings.warn( +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default2]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default7]: warnings.warn( +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]: warnings.warn( +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]: warnings.warn( +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]: warnings.warn( +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:Model config T5Config { +[default0]: "_name_or_path": "t5-small", +[default0]: "architectures": [ +[default0]: "T5ForConditionalGeneration" +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]: ], +[default0]: "d_ff": 2048, +[default0]: "d_kv": 64, +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]: "d_model": 512, +[default0]: "decoder_start_token_id": 0, +[default0]: "dense_act_fn": "relu", +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default0]: "dropout_rate": 0.1, +[default0]: "eos_token_id": 1, +[default0]: "feed_forward_proj": "relu", +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: "initializer_factor": 1.0, +[default1]: warnings.warn( +[default0]: "is_encoder_decoder": true, +[default0]: "is_gated_act": false, +[default0]: "layer_norm_epsilon": 1e-06, +[default0]: "model_type": "t5", +[default0]: "n_positions": 512, +[default0]: "num_decoder_layers": 6, +[default0]: "num_heads": 8, +[default0]: "num_layers": 6, +[default0]: "output_past": true, +[default0]: "pad_token_id": 0, +[default0]: "relative_attention_max_distance": 128, +[default0]: "relative_attention_num_buckets": 32, +[default0]: "task_specific_params": { +[default0]: "summarization": { +[default0]: "early_stopping": true, +[default0]: "length_penalty": 2.0, +[default0]: "max_length": 200, +[default0]: "min_length": 30, +[default0]: "no_repeat_ngram_size": 3, +[default0]: "num_beams": 4, +[default0]: "prefix": "summarize: " +[default0]: }, +[default0]: "translation_en_to_de": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to German: " +[default0]: }, +[default0]: "translation_en_to_fr": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to French: " +[default0]: }, +[default0]: "translation_en_to_ro": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to Romanian: " +[default0]: } +[default0]: }, +[default0]: "transformers_version": "4.25.0.dev0", +[default0]: "use_cache": true, +[default0]: "vocab_size": 32128 +[default0]:} +[default0]: +[default0]:Offline mode: forcing local_files_only=True +[default0]:loading file spiece.model from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/spiece.model +[default0]:loading file tokenizer.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/tokenizer.json +[default0]:loading file added_tokens.json from cache at None +[default0]:loading file special_tokens_map.json from cache at None +[default0]:loading file tokenizer_config.json from cache at None +[default0]:loading configuration file config.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/config.json +[default0]:Model config T5Config { +[default0]: "_name_or_path": "t5-small", +[default0]: "architectures": [ +[default0]: "T5ForConditionalGeneration" +[default0]: ], +[default0]: "d_ff": 2048, +[default0]: "d_kv": 64, +[default0]: "d_model": 512, +[default0]: "decoder_start_token_id": 0, +[default0]: "dense_act_fn": "relu", +[default0]: "dropout_rate": 0.1, +[default0]: "eos_token_id": 1, +[default0]: "feed_forward_proj": "relu", +[default0]: "initializer_factor": 1.0, +[default0]: "is_encoder_decoder": true, +[default0]: "is_gated_act": false, +[default0]: "layer_norm_epsilon": 1e-06, +[default0]: "model_type": "t5", +[default0]: "n_positions": 512, +[default0]: "num_decoder_layers": 6, +[default0]: "num_heads": 8, +[default0]: "num_layers": 6, +[default0]: "output_past": true, +[default0]: "pad_token_id": 0, +[default0]: "relative_attention_max_distance": 128, +[default0]: "relative_attention_num_buckets": 32, +[default0]: "task_specific_params": { +[default0]: "summarization": { +[default0]: "early_stopping": true, +[default0]: "length_penalty": 2.0, +[default0]: "max_length": 200, +[default0]: "min_length": 30, +[default0]: "no_repeat_ngram_size": 3, +[default0]: "num_beams": 4, +[default0]: "prefix": "summarize: " +[default0]: }, +[default0]: "translation_en_to_de": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to German: " +[default0]: }, +[default0]: "translation_en_to_fr": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to French: " +[default0]: }, +[default0]: "translation_en_to_ro": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to Romanian: " +[default0]: } +[default0]: }, +[default0]: "transformers_version": "4.25.0.dev0", +[default0]: "use_cache": true, +[default0]: "vocab_size": 32128 +[default0]:} +[default0]: +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]: warnings.warn( +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default0]: > padded vocab (size: 32100) with 19100 dummy tokens (new size: 51200) +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default7]:> setting tensorboard ... +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default0]:DeepSpeed general environment info: +[default0]:torch install path ............... ['/gpfswork/rech/six/commun/conda/tr11-176B-ml/lib/python3.8/site-packages/torch'] +[default0]:torch version .................... 1.11.0+cu115 +[default0]:torch cuda version ............... 11.5 +[default0]:torch hip version ................ None +[default0]:nvcc version ..................... 11.4 +[default0]:deepspeed install path ........... ['/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/DeepSpeed/deepspeed'] +[default0]:deepspeed info ................... 0.7.2+2a644488, 2a644488, master +[default0]:deepspeed wheel compiled w. ...... torch 1.11, cuda 11.5 +[default0]:**** Git info for Megatron: git_hash=ef0c6b8 git_branch=mup_integration **** +[default0]:> initializing torch distributed ... +[default0]:[2023-02-16 11:19:54,313] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[default0]:> initializing tensor model parallel with size 2 +[default0]:> initializing pipeline model parallel with size 1 +[default0]:> setting random seeds to 42 ... +[default0]:[2023-02-16 11:19:57,244] [INFO] [checkpointing.py:226:model_parallel_cuda_manual_seed] > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 2760 and data parallel seed: 42 +[default0]:> compiling dataset index builder ... +[default0]:make: Entering directory '/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/data' +[default0]:make: Nothing to be done for 'default'. +[default0]:make: Leaving directory '/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/data' +[default0]:>>> done with dataset index builder. Compilation time: 0.086 seconds +[default0]:> compiling and loading fused kernels ... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module scaled_upper_triang_masked_softmax_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module scaled_upper_triang_masked_softmax_cuda... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module scaled_masked_softmax_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module scaled_masked_softmax_cuda... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module fused_mix_prec_layer_norm_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module fused_mix_prec_layer_norm_cuda... +[default0]:>>> done with compiling and loading fused kernels. Compilation time: 8.871 seconds +[default0]:time to initialize megatron (seconds): -41.798 +[default0]:[after megatron is initialized] datetime: 2023-02-16 11:20:06 +[default0]:building GPT model ... +[default0]:[2023-02-16 11:20:06,284] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 11:20:06,285] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +[default0]:[2023-02-16 11:20:06,285] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.39 GB, percent = 9.0% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 11:20:07,596] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 11:20:07,794] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 11:20:07,794] [INFO] [utils.py:828:see_memory_usage] MA 2.56 GB Max_MA 2.56 GB CA 2.62 GB Max_CA 3 GB +[default0]:[2023-02-16 11:20:07,795] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.92 GB, percent = 9.1% +[default0]:building GPT model ... +[default0]:[2023-02-16 11:20:07,857] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 11:20:07,858] [INFO] [utils.py:828:see_memory_usage] MA 2.56 GB Max_MA 2.56 GB CA 2.62 GB Max_CA 3 GB +[default0]:[2023-02-16 11:20:07,858] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.92 GB, percent = 9.1% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 11:20:09,168] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 11:20:09,272] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 11:20:09,273] [INFO] [utils.py:828:see_memory_usage] MA 2.57 GB Max_MA 2.57 GB CA 2.63 GB Max_CA 3 GB +[default0]:[2023-02-16 11:20:09,273] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.94 GB, percent = 9.1% +[default0]:building GPT model ... +[default0]:[2023-02-16 11:20:09,336] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 11:20:09,336] [INFO] [utils.py:828:see_memory_usage] MA 2.57 GB Max_MA 2.57 GB CA 2.63 GB Max_CA 3 GB +[default0]:[2023-02-16 11:20:09,336] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.94 GB, percent = 9.1% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 11:20:10,648] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 11:20:10,760] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 11:20:10,761] [INFO] [utils.py:828:see_memory_usage] MA 2.59 GB Max_MA 2.59 GB CA 2.66 GB Max_CA 3 GB +[default0]:[2023-02-16 11:20:10,761] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 45.95 GB, percent = 9.1% +[default0]:setting training iterations to 3814 +[default0]:> learning rate decay style: cosine +[default0]:DeepSpeed is enabled. +[default0]:[2023-02-16 11:20:10,797] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.2+2a644488, git-hash=2a644488, git-branch=master +[default0]:[2023-02-16 11:20:12,356] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +[default0]:[2023-02-16 11:20:12,356] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +[default0]:[2023-02-16 11:20:12,356] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +[default0]:[2023-02-16 11:20:12,369] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = {basic_optimizer.__class__.__name__} +[default0]:[2023-02-16 11:20:12,369] [INFO] [utils.py:52:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type= +[default0]:[2023-02-16 11:20:12,369] [INFO] [logging.py:68:log_dist] [Rank 0] Creating fp16 ZeRO stage 1 optimizer +[default0]:[2023-02-16 11:20:12,369] [INFO] [stage_1_and_2.py:134:__init__] Reduce bucket size 500000000 +[default0]:[2023-02-16 11:20:12,369] [INFO] [stage_1_and_2.py:135:__init__] Allgather bucket size 500000000 +[default0]:[2023-02-16 11:20:12,369] [INFO] [stage_1_and_2.py:136:__init__] CPU Offload: False +[default0]:[2023-02-16 11:20:12,369] [INFO] [stage_1_and_2.py:137:__init__] Round robin gradient partitioning: False +[default0]:Rank: 8 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 56 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 10 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 26 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 0 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 2 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 34 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 32 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 38 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 50 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 54 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 29 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 39 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 18 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 42 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 12 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 4 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 5 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 55 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 51 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 47 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 58 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 35 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 28 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 48 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 21 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 33 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 24 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 45 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 6 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 17 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 49 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 23 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 27 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 31 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 41 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 25 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 57 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 14 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 7 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 40 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 1 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 62 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 59 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 3 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 43 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 46 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 63 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 44 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 30 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 16 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 36 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 22 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 13 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 19 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 20 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 37 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 52 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 11 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 15 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 9 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 53 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 60 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 61 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:[2023-02-16 11:20:18,525] [INFO] [utils.py:827:see_memory_usage] Before initializing optimizer states +[default0]:[2023-02-16 11:20:18,525] [INFO] [utils.py:828:see_memory_usage] MA 2.66 GB Max_MA 2.69 GB CA 5.17 GB Max_CA 5 GB +[default0]:[2023-02-16 11:20:18,526] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 61.05 GB, percent = 12.1% +[default0]:[2023-02-16 11:20:18,633] [INFO] [utils.py:827:see_memory_usage] After initializing optimizer states +[default0]:[2023-02-16 11:20:18,634] [INFO] [utils.py:828:see_memory_usage] MA 2.96 GB Max_MA 3.12 GB CA 5.5 GB Max_CA 6 GB +[default0]:[2023-02-16 11:20:18,634] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 61.05 GB, percent = 12.1% +[default0]:[2023-02-16 11:20:18,634] [INFO] [stage_1_and_2.py:516:__init__] optimizer state initialized +[default0]:[2023-02-16 11:20:18,695] [INFO] [utils.py:827:see_memory_usage] After initializing ZeRO optimizer +[default0]:[2023-02-16 11:20:18,696] [INFO] [utils.py:828:see_memory_usage] MA 2.96 GB Max_MA 2.96 GB CA 5.5 GB Max_CA 6 GB +[default0]:[2023-02-16 11:20:18,696] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 61.05 GB, percent = 12.1% +[default0]:[2023-02-16 11:20:18,696] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +[default0]:[2023-02-16 11:20:18,696] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +[default0]:[2023-02-16 11:20:18,696] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +[default0]:[2023-02-16 11:20:18,696] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0, 0.0, 0.0, 0.0], mom=[(0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95)] +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:987:print] DeepSpeedEngine configuration: +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] activation_checkpointing_config { +[default0]: "partition_activations": false, +[default0]: "contiguous_memory_optimization": false, +[default0]: "cpu_checkpointing": false, +[default0]: "number_checkpoints": null, +[default0]: "synchronize_checkpoint_boundary": false, +[default0]: "profile": false +[default0]:} +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] amp_enabled .................. False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] amp_params ................... False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] autotuning_config ............ { +[default0]: "enabled": false, +[default0]: "start_step": null, +[default0]: "end_step": null, +[default0]: "metric_path": null, +[default0]: "arg_mappings": null, +[default0]: "metric": "throughput", +[default0]: "model_info": null, +[default0]: "results_dir": null, +[default0]: "exps_dir": null, +[default0]: "overwrite": true, +[default0]: "fast": true, +[default0]: "start_profile_step": 3, +[default0]: "end_profile_step": 5, +[default0]: "tuner_type": "gridsearch", +[default0]: "tuner_early_stopping": 5, +[default0]: "tuner_num_trials": 50, +[default0]: "model_info_path": null, +[default0]: "mp_size": 1, +[default0]: "max_train_batch_size": null, +[default0]: "min_train_batch_size": 1, +[default0]: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +[default0]: "min_train_micro_batch_size_per_gpu": 1, +[default0]: "num_tuning_micro_batch_sizes": 3 +[default0]:} +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] bfloat16_enabled ............. False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] checkpoint_tag_validation_enabled True +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] checkpoint_tag_validation_fail False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] comms_config ................. +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] communication_data_type ...... None +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] curriculum_enabled ........... False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] curriculum_params ............ False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] dataloader_drop_last ......... False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] disable_allgather ............ False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] dump_state ................... False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] dynamic_loss_scale_args ...... {'init_scale': 4096, 'scale_window': 500, 'delayed_shift': 2, 'min_scale': 1} +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] eigenvalue_enabled ........... False +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] eigenvalue_gas_boundary_resolution 1 +[default0]:[2023-02-16 11:20:18,697] [INFO] [config.py:991:print] eigenvalue_layer_name ........ bert.encoder.layer +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] eigenvalue_layer_num ......... 0 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] eigenvalue_max_iter .......... 100 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] eigenvalue_stability ......... 1e-06 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] eigenvalue_tol ............... 0.01 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] eigenvalue_verbose ........... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] elasticity_enabled ........... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] flops_profiler_config ........ { +[default0]: "enabled": false, +[default0]: "profile_step": 1, +[default0]: "module_depth": -1, +[default0]: "top_modules": 1, +[default0]: "detailed": true, +[default0]: "output_file": null +[default0]:} +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] fp16_auto_cast ............... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] fp16_enabled ................. True +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] fp16_master_weights_and_gradients False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] global_rank .................. 0 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] gradient_accumulation_steps .. 1 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] gradient_clipping ............ 1.0 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] gradient_predivide_factor .... 1.0 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] initial_dynamic_scale ........ 4096 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] load_universal_checkpoint .... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] loss_scale ................... 0 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] memory_breakdown ............. False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] monitor_config ............... +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] nebula_config ................ { +[default0]: "enabled": false, +[default0]: "persistent_storage_path": null, +[default0]: "persistent_time_interval": 100, +[default0]: "num_of_version_in_retention": 2, +[default0]: "enable_nebula_load": true, +[default0]: "load_path": null +[default0]:} +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] optimizer_legacy_fusion ...... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] optimizer_name ............... None +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] optimizer_params ............. None +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] pld_enabled .................. False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] pld_params ................... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] prescale_gradients ........... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] scheduler_name ............... None +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] scheduler_params ............. None +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] sparse_attention ............. None +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] sparse_gradients_enabled ..... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] steps_per_print .............. 2000 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] train_batch_size ............. 512 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] train_micro_batch_size_per_gpu 16 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] wall_clock_breakdown ......... False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] world_size ................... 32 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] zero_allow_untested_optimizer False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] zero_config .................. stage=1 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] zero_enabled ................. True +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:991:print] zero_optimization_stage ...... 1 +[default0]:[2023-02-16 11:20:18,698] [INFO] [config.py:976:print_user_config] json = { +[default0]: "train_micro_batch_size_per_gpu": 16, +[default0]: "train_batch_size": 512, +[default0]: "gradient_clipping": 1.0, +[default0]: "zero_optimization": { +[default0]: "stage": 1 +[default0]: }, +[default0]: "fp16": { +[default0]: "enabled": true, +[default0]: "loss_scale": 0, +[default0]: "loss_scale_window": 500, +[default0]: "hysteresis": 2, +[default0]: "min_loss_scale": 1, +[default0]: "initial_scale_power": 12 +[default0]: }, +[default0]: "steps_per_print": 2.000000e+03, +[default0]: "wall_clock_breakdown": false +[default0]:} +[default0]:[2023-02-16 11:20:18,698] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=16 +[default0]:[2023-02-16 11:20:18,981] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=41 [0, 41) STAGE_PARAMS=1324615680 (1324.616M) TOTAL_PARAMS=2649231360 (2649.231M) UNIQUE_PARAMS=2649231360 (2649.231M) +[default6]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,981] [INFO] [engine.py:145:__init__] RANK=1 STAGE=0 LAYERS=41 [0, 41) STAGE_PARAMS=1324615680 (1324.616M) TOTAL_PARAMS=2649231360 (2649.231M) UNIQUE_PARAMS=2649231360 (2649.231M) +[default1]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:time (ms) | load-checkpoint: 15.59 +[default1]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,994] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,998] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:18,988] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:WARNING: could not find the metadata file /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: will not load any checkpoints and will start from random +[default7]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 11:20:19,003] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 11:20:18,996] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 11:20:18,999] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:estimated model parameters: 2.64923136 +[default0]:estimated model parameters without embeddings: 2.51815936 +[default0]:/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +[default0]: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") +[default0]:[after model, optimizer, and learning rate scheduler are built] datetime: 2023-02-16 11:20:19 +[default0]:> building train, validation, and test datasets ... +[default0]: > datasets target sizes (minimum size): +[default0]: train: 1953125 +[default0]: validation: 2048 +[default0]: test: 512 +[default0]:> building train, validation, and test datasets for GPT ... +[default0]: > building dataset index ... +[default0]: reading sizes... +[default0]: reading pointers... +[default0]: reading document index... +[default0]: creating numpy buffer of mmap... +[default0]: creating memory view of numpy buffer... +[default0]: > finished creating indexed dataset in 0.261336 seconds +[default0]: number of documents: 364868892 +[default0]: > dataset split: +[default0]: train: +[default0]: document indices in [0, 353557956) total of 353557956 documents +[default0]: validation: +[default0]: document indices in [353557956, 364504023) total of 10946067 documents +[default0]: test: +[default0]: document indices in [364504023, 364868892) total of 364869 documents +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.045 seconds +[default0]: total number of samples: 82627993 +[default0]: total number of epochs: 1 +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.034 seconds +[default0]: total number of samples: 2558380 +[default0]: total number of epochs: 1 +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.008 seconds +[default0]: total number of samples: 84955 +[default0]: total number of epochs: 1 +[default0]:> finished creating GPT datasets ... +[default0]:[after dataloaders are built] datetime: 2023-02-16 11:20:29 +[default0]:done with setup ... +[default0]:training ... +[default0]:Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +[default0]:[000-000] 2.6492B / 2.5182B +[default1]:[001-000] 2.6492B / 2.5182B +[default7]:time (ms) | model-and-optimizer-setup: 12957.07 | train/valid/test-data-iterators-setup: 7649.41 +[default0]:[before the start of training step] datetime: 2023-02-16 11:20:29 +[default0]:[2023-02-16 11:20:29,161] [INFO] [checkpointing.py:547:forward] Activation Checkpointing Information +[default0]:[2023-02-16 11:20:29,161] [INFO] [checkpointing.py:548:forward] ----Partition Activations False, CPU CHECKPOINTING False +[default0]:[2023-02-16 11:20:29,161] [INFO] [checkpointing.py:551:forward] ----contiguous Memory Checkpointing False with 32 total layers +[default0]:[2023-02-16 11:20:29,161] [INFO] [checkpointing.py:554:forward] ----Synchronization False +[default0]:[2023-02-16 11:20:29,161] [INFO] [checkpointing.py:555:forward] ----Profiling time in checkpointing False +[default0]:[Rank 0] (after 1 iterations) memory (MB) | allocated: 6240.66552734375 | max allocated: 20946.41015625 | reserved: 24996.0 | max reserved: 24996.0 +[default7]: iteration 1/ 3814 | consumed samples: 512 | consumed tokens: 1048576 | elapsed time per iteration (s): 6.16 | learning rate: 4.754E-07 | global batch size: 512 | lm loss: 1.084328E+01 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.118 | TFLOPs: 62.78 | +[default1]:[Rank 1] (after 1 iterations) memory (MB) | allocated: 6264.68505859375 | max allocated: 20970.4296875 | reserved: 24998.0 | max reserved: 24998.0 +[default7]: iteration 2/ 3814 | consumed samples: 1024 | consumed tokens: 2097152 | elapsed time per iteration (s): 5.42 | learning rate: 9.507E-07 | global batch size: 512 | lm loss: 1.084320E+01 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.457 | TFLOPs: 71.34 | +[default7]: iteration 3/ 3814 | consumed samples: 1536 | consumed tokens: 3145728 | elapsed time per iteration (s): 5.38 | learning rate: 1.426E-06 | global batch size: 512 | lm loss: 1.084324E+01 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.154 | TFLOPs: 71.87 | +[default7]: iteration 4/ 3814 | consumed samples: 2048 | consumed tokens: 4194304 | elapsed time per iteration (s): 5.37 | learning rate: 1.901E-06 | global batch size: 512 | lm loss: 1.084302E+01 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.290 | TFLOPs: 71.97 | +[default7]: iteration 5/ 3814 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 5.39 | learning rate: 2.377E-06 | global batch size: 512 | lm loss: 1.084248E+01 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.011 | TFLOPs: 71.76 | +[default7]: iteration 6/ 3814 | consumed samples: 3072 | consumed tokens: 6291456 | elapsed time per iteration (s): 5.43 | learning rate: 2.852E-06 | global batch size: 512 | lm loss: 1.084069E+01 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.319 | TFLOPs: 71.24 | +[default7]: iteration 7/ 3814 | consumed samples: 3584 | consumed tokens: 7340032 | elapsed time per iteration (s): 5.38 | learning rate: 3.327E-06 | global batch size: 512 | lm loss: 1.083979E+01 | loss scale: 4096.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.218 | TFLOPs: 71.92 | +[default7]: iteration 8/ 3814 | consumed samples: 4096 | consumed tokens: 8388608 | elapsed time per iteration (s): 5.38 | learning rate: 3.803E-06 | global batch size: 512 | lm loss: 1.083438E+01 | loss scale: 4096.0 | grad norm: 0.091 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.120 | TFLOPs: 71.85 | +[default7]: iteration 9/ 3814 | consumed samples: 4608 | consumed tokens: 9437184 | elapsed time per iteration (s): 5.37 | learning rate: 4.278E-06 | global batch size: 512 | lm loss: 1.083210E+01 | loss scale: 4096.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.372 | TFLOPs: 72.04 | +[default7]: iteration 10/ 3814 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 5.37 | learning rate: 4.754E-06 | global batch size: 512 | lm loss: 1.082176E+01 | loss scale: 4096.0 | grad norm: 0.076 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.317 | TFLOPs: 71.99 | +[default7]: iteration 11/ 3814 | consumed samples: 5632 | consumed tokens: 11534336 | elapsed time per iteration (s): 5.39 | learning rate: 5.229E-06 | global batch size: 512 | lm loss: 1.081894E+01 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.065 | TFLOPs: 71.80 | +[default7]: iteration 12/ 3814 | consumed samples: 6144 | consumed tokens: 12582912 | elapsed time per iteration (s): 5.38 | learning rate: 5.704E-06 | global batch size: 512 | lm loss: 1.081455E+01 | loss scale: 4096.0 | grad norm: 0.064 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.195 | TFLOPs: 71.90 | +[default7]: iteration 13/ 3814 | consumed samples: 6656 | consumed tokens: 13631488 | elapsed time per iteration (s): 5.38 | learning rate: 6.180E-06 | global batch size: 512 | lm loss: 1.081005E+01 | loss scale: 4096.0 | grad norm: 0.058 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.144 | TFLOPs: 71.86 | +[default7]: iteration 14/ 3814 | consumed samples: 7168 | consumed tokens: 14680064 | elapsed time per iteration (s): 5.38 | learning rate: 6.655E-06 | global batch size: 512 | lm loss: 1.080552E+01 | loss scale: 4096.0 | grad norm: 0.054 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.143 | TFLOPs: 71.86 | +[default7]: iteration 15/ 3814 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 5.39 | learning rate: 7.130E-06 | global batch size: 512 | lm loss: 1.080225E+01 | loss scale: 4096.0 | grad norm: 0.049 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.936 | TFLOPs: 71.71 | +[default7]: iteration 16/ 3814 | consumed samples: 8192 | consumed tokens: 16777216 | elapsed time per iteration (s): 5.38 | learning rate: 7.606E-06 | global batch size: 512 | lm loss: 1.079723E+01 | loss scale: 4096.0 | grad norm: 0.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.147 | TFLOPs: 71.87 | +[default7]: iteration 17/ 3814 | consumed samples: 8704 | consumed tokens: 17825792 | elapsed time per iteration (s): 5.37 | learning rate: 8.081E-06 | global batch size: 512 | lm loss: 1.079337E+01 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.302 | TFLOPs: 71.98 | +[default7]: iteration 18/ 3814 | consumed samples: 9216 | consumed tokens: 18874368 | elapsed time per iteration (s): 5.37 | learning rate: 8.556E-06 | global batch size: 512 | lm loss: 1.079106E+01 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.295 | TFLOPs: 71.98 | +[default7]: iteration 19/ 3814 | consumed samples: 9728 | consumed tokens: 19922944 | elapsed time per iteration (s): 5.36 | learning rate: 9.032E-06 | global batch size: 512 | lm loss: 1.078864E+01 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.440 | TFLOPs: 72.09 | +[default7]: iteration 20/ 3814 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 5.38 | learning rate: 9.507E-06 | global batch size: 512 | lm loss: 1.078458E+01 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.094 | TFLOPs: 71.83 | +[default7]: iteration 21/ 3814 | consumed samples: 10752 | consumed tokens: 22020096 | elapsed time per iteration (s): 5.39 | learning rate: 9.982E-06 | global batch size: 512 | lm loss: 1.078086E+01 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.060 | TFLOPs: 71.80 | +[default7]: iteration 22/ 3814 | consumed samples: 11264 | consumed tokens: 23068672 | elapsed time per iteration (s): 5.38 | learning rate: 1.046E-05 | global batch size: 512 | lm loss: 1.077795E+01 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.215 | TFLOPs: 71.92 | +[default7]: iteration 23/ 3814 | consumed samples: 11776 | consumed tokens: 24117248 | elapsed time per iteration (s): 5.38 | learning rate: 1.093E-05 | global batch size: 512 | lm loss: 1.077451E+01 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.123 | TFLOPs: 71.85 | +[default7]: iteration 24/ 3814 | consumed samples: 12288 | consumed tokens: 25165824 | elapsed time per iteration (s): 5.37 | learning rate: 1.141E-05 | global batch size: 512 | lm loss: 1.077104E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.370 | TFLOPs: 72.03 | +[default7]: iteration 25/ 3814 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 5.37 | learning rate: 1.188E-05 | global batch size: 512 | lm loss: 1.076886E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.358 | TFLOPs: 72.02 | +[default7]: iteration 26/ 3814 | consumed samples: 13312 | consumed tokens: 27262976 | elapsed time per iteration (s): 5.36 | learning rate: 1.236E-05 | global batch size: 512 | lm loss: 1.076521E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.456 | TFLOPs: 72.10 | +[default7]: iteration 27/ 3814 | consumed samples: 13824 | consumed tokens: 28311552 | elapsed time per iteration (s): 5.39 | learning rate: 1.283E-05 | global batch size: 512 | lm loss: 1.076285E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.018 | TFLOPs: 71.77 | +[default7]: iteration 28/ 3814 | consumed samples: 14336 | consumed tokens: 29360128 | elapsed time per iteration (s): 5.36 | learning rate: 1.331E-05 | global batch size: 512 | lm loss: 1.076069E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.497 | TFLOPs: 72.13 | +[default7]: iteration 29/ 3814 | consumed samples: 14848 | consumed tokens: 30408704 | elapsed time per iteration (s): 5.37 | learning rate: 1.379E-05 | global batch size: 512 | lm loss: 1.075811E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.333 | TFLOPs: 72.01 | +[default7]: iteration 30/ 3814 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 5.36 | learning rate: 1.426E-05 | global batch size: 512 | lm loss: 1.075518E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.439 | TFLOPs: 72.09 | +[default7]: iteration 31/ 3814 | consumed samples: 15872 | consumed tokens: 32505856 | elapsed time per iteration (s): 5.43 | learning rate: 1.474E-05 | global batch size: 512 | lm loss: 1.075355E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 32/ 3814 | consumed samples: 16384 | consumed tokens: 33554432 | elapsed time per iteration (s): 5.39 | learning rate: 1.521E-05 | global batch size: 512 | lm loss: 1.075085E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.903 | TFLOPs: 71.68 | +[default7]: iteration 33/ 3814 | consumed samples: 16896 | consumed tokens: 34603008 | elapsed time per iteration (s): 5.40 | learning rate: 1.569E-05 | global batch size: 512 | lm loss: 1.074883E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.838 | TFLOPs: 71.63 | +[default7]: iteration 34/ 3814 | consumed samples: 17408 | consumed tokens: 35651584 | elapsed time per iteration (s): 5.40 | learning rate: 1.616E-05 | global batch size: 512 | lm loss: 1.074669E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.789 | TFLOPs: 71.60 | +[default7]: iteration 35/ 3814 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 5.40 | learning rate: 1.664E-05 | global batch size: 512 | lm loss: 1.074419E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.749 | TFLOPs: 71.57 | +[default7]: iteration 36/ 3814 | consumed samples: 18432 | consumed tokens: 37748736 | elapsed time per iteration (s): 5.40 | learning rate: 1.711E-05 | global batch size: 512 | lm loss: 1.074182E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.806 | TFLOPs: 71.61 | +[default7]: iteration 37/ 3814 | consumed samples: 18944 | consumed tokens: 38797312 | elapsed time per iteration (s): 5.41 | learning rate: 1.759E-05 | global batch size: 512 | lm loss: 1.074025E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.695 | TFLOPs: 71.52 | +[default7]: iteration 38/ 3814 | consumed samples: 19456 | consumed tokens: 39845888 | elapsed time per iteration (s): 5.42 | learning rate: 1.806E-05 | global batch size: 512 | lm loss: 1.073719E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.409 | TFLOPs: 71.31 | +[default7]: iteration 39/ 3814 | consumed samples: 19968 | consumed tokens: 40894464 | elapsed time per iteration (s): 5.39 | learning rate: 1.854E-05 | global batch size: 512 | lm loss: 1.073600E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.068 | TFLOPs: 71.81 | +[default7]: iteration 40/ 3814 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 5.40 | learning rate: 1.901E-05 | global batch size: 512 | lm loss: 1.073332E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.841 | TFLOPs: 71.63 | +[default7]: iteration 41/ 3814 | consumed samples: 20992 | consumed tokens: 42991616 | elapsed time per iteration (s): 5.39 | learning rate: 1.949E-05 | global batch size: 512 | lm loss: 1.073025E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.978 | TFLOPs: 71.74 | +[default7]: iteration 42/ 3814 | consumed samples: 21504 | consumed tokens: 44040192 | elapsed time per iteration (s): 5.38 | learning rate: 1.996E-05 | global batch size: 512 | lm loss: 1.072812E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.131 | TFLOPs: 71.85 | +[default7]: iteration 43/ 3814 | consumed samples: 22016 | consumed tokens: 45088768 | elapsed time per iteration (s): 5.37 | learning rate: 2.044E-05 | global batch size: 512 | lm loss: 1.072581E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.309 | TFLOPs: 71.99 | +[default7]: iteration 44/ 3814 | consumed samples: 22528 | consumed tokens: 46137344 | elapsed time per iteration (s): 5.35 | learning rate: 2.092E-05 | global batch size: 512 | lm loss: 1.072360E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.644 | TFLOPs: 72.24 | +[default7]: iteration 45/ 3814 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 5.37 | learning rate: 2.139E-05 | global batch size: 512 | lm loss: 1.072152E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.283 | TFLOPs: 71.97 | +[default7]: iteration 46/ 3814 | consumed samples: 23552 | consumed tokens: 48234496 | elapsed time per iteration (s): 5.37 | learning rate: 2.187E-05 | global batch size: 512 | lm loss: 1.071877E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.416 | TFLOPs: 72.07 | +[default7]: iteration 47/ 3814 | consumed samples: 24064 | consumed tokens: 49283072 | elapsed time per iteration (s): 5.39 | learning rate: 2.234E-05 | global batch size: 512 | lm loss: 1.071607E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.931 | TFLOPs: 71.70 | +[default7]: iteration 48/ 3814 | consumed samples: 24576 | consumed tokens: 50331648 | elapsed time per iteration (s): 5.39 | learning rate: 2.282E-05 | global batch size: 512 | lm loss: 1.071350E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.917 | TFLOPs: 71.69 | +[default7]: iteration 49/ 3814 | consumed samples: 25088 | consumed tokens: 51380224 | elapsed time per iteration (s): 5.42 | learning rate: 2.329E-05 | global batch size: 512 | lm loss: 1.071080E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 50/ 3814 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 5.41 | learning rate: 2.377E-05 | global batch size: 512 | lm loss: 1.070809E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.556 | TFLOPs: 71.42 | +[default7]: iteration 51/ 3814 | consumed samples: 26112 | consumed tokens: 53477376 | elapsed time per iteration (s): 5.38 | learning rate: 2.424E-05 | global batch size: 512 | lm loss: 1.070510E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.175 | TFLOPs: 71.89 | +[default7]: iteration 52/ 3814 | consumed samples: 26624 | consumed tokens: 54525952 | elapsed time per iteration (s): 5.37 | learning rate: 2.472E-05 | global batch size: 512 | lm loss: 1.070216E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.296 | TFLOPs: 71.98 | +[default7]: iteration 53/ 3814 | consumed samples: 27136 | consumed tokens: 55574528 | elapsed time per iteration (s): 5.38 | learning rate: 2.519E-05 | global batch size: 512 | lm loss: 1.069923E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.249 | TFLOPs: 71.94 | +[default7]: iteration 54/ 3814 | consumed samples: 27648 | consumed tokens: 56623104 | elapsed time per iteration (s): 5.39 | learning rate: 2.567E-05 | global batch size: 512 | lm loss: 1.069630E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.070 | TFLOPs: 71.81 | +[default7]: iteration 55/ 3814 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 5.38 | learning rate: 2.614E-05 | global batch size: 512 | lm loss: 1.069319E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.083 | TFLOPs: 71.82 | +[default7]: iteration 56/ 3814 | consumed samples: 28672 | consumed tokens: 58720256 | elapsed time per iteration (s): 5.43 | learning rate: 2.662E-05 | global batch size: 512 | lm loss: 1.068885E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.302 | TFLOPs: 71.23 | +[default7]: iteration 57/ 3814 | consumed samples: 29184 | consumed tokens: 59768832 | elapsed time per iteration (s): 5.38 | learning rate: 2.710E-05 | global batch size: 512 | lm loss: 1.068555E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.160 | TFLOPs: 71.88 | +[default7]: iteration 58/ 3814 | consumed samples: 29696 | consumed tokens: 60817408 | elapsed time per iteration (s): 5.41 | learning rate: 2.757E-05 | global batch size: 512 | lm loss: 1.068158E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.712 | TFLOPs: 71.54 | +[default7]: iteration 59/ 3814 | consumed samples: 30208 | consumed tokens: 61865984 | elapsed time per iteration (s): 5.39 | learning rate: 2.805E-05 | global batch size: 512 | lm loss: 1.067747E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.948 | TFLOPs: 71.72 | +[default7]: iteration 60/ 3814 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 5.38 | learning rate: 2.852E-05 | global batch size: 512 | lm loss: 1.067455E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.154 | TFLOPs: 71.87 | +[default7]: iteration 61/ 3814 | consumed samples: 31232 | consumed tokens: 63963136 | elapsed time per iteration (s): 5.39 | learning rate: 2.900E-05 | global batch size: 512 | lm loss: 1.067030E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.990 | TFLOPs: 71.75 | +[default7]: iteration 62/ 3814 | consumed samples: 31744 | consumed tokens: 65011712 | elapsed time per iteration (s): 5.42 | learning rate: 2.947E-05 | global batch size: 512 | lm loss: 1.066732E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.496 | TFLOPs: 71.37 | +[default7]: iteration 63/ 3814 | consumed samples: 32256 | consumed tokens: 66060288 | elapsed time per iteration (s): 5.41 | learning rate: 2.995E-05 | global batch size: 512 | lm loss: 1.066153E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.693 | TFLOPs: 71.52 | +[default7]: iteration 64/ 3814 | consumed samples: 32768 | consumed tokens: 67108864 | elapsed time per iteration (s): 5.43 | learning rate: 3.042E-05 | global batch size: 512 | lm loss: 1.065868E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.224 | TFLOPs: 71.17 | +[default7]: iteration 65/ 3814 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 5.39 | learning rate: 3.090E-05 | global batch size: 512 | lm loss: 1.065498E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.929 | TFLOPs: 71.70 | +[default7]: iteration 66/ 3814 | consumed samples: 33792 | consumed tokens: 69206016 | elapsed time per iteration (s): 5.39 | learning rate: 3.137E-05 | global batch size: 512 | lm loss: 1.065073E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.936 | TFLOPs: 71.71 | +[default7]: iteration 67/ 3814 | consumed samples: 34304 | consumed tokens: 70254592 | elapsed time per iteration (s): 5.39 | learning rate: 3.185E-05 | global batch size: 512 | lm loss: 1.064694E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.040 | TFLOPs: 71.78 | +[default7]: iteration 68/ 3814 | consumed samples: 34816 | consumed tokens: 71303168 | elapsed time per iteration (s): 5.38 | learning rate: 3.232E-05 | global batch size: 512 | lm loss: 1.064217E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.147 | TFLOPs: 71.87 | +[default7]: iteration 69/ 3814 | consumed samples: 35328 | consumed tokens: 72351744 | elapsed time per iteration (s): 5.39 | learning rate: 3.280E-05 | global batch size: 512 | lm loss: 1.063674E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.039 | TFLOPs: 71.78 | +[default7]: iteration 70/ 3814 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 5.35 | learning rate: 3.327E-05 | global batch size: 512 | lm loss: 1.063442E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.711 | TFLOPs: 72.29 | +[default7]: iteration 71/ 3814 | consumed samples: 36352 | consumed tokens: 74448896 | elapsed time per iteration (s): 5.35 | learning rate: 3.375E-05 | global batch size: 512 | lm loss: 1.062991E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.625 | TFLOPs: 72.23 | +[default7]: iteration 72/ 3814 | consumed samples: 36864 | consumed tokens: 75497472 | elapsed time per iteration (s): 5.34 | learning rate: 3.423E-05 | global batch size: 512 | lm loss: 1.062466E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.838 | TFLOPs: 72.39 | +[default7]: iteration 73/ 3814 | consumed samples: 37376 | consumed tokens: 76546048 | elapsed time per iteration (s): 5.34 | learning rate: 3.470E-05 | global batch size: 512 | lm loss: 1.061906E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.939 | TFLOPs: 72.46 | +[default7]: iteration 74/ 3814 | consumed samples: 37888 | consumed tokens: 77594624 | elapsed time per iteration (s): 5.34 | learning rate: 3.518E-05 | global batch size: 512 | lm loss: 1.061579E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.807 | TFLOPs: 72.36 | +[default7]: iteration 75/ 3814 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 5.35 | learning rate: 3.565E-05 | global batch size: 512 | lm loss: 1.060981E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.784 | TFLOPs: 72.35 | +[default7]: iteration 76/ 3814 | consumed samples: 38912 | consumed tokens: 79691776 | elapsed time per iteration (s): 5.34 | learning rate: 3.613E-05 | global batch size: 512 | lm loss: 1.060591E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.955 | TFLOPs: 72.48 | +[default7]: iteration 77/ 3814 | consumed samples: 39424 | consumed tokens: 80740352 | elapsed time per iteration (s): 5.35 | learning rate: 3.660E-05 | global batch size: 512 | lm loss: 1.060146E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.764 | TFLOPs: 72.33 | +[default7]: iteration 78/ 3814 | consumed samples: 39936 | consumed tokens: 81788928 | elapsed time per iteration (s): 5.37 | learning rate: 3.708E-05 | global batch size: 512 | lm loss: 1.059575E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.374 | TFLOPs: 72.04 | +[default7]: iteration 79/ 3814 | consumed samples: 40448 | consumed tokens: 82837504 | elapsed time per iteration (s): 5.35 | learning rate: 3.755E-05 | global batch size: 512 | lm loss: 1.059123E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.714 | TFLOPs: 72.29 | +[default7]: iteration 80/ 3814 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 5.37 | learning rate: 3.803E-05 | global batch size: 512 | lm loss: 1.058662E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.279 | TFLOPs: 71.97 | +[default7]: iteration 81/ 3814 | consumed samples: 41472 | consumed tokens: 84934656 | elapsed time per iteration (s): 5.33 | learning rate: 3.850E-05 | global batch size: 512 | lm loss: 1.058027E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.033 | TFLOPs: 72.53 | +[default7]: iteration 82/ 3814 | consumed samples: 41984 | consumed tokens: 85983232 | elapsed time per iteration (s): 5.33 | learning rate: 3.898E-05 | global batch size: 512 | lm loss: 1.057597E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.108 | TFLOPs: 72.59 | +[default7]: iteration 83/ 3814 | consumed samples: 42496 | consumed tokens: 87031808 | elapsed time per iteration (s): 5.33 | learning rate: 3.945E-05 | global batch size: 512 | lm loss: 1.056938E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.115 | TFLOPs: 72.60 | +[default7]: iteration 84/ 3814 | consumed samples: 43008 | consumed tokens: 88080384 | elapsed time per iteration (s): 5.34 | learning rate: 3.993E-05 | global batch size: 512 | lm loss: 1.056280E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.928 | TFLOPs: 72.46 | +[default7]: iteration 85/ 3814 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 5.32 | learning rate: 4.041E-05 | global batch size: 512 | lm loss: 1.056057E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.219 | TFLOPs: 72.68 | +[default7]: iteration 86/ 3814 | consumed samples: 44032 | consumed tokens: 90177536 | elapsed time per iteration (s): 5.34 | learning rate: 4.088E-05 | global batch size: 512 | lm loss: 1.055226E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.855 | TFLOPs: 72.40 | +[default7]: iteration 87/ 3814 | consumed samples: 44544 | consumed tokens: 91226112 | elapsed time per iteration (s): 5.34 | learning rate: 4.136E-05 | global batch size: 512 | lm loss: 1.054877E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.951 | TFLOPs: 72.47 | +[default7]: iteration 88/ 3814 | consumed samples: 45056 | consumed tokens: 92274688 | elapsed time per iteration (s): 5.32 | learning rate: 4.183E-05 | global batch size: 512 | lm loss: 1.054221E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.154 | TFLOPs: 72.63 | +[default7]: iteration 89/ 3814 | consumed samples: 45568 | consumed tokens: 93323264 | elapsed time per iteration (s): 5.33 | learning rate: 4.231E-05 | global batch size: 512 | lm loss: 1.053449E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.029 | TFLOPs: 72.53 | +[default7]: iteration 90/ 3814 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 5.32 | learning rate: 4.278E-05 | global batch size: 512 | lm loss: 1.052947E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.265 | TFLOPs: 72.71 | +[default7]: iteration 91/ 3814 | consumed samples: 46592 | consumed tokens: 95420416 | elapsed time per iteration (s): 5.34 | learning rate: 4.326E-05 | global batch size: 512 | lm loss: 1.052496E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.953 | TFLOPs: 72.47 | +[default7]: iteration 92/ 3814 | consumed samples: 47104 | consumed tokens: 96468992 | elapsed time per iteration (s): 5.32 | learning rate: 4.373E-05 | global batch size: 512 | lm loss: 1.051835E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.329 | TFLOPs: 72.76 | +[default7]: iteration 93/ 3814 | consumed samples: 47616 | consumed tokens: 97517568 | elapsed time per iteration (s): 5.32 | learning rate: 4.421E-05 | global batch size: 512 | lm loss: 1.051185E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.302 | TFLOPs: 72.74 | +[default7]: iteration 94/ 3814 | consumed samples: 48128 | consumed tokens: 98566144 | elapsed time per iteration (s): 5.33 | learning rate: 4.468E-05 | global batch size: 512 | lm loss: 1.050574E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.011 | TFLOPs: 72.52 | +[default7]: iteration 95/ 3814 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 5.35 | learning rate: 4.516E-05 | global batch size: 512 | lm loss: 1.050155E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.673 | TFLOPs: 72.26 | +[default7]: iteration 96/ 3814 | consumed samples: 49152 | consumed tokens: 100663296 | elapsed time per iteration (s): 5.33 | learning rate: 4.563E-05 | global batch size: 512 | lm loss: 1.049307E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.032 | TFLOPs: 72.53 | +[default7]: iteration 97/ 3814 | consumed samples: 49664 | consumed tokens: 101711872 | elapsed time per iteration (s): 5.32 | learning rate: 4.611E-05 | global batch size: 512 | lm loss: 1.048800E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.320 | TFLOPs: 72.75 | +[default7]: iteration 98/ 3814 | consumed samples: 50176 | consumed tokens: 102760448 | elapsed time per iteration (s): 5.32 | learning rate: 4.658E-05 | global batch size: 512 | lm loss: 1.048090E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.221 | TFLOPs: 72.68 | +[default7]: iteration 99/ 3814 | consumed samples: 50688 | consumed tokens: 103809024 | elapsed time per iteration (s): 5.32 | learning rate: 4.706E-05 | global batch size: 512 | lm loss: 1.047610E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.214 | TFLOPs: 72.67 | +[default7]: iteration 100/ 3814 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 5.34 | learning rate: 4.754E-05 | global batch size: 512 | lm loss: 1.047046E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.892 | TFLOPs: 72.43 | +[default7]: iteration 101/ 3814 | consumed samples: 51712 | consumed tokens: 105906176 | elapsed time per iteration (s): 5.34 | learning rate: 4.801E-05 | global batch size: 512 | lm loss: 1.046378E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.913 | TFLOPs: 72.44 | +[default7]: iteration 102/ 3814 | consumed samples: 52224 | consumed tokens: 106954752 | elapsed time per iteration (s): 5.34 | learning rate: 4.849E-05 | global batch size: 512 | lm loss: 1.045678E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.859 | TFLOPs: 72.40 | +[default7]: iteration 103/ 3814 | consumed samples: 52736 | consumed tokens: 108003328 | elapsed time per iteration (s): 5.37 | learning rate: 4.896E-05 | global batch size: 512 | lm loss: 1.044723E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.386 | TFLOPs: 72.05 | +[default7]: iteration 104/ 3814 | consumed samples: 53248 | consumed tokens: 109051904 | elapsed time per iteration (s): 5.34 | learning rate: 4.944E-05 | global batch size: 512 | lm loss: 1.044250E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.896 | TFLOPs: 72.43 | +[default7]: iteration 105/ 3814 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 5.32 | learning rate: 4.991E-05 | global batch size: 512 | lm loss: 1.043619E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.250 | TFLOPs: 72.70 | +[default7]: iteration 106/ 3814 | consumed samples: 54272 | consumed tokens: 111149056 | elapsed time per iteration (s): 5.33 | learning rate: 5.039E-05 | global batch size: 512 | lm loss: 1.042880E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.043 | TFLOPs: 72.54 | +[default7]: iteration 107/ 3814 | consumed samples: 54784 | consumed tokens: 112197632 | elapsed time per iteration (s): 5.36 | learning rate: 5.086E-05 | global batch size: 512 | lm loss: 1.042221E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.482 | TFLOPs: 72.12 | +[default7]: iteration 108/ 3814 | consumed samples: 55296 | consumed tokens: 113246208 | elapsed time per iteration (s): 5.34 | learning rate: 5.134E-05 | global batch size: 512 | lm loss: 1.041657E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.911 | TFLOPs: 72.44 | +[default7]: iteration 109/ 3814 | consumed samples: 55808 | consumed tokens: 114294784 | elapsed time per iteration (s): 5.36 | learning rate: 5.181E-05 | global batch size: 512 | lm loss: 1.040618E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.535 | TFLOPs: 72.16 | +[default7]: iteration 110/ 3814 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 5.33 | learning rate: 5.229E-05 | global batch size: 512 | lm loss: 1.040442E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.095 | TFLOPs: 72.58 | +[default7]: iteration 111/ 3814 | consumed samples: 56832 | consumed tokens: 116391936 | elapsed time per iteration (s): 5.33 | learning rate: 5.276E-05 | global batch size: 512 | lm loss: 1.039491E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.078 | TFLOPs: 72.57 | +[default7]: iteration 112/ 3814 | consumed samples: 57344 | consumed tokens: 117440512 | elapsed time per iteration (s): 5.31 | learning rate: 5.324E-05 | global batch size: 512 | lm loss: 1.038871E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.405 | TFLOPs: 72.82 | +[default7]: iteration 113/ 3814 | consumed samples: 57856 | consumed tokens: 118489088 | elapsed time per iteration (s): 5.33 | learning rate: 5.372E-05 | global batch size: 512 | lm loss: 1.038044E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.002 | TFLOPs: 72.51 | +[default7]: iteration 114/ 3814 | consumed samples: 58368 | consumed tokens: 119537664 | elapsed time per iteration (s): 5.36 | learning rate: 5.419E-05 | global batch size: 512 | lm loss: 1.037405E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.483 | TFLOPs: 72.12 | +[default7]: iteration 115/ 3814 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 5.31 | learning rate: 5.467E-05 | global batch size: 512 | lm loss: 1.036740E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.483 | TFLOPs: 72.87 | +[default7]: iteration 116/ 3814 | consumed samples: 59392 | consumed tokens: 121634816 | elapsed time per iteration (s): 5.32 | learning rate: 5.514E-05 | global batch size: 512 | lm loss: 1.036261E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.248 | TFLOPs: 72.70 | +[default7]: iteration 117/ 3814 | consumed samples: 59904 | consumed tokens: 122683392 | elapsed time per iteration (s): 5.34 | learning rate: 5.562E-05 | global batch size: 512 | lm loss: 1.035035E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.937 | TFLOPs: 72.46 | +[default7]: iteration 118/ 3814 | consumed samples: 60416 | consumed tokens: 123731968 | elapsed time per iteration (s): 5.34 | learning rate: 5.609E-05 | global batch size: 512 | lm loss: 1.034326E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.965 | TFLOPs: 72.48 | +[default7]: iteration 119/ 3814 | consumed samples: 60928 | consumed tokens: 124780544 | elapsed time per iteration (s): 5.33 | learning rate: 5.657E-05 | global batch size: 512 | lm loss: 1.033530E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.992 | TFLOPs: 72.50 | +[default7]: iteration 120/ 3814 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 5.33 | learning rate: 5.704E-05 | global batch size: 512 | lm loss: 1.032825E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.026 | TFLOPs: 72.53 | +[default7]: iteration 121/ 3814 | consumed samples: 61952 | consumed tokens: 126877696 | elapsed time per iteration (s): 5.36 | learning rate: 5.752E-05 | global batch size: 512 | lm loss: 1.031956E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.593 | TFLOPs: 72.20 | +[default7]: iteration 122/ 3814 | consumed samples: 62464 | consumed tokens: 127926272 | elapsed time per iteration (s): 5.33 | learning rate: 5.799E-05 | global batch size: 512 | lm loss: 1.031272E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.026 | TFLOPs: 72.53 | +[default7]: iteration 123/ 3814 | consumed samples: 62976 | consumed tokens: 128974848 | elapsed time per iteration (s): 5.35 | learning rate: 5.847E-05 | global batch size: 512 | lm loss: 1.030508E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.728 | TFLOPs: 72.30 | +[default7]: iteration 124/ 3814 | consumed samples: 63488 | consumed tokens: 130023424 | elapsed time per iteration (s): 5.37 | learning rate: 5.894E-05 | global batch size: 512 | lm loss: 1.029760E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.345 | TFLOPs: 72.01 | +[default7]: iteration 125/ 3814 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 5.33 | learning rate: 5.942E-05 | global batch size: 512 | lm loss: 1.029041E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.991 | TFLOPs: 72.50 | +[default7]: iteration 126/ 3814 | consumed samples: 64512 | consumed tokens: 132120576 | elapsed time per iteration (s): 5.33 | learning rate: 5.989E-05 | global batch size: 512 | lm loss: 1.027877E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.139 | TFLOPs: 72.61 | +[default7]: iteration 127/ 3814 | consumed samples: 65024 | consumed tokens: 133169152 | elapsed time per iteration (s): 5.33 | learning rate: 6.037E-05 | global batch size: 512 | lm loss: 1.027242E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.091 | TFLOPs: 72.58 | +[default7]: iteration 128/ 3814 | consumed samples: 65536 | consumed tokens: 134217728 | elapsed time per iteration (s): 5.33 | learning rate: 6.085E-05 | global batch size: 512 | lm loss: 1.026612E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.048 | TFLOPs: 72.55 | +[default7]: iteration 129/ 3814 | consumed samples: 66048 | consumed tokens: 135266304 | elapsed time per iteration (s): 5.31 | learning rate: 6.132E-05 | global batch size: 512 | lm loss: 1.025563E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.438 | TFLOPs: 72.84 | +[default7]: iteration 130/ 3814 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 5.31 | learning rate: 6.180E-05 | global batch size: 512 | lm loss: 1.024653E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.389 | TFLOPs: 72.80 | +[default7]: iteration 131/ 3814 | consumed samples: 67072 | consumed tokens: 137363456 | elapsed time per iteration (s): 5.30 | learning rate: 6.227E-05 | global batch size: 512 | lm loss: 1.024000E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.527 | TFLOPs: 72.91 | +[default7]: iteration 132/ 3814 | consumed samples: 67584 | consumed tokens: 138412032 | elapsed time per iteration (s): 5.30 | learning rate: 6.275E-05 | global batch size: 512 | lm loss: 1.022939E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.579 | TFLOPs: 72.95 | +[default7]: iteration 133/ 3814 | consumed samples: 68096 | consumed tokens: 139460608 | elapsed time per iteration (s): 5.31 | learning rate: 6.322E-05 | global batch size: 512 | lm loss: 1.022085E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.431 | TFLOPs: 72.84 | +[default7]: iteration 134/ 3814 | consumed samples: 68608 | consumed tokens: 140509184 | elapsed time per iteration (s): 5.31 | learning rate: 6.370E-05 | global batch size: 512 | lm loss: 1.021276E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.377 | TFLOPs: 72.79 | +[default7]: iteration 135/ 3814 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 5.31 | learning rate: 6.417E-05 | global batch size: 512 | lm loss: 1.020830E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.402 | TFLOPs: 72.81 | +[default7]: iteration 136/ 3814 | consumed samples: 69632 | consumed tokens: 142606336 | elapsed time per iteration (s): 5.31 | learning rate: 6.465E-05 | global batch size: 512 | lm loss: 1.019687E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.399 | TFLOPs: 72.81 | +[default7]: iteration 137/ 3814 | consumed samples: 70144 | consumed tokens: 143654912 | elapsed time per iteration (s): 5.33 | learning rate: 6.512E-05 | global batch size: 512 | lm loss: 1.018959E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.115 | TFLOPs: 72.60 | +[default7]: iteration 138/ 3814 | consumed samples: 70656 | consumed tokens: 144703488 | elapsed time per iteration (s): 5.34 | learning rate: 6.560E-05 | global batch size: 512 | lm loss: 1.017420E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.965 | TFLOPs: 72.48 | +[default7]: iteration 139/ 3814 | consumed samples: 71168 | consumed tokens: 145752064 | elapsed time per iteration (s): 5.32 | learning rate: 6.607E-05 | global batch size: 512 | lm loss: 1.017094E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.165 | TFLOPs: 72.63 | +[default7]: iteration 140/ 3814 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 5.31 | learning rate: 6.655E-05 | global batch size: 512 | lm loss: 1.015931E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.417 | TFLOPs: 72.82 | +[default7]: iteration 141/ 3814 | consumed samples: 72192 | consumed tokens: 147849216 | elapsed time per iteration (s): 5.32 | learning rate: 6.703E-05 | global batch size: 512 | lm loss: 1.014729E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.265 | TFLOPs: 72.71 | +[default7]: iteration 142/ 3814 | consumed samples: 72704 | consumed tokens: 148897792 | elapsed time per iteration (s): 5.32 | learning rate: 6.750E-05 | global batch size: 512 | lm loss: 1.013652E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.214 | TFLOPs: 72.67 | +[default7]: iteration 143/ 3814 | consumed samples: 73216 | consumed tokens: 149946368 | elapsed time per iteration (s): 5.32 | learning rate: 6.798E-05 | global batch size: 512 | lm loss: 1.013825E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.320 | TFLOPs: 72.75 | +[default7]: iteration 144/ 3814 | consumed samples: 73728 | consumed tokens: 150994944 | elapsed time per iteration (s): 5.32 | learning rate: 6.845E-05 | global batch size: 512 | lm loss: 1.012408E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.261 | TFLOPs: 72.71 | +[default7]: iteration 145/ 3814 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 5.30 | learning rate: 6.893E-05 | global batch size: 512 | lm loss: 1.011396E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.624 | TFLOPs: 72.98 | +[default7]: iteration 146/ 3814 | consumed samples: 74752 | consumed tokens: 153092096 | elapsed time per iteration (s): 5.32 | learning rate: 6.940E-05 | global batch size: 512 | lm loss: 1.010230E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.235 | TFLOPs: 72.69 | +[default7]: iteration 147/ 3814 | consumed samples: 75264 | consumed tokens: 154140672 | elapsed time per iteration (s): 5.32 | learning rate: 6.988E-05 | global batch size: 512 | lm loss: 1.009617E+01 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.261 | TFLOPs: 72.71 | +[default7]: iteration 148/ 3814 | consumed samples: 75776 | consumed tokens: 155189248 | elapsed time per iteration (s): 5.31 | learning rate: 7.035E-05 | global batch size: 512 | lm loss: 1.008630E+01 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.438 | TFLOPs: 72.84 | +[default7]: iteration 149/ 3814 | consumed samples: 76288 | consumed tokens: 156237824 | elapsed time per iteration (s): 5.28 | learning rate: 7.083E-05 | global batch size: 512 | lm loss: 1.007301E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.905 | TFLOPs: 73.19 | +[default7]: iteration 150/ 3814 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 5.31 | learning rate: 7.130E-05 | global batch size: 512 | lm loss: 1.006475E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.444 | TFLOPs: 72.85 | +[default7]: iteration 151/ 3814 | consumed samples: 77312 | consumed tokens: 158334976 | elapsed time per iteration (s): 5.29 | learning rate: 7.178E-05 | global batch size: 512 | lm loss: 1.005547E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.725 | TFLOPs: 73.06 | +[default7]: iteration 152/ 3814 | consumed samples: 77824 | consumed tokens: 159383552 | elapsed time per iteration (s): 5.30 | learning rate: 7.225E-05 | global batch size: 512 | lm loss: 1.004651E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.561 | TFLOPs: 72.93 | +[default7]: iteration 153/ 3814 | consumed samples: 78336 | consumed tokens: 160432128 | elapsed time per iteration (s): 5.33 | learning rate: 7.273E-05 | global batch size: 512 | lm loss: 1.003428E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.024 | TFLOPs: 72.53 | +[default7]: iteration 154/ 3814 | consumed samples: 78848 | consumed tokens: 161480704 | elapsed time per iteration (s): 5.33 | learning rate: 7.320E-05 | global batch size: 512 | lm loss: 1.002317E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.053 | TFLOPs: 72.55 | +[default7]: iteration 155/ 3814 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 5.33 | learning rate: 7.368E-05 | global batch size: 512 | lm loss: 1.001378E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.116 | TFLOPs: 72.60 | +[default7]: iteration 156/ 3814 | consumed samples: 79872 | consumed tokens: 163577856 | elapsed time per iteration (s): 5.35 | learning rate: 7.416E-05 | global batch size: 512 | lm loss: 1.000685E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.712 | TFLOPs: 72.29 | +[default7]: iteration 157/ 3814 | consumed samples: 80384 | consumed tokens: 164626432 | elapsed time per iteration (s): 5.32 | learning rate: 7.463E-05 | global batch size: 512 | lm loss: 9.994298E+00 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.199 | TFLOPs: 72.66 | +[default7]: iteration 158/ 3814 | consumed samples: 80896 | consumed tokens: 165675008 | elapsed time per iteration (s): 5.31 | learning rate: 7.511E-05 | global batch size: 512 | lm loss: 9.983011E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.358 | TFLOPs: 72.78 | +[default7]: iteration 159/ 3814 | consumed samples: 81408 | consumed tokens: 166723584 | elapsed time per iteration (s): 5.30 | learning rate: 7.558E-05 | global batch size: 512 | lm loss: 9.970062E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.687 | TFLOPs: 73.03 | +[default7]: iteration 160/ 3814 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 5.31 | learning rate: 7.606E-05 | global batch size: 512 | lm loss: 9.964444E+00 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.398 | TFLOPs: 72.81 | +[default7]: iteration 161/ 3814 | consumed samples: 82432 | consumed tokens: 168820736 | elapsed time per iteration (s): 5.30 | learning rate: 7.653E-05 | global batch size: 512 | lm loss: 9.956097E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.641 | TFLOPs: 72.99 | +[default7]: iteration 162/ 3814 | consumed samples: 82944 | consumed tokens: 169869312 | elapsed time per iteration (s): 5.31 | learning rate: 7.701E-05 | global batch size: 512 | lm loss: 9.945373E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.398 | TFLOPs: 72.81 | +[default7]: iteration 163/ 3814 | consumed samples: 83456 | consumed tokens: 170917888 | elapsed time per iteration (s): 5.30 | learning rate: 7.748E-05 | global batch size: 512 | lm loss: 9.931705E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.524 | TFLOPs: 72.91 | +[default7]: iteration 164/ 3814 | consumed samples: 83968 | consumed tokens: 171966464 | elapsed time per iteration (s): 5.29 | learning rate: 7.796E-05 | global batch size: 512 | lm loss: 9.920040E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.736 | TFLOPs: 73.07 | +[default7]: iteration 165/ 3814 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 5.30 | learning rate: 7.843E-05 | global batch size: 512 | lm loss: 9.910382E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.611 | TFLOPs: 72.97 | +[default7]: iteration 166/ 3814 | consumed samples: 84992 | consumed tokens: 174063616 | elapsed time per iteration (s): 5.29 | learning rate: 7.891E-05 | global batch size: 512 | lm loss: 9.896185E+00 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.774 | TFLOPs: 73.09 | +[default7]: iteration 167/ 3814 | consumed samples: 85504 | consumed tokens: 175112192 | elapsed time per iteration (s): 5.29 | learning rate: 7.938E-05 | global batch size: 512 | lm loss: 9.890118E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.731 | TFLOPs: 73.06 | +[default7]: iteration 168/ 3814 | consumed samples: 86016 | consumed tokens: 176160768 | elapsed time per iteration (s): 5.31 | learning rate: 7.986E-05 | global batch size: 512 | lm loss: 9.873681E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.343 | TFLOPs: 72.77 | +[default7]: iteration 169/ 3814 | consumed samples: 86528 | consumed tokens: 177209344 | elapsed time per iteration (s): 5.33 | learning rate: 8.034E-05 | global batch size: 512 | lm loss: 9.871252E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.976 | TFLOPs: 72.49 | +[default7]: iteration 170/ 3814 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 5.34 | learning rate: 8.081E-05 | global batch size: 512 | lm loss: 9.849233E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.914 | TFLOPs: 72.45 | +[default7]: iteration 171/ 3814 | consumed samples: 87552 | consumed tokens: 179306496 | elapsed time per iteration (s): 5.32 | learning rate: 8.129E-05 | global batch size: 512 | lm loss: 9.847050E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.230 | TFLOPs: 72.68 | +[default7]: iteration 172/ 3814 | consumed samples: 88064 | consumed tokens: 180355072 | elapsed time per iteration (s): 5.31 | learning rate: 8.176E-05 | global batch size: 512 | lm loss: 9.827371E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.346 | TFLOPs: 72.77 | +[default7]: iteration 173/ 3814 | consumed samples: 88576 | consumed tokens: 181403648 | elapsed time per iteration (s): 5.33 | learning rate: 8.224E-05 | global batch size: 512 | lm loss: 9.819230E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.067 | TFLOPs: 72.56 | +[default7]: iteration 174/ 3814 | consumed samples: 89088 | consumed tokens: 182452224 | elapsed time per iteration (s): 5.36 | learning rate: 8.271E-05 | global batch size: 512 | lm loss: 9.813724E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.463 | TFLOPs: 72.10 | +[default7]: iteration 175/ 3814 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 5.32 | learning rate: 8.319E-05 | global batch size: 512 | lm loss: 9.799225E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.318 | TFLOPs: 72.75 | +[default7]: iteration 176/ 3814 | consumed samples: 90112 | consumed tokens: 184549376 | elapsed time per iteration (s): 5.28 | learning rate: 8.366E-05 | global batch size: 512 | lm loss: 9.791071E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.879 | TFLOPs: 73.17 | +[default7]: iteration 177/ 3814 | consumed samples: 90624 | consumed tokens: 185597952 | elapsed time per iteration (s): 5.29 | learning rate: 8.414E-05 | global batch size: 512 | lm loss: 9.775797E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.827 | TFLOPs: 73.13 | +[default7]: iteration 178/ 3814 | consumed samples: 91136 | consumed tokens: 186646528 | elapsed time per iteration (s): 5.29 | learning rate: 8.461E-05 | global batch size: 512 | lm loss: 9.762317E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.800 | TFLOPs: 73.11 | +[default7]: iteration 179/ 3814 | consumed samples: 91648 | consumed tokens: 187695104 | elapsed time per iteration (s): 5.33 | learning rate: 8.509E-05 | global batch size: 512 | lm loss: 9.750772E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.064 | TFLOPs: 72.56 | +[default7]: iteration 180/ 3814 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 5.34 | learning rate: 8.556E-05 | global batch size: 512 | lm loss: 9.733981E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.929 | TFLOPs: 72.46 | +[default7]: iteration 181/ 3814 | consumed samples: 92672 | consumed tokens: 189792256 | elapsed time per iteration (s): 5.33 | learning rate: 8.604E-05 | global batch size: 512 | lm loss: 9.726596E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.126 | TFLOPs: 72.60 | +[default7]: iteration 182/ 3814 | consumed samples: 93184 | consumed tokens: 190840832 | elapsed time per iteration (s): 5.31 | learning rate: 8.651E-05 | global batch size: 512 | lm loss: 9.719937E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.490 | TFLOPs: 72.88 | +[default7]: iteration 183/ 3814 | consumed samples: 93696 | consumed tokens: 191889408 | elapsed time per iteration (s): 5.29 | learning rate: 8.699E-05 | global batch size: 512 | lm loss: 9.701593E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.869 | TFLOPs: 73.17 | +[default7]: iteration 184/ 3814 | consumed samples: 94208 | consumed tokens: 192937984 | elapsed time per iteration (s): 5.30 | learning rate: 8.747E-05 | global batch size: 512 | lm loss: 9.690262E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.633 | TFLOPs: 72.99 | +[default7]: iteration 185/ 3814 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 5.29 | learning rate: 8.794E-05 | global batch size: 512 | lm loss: 9.683443E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.765 | TFLOPs: 73.09 | +[default7]: iteration 186/ 3814 | consumed samples: 95232 | consumed tokens: 195035136 | elapsed time per iteration (s): 5.32 | learning rate: 8.842E-05 | global batch size: 512 | lm loss: 9.669689E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.318 | TFLOPs: 72.75 | +[default7]: iteration 187/ 3814 | consumed samples: 95744 | consumed tokens: 196083712 | elapsed time per iteration (s): 5.30 | learning rate: 8.889E-05 | global batch size: 512 | lm loss: 9.652879E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.648 | TFLOPs: 73.00 | +[default7]: iteration 188/ 3814 | consumed samples: 96256 | consumed tokens: 197132288 | elapsed time per iteration (s): 5.30 | learning rate: 8.937E-05 | global batch size: 512 | lm loss: 9.642898E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.597 | TFLOPs: 72.96 | +[default7]: iteration 189/ 3814 | consumed samples: 96768 | consumed tokens: 198180864 | elapsed time per iteration (s): 5.32 | learning rate: 8.984E-05 | global batch size: 512 | lm loss: 9.629091E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.267 | TFLOPs: 72.71 | +[default7]: iteration 190/ 3814 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 5.30 | learning rate: 9.032E-05 | global batch size: 512 | lm loss: 9.619547E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.645 | TFLOPs: 73.00 | +[default7]: iteration 191/ 3814 | consumed samples: 97792 | consumed tokens: 200278016 | elapsed time per iteration (s): 5.30 | learning rate: 9.079E-05 | global batch size: 512 | lm loss: 9.608498E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.641 | TFLOPs: 72.99 | +[default7]: iteration 192/ 3814 | consumed samples: 98304 | consumed tokens: 201326592 | elapsed time per iteration (s): 5.29 | learning rate: 9.127E-05 | global batch size: 512 | lm loss: 9.590815E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.821 | TFLOPs: 73.13 | +[default7]: iteration 193/ 3814 | consumed samples: 98816 | consumed tokens: 202375168 | elapsed time per iteration (s): 5.30 | learning rate: 9.174E-05 | global batch size: 512 | lm loss: 9.576266E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.549 | TFLOPs: 72.92 | +[default7]: iteration 194/ 3814 | consumed samples: 99328 | consumed tokens: 203423744 | elapsed time per iteration (s): 5.31 | learning rate: 9.222E-05 | global batch size: 512 | lm loss: 9.564390E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.395 | TFLOPs: 72.81 | +[default7]: iteration 195/ 3814 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 5.32 | learning rate: 9.269E-05 | global batch size: 512 | lm loss: 9.562397E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.320 | TFLOPs: 72.75 | +[default7]: iteration 196/ 3814 | consumed samples: 100352 | consumed tokens: 205520896 | elapsed time per iteration (s): 5.31 | learning rate: 9.317E-05 | global batch size: 512 | lm loss: 9.545841E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.375 | TFLOPs: 72.79 | +[default7]: iteration 197/ 3814 | consumed samples: 100864 | consumed tokens: 206569472 | elapsed time per iteration (s): 5.31 | learning rate: 9.365E-05 | global batch size: 512 | lm loss: 9.528913E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.390 | TFLOPs: 72.80 | +[default7]: iteration 198/ 3814 | consumed samples: 101376 | consumed tokens: 207618048 | elapsed time per iteration (s): 5.32 | learning rate: 9.412E-05 | global batch size: 512 | lm loss: 9.521463E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.285 | TFLOPs: 72.73 | +[default7]: iteration 199/ 3814 | consumed samples: 101888 | consumed tokens: 208666624 | elapsed time per iteration (s): 5.31 | learning rate: 9.460E-05 | global batch size: 512 | lm loss: 9.508928E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.410 | TFLOPs: 72.82 | +[default7]: iteration 200/ 3814 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 5.32 | learning rate: 9.507E-05 | global batch size: 512 | lm loss: 9.485943E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.194 | TFLOPs: 72.66 | +[default7]: iteration 201/ 3814 | consumed samples: 102912 | consumed tokens: 210763776 | elapsed time per iteration (s): 5.30 | learning rate: 9.555E-05 | global batch size: 512 | lm loss: 9.482991E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.687 | TFLOPs: 73.03 | +[default7]: iteration 202/ 3814 | consumed samples: 103424 | consumed tokens: 211812352 | elapsed time per iteration (s): 5.29 | learning rate: 9.602E-05 | global batch size: 512 | lm loss: 9.467093E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.707 | TFLOPs: 73.04 | +[default7]: iteration 203/ 3814 | consumed samples: 103936 | consumed tokens: 212860928 | elapsed time per iteration (s): 5.32 | learning rate: 9.650E-05 | global batch size: 512 | lm loss: 9.452475E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.242 | TFLOPs: 72.69 | +[default7]: iteration 204/ 3814 | consumed samples: 104448 | consumed tokens: 213909504 | elapsed time per iteration (s): 5.32 | learning rate: 9.697E-05 | global batch size: 512 | lm loss: 9.438707E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.191 | TFLOPs: 72.65 | +[default7]: iteration 205/ 3814 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 5.30 | learning rate: 9.745E-05 | global batch size: 512 | lm loss: 9.434565E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.585 | TFLOPs: 72.95 | +[default7]: iteration 206/ 3814 | consumed samples: 105472 | consumed tokens: 216006656 | elapsed time per iteration (s): 5.30 | learning rate: 9.792E-05 | global batch size: 512 | lm loss: 9.420014E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.578 | TFLOPs: 72.95 | +[default7]: iteration 207/ 3814 | consumed samples: 105984 | consumed tokens: 217055232 | elapsed time per iteration (s): 5.32 | learning rate: 9.840E-05 | global batch size: 512 | lm loss: 9.396791E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.304 | TFLOPs: 72.74 | +[default7]: iteration 208/ 3814 | consumed samples: 106496 | consumed tokens: 218103808 | elapsed time per iteration (s): 5.34 | learning rate: 9.887E-05 | global batch size: 512 | lm loss: 9.383839E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.875 | TFLOPs: 72.42 | +[default7]: iteration 209/ 3814 | consumed samples: 107008 | consumed tokens: 219152384 | elapsed time per iteration (s): 5.33 | learning rate: 9.935E-05 | global batch size: 512 | lm loss: 9.374474E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.145 | TFLOPs: 72.62 | +[default7]: iteration 210/ 3814 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 5.34 | learning rate: 9.982E-05 | global batch size: 512 | lm loss: 9.362868E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.893 | TFLOPs: 72.43 | +[default7]: iteration 211/ 3814 | consumed samples: 108032 | consumed tokens: 221249536 | elapsed time per iteration (s): 5.34 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 9.340849E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.926 | TFLOPs: 72.45 | +[default7]: iteration 212/ 3814 | consumed samples: 108544 | consumed tokens: 222298112 | elapsed time per iteration (s): 5.34 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 9.343000E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.877 | TFLOPs: 72.42 | +[default7]: iteration 213/ 3814 | consumed samples: 109056 | consumed tokens: 223346688 | elapsed time per iteration (s): 5.33 | learning rate: 1.013E-04 | global batch size: 512 | lm loss: 9.321430E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.128 | TFLOPs: 72.61 | +[default7]: iteration 214/ 3814 | consumed samples: 109568 | consumed tokens: 224395264 | elapsed time per iteration (s): 5.33 | learning rate: 1.017E-04 | global batch size: 512 | lm loss: 9.305206E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.984 | TFLOPs: 72.50 | +[default7]: iteration 215/ 3814 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 5.33 | learning rate: 1.022E-04 | global batch size: 512 | lm loss: 9.298841E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.025 | TFLOPs: 72.53 | +[default7]: iteration 216/ 3814 | consumed samples: 110592 | consumed tokens: 226492416 | elapsed time per iteration (s): 5.33 | learning rate: 1.027E-04 | global batch size: 512 | lm loss: 9.293509E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.143 | TFLOPs: 72.62 | +[default7]: iteration 217/ 3814 | consumed samples: 111104 | consumed tokens: 227540992 | elapsed time per iteration (s): 5.32 | learning rate: 1.032E-04 | global batch size: 512 | lm loss: 9.272388E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.234 | TFLOPs: 72.69 | +[default7]: iteration 218/ 3814 | consumed samples: 111616 | consumed tokens: 228589568 | elapsed time per iteration (s): 5.34 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 9.255223E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.937 | TFLOPs: 72.46 | +[default7]: iteration 219/ 3814 | consumed samples: 112128 | consumed tokens: 229638144 | elapsed time per iteration (s): 5.32 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 9.242064E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.281 | TFLOPs: 72.72 | +[default7]: iteration 220/ 3814 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 5.33 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 9.229397E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.986 | TFLOPs: 72.50 | +[default7]: iteration 221/ 3814 | consumed samples: 113152 | consumed tokens: 231735296 | elapsed time per iteration (s): 5.32 | learning rate: 1.051E-04 | global batch size: 512 | lm loss: 9.230874E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.255 | TFLOPs: 72.70 | +[default7]: iteration 222/ 3814 | consumed samples: 113664 | consumed tokens: 232783872 | elapsed time per iteration (s): 5.32 | learning rate: 1.055E-04 | global batch size: 512 | lm loss: 9.205098E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.172 | TFLOPs: 72.64 | +[default7]: iteration 223/ 3814 | consumed samples: 114176 | consumed tokens: 233832448 | elapsed time per iteration (s): 5.33 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 9.191916E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.015 | TFLOPs: 72.52 | +[default7]: iteration 224/ 3814 | consumed samples: 114688 | consumed tokens: 234881024 | elapsed time per iteration (s): 5.36 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 9.176584E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.594 | TFLOPs: 72.20 | +[default7]: iteration 225/ 3814 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 5.34 | learning rate: 1.070E-04 | global batch size: 512 | lm loss: 9.164513E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.841 | TFLOPs: 72.39 | +[default7]: iteration 226/ 3814 | consumed samples: 115712 | consumed tokens: 236978176 | elapsed time per iteration (s): 5.32 | learning rate: 1.074E-04 | global batch size: 512 | lm loss: 9.152882E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.209 | TFLOPs: 72.67 | +[default7]: iteration 227/ 3814 | consumed samples: 116224 | consumed tokens: 238026752 | elapsed time per iteration (s): 5.31 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 9.137157E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.374 | TFLOPs: 72.79 | +[default7]: iteration 228/ 3814 | consumed samples: 116736 | consumed tokens: 239075328 | elapsed time per iteration (s): 5.32 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 9.121049E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.197 | TFLOPs: 72.66 | +[default7]: iteration 229/ 3814 | consumed samples: 117248 | consumed tokens: 240123904 | elapsed time per iteration (s): 5.31 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 9.113119E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.397 | TFLOPs: 72.81 | +[default7]: iteration 230/ 3814 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 5.34 | learning rate: 1.093E-04 | global batch size: 512 | lm loss: 9.093582E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.935 | TFLOPs: 72.46 | +[default7]: iteration 231/ 3814 | consumed samples: 118272 | consumed tokens: 242221056 | elapsed time per iteration (s): 5.36 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 9.081664E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.610 | TFLOPs: 72.21 | +[default7]: iteration 232/ 3814 | consumed samples: 118784 | consumed tokens: 243269632 | elapsed time per iteration (s): 5.35 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 9.067253E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.670 | TFLOPs: 72.26 | +[default7]: iteration 233/ 3814 | consumed samples: 119296 | consumed tokens: 244318208 | elapsed time per iteration (s): 5.37 | learning rate: 1.108E-04 | global batch size: 512 | lm loss: 9.050978E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.400 | TFLOPs: 72.06 | +[default7]: iteration 234/ 3814 | consumed samples: 119808 | consumed tokens: 245366784 | elapsed time per iteration (s): 5.34 | learning rate: 1.112E-04 | global batch size: 512 | lm loss: 9.032274E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.892 | TFLOPs: 72.43 | +[default7]: iteration 235/ 3814 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 5.36 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 9.030124E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.590 | TFLOPs: 72.20 | +[default7]: iteration 236/ 3814 | consumed samples: 120832 | consumed tokens: 247463936 | elapsed time per iteration (s): 5.36 | learning rate: 1.122E-04 | global batch size: 512 | lm loss: 9.011617E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.492 | TFLOPs: 72.13 | +[default7]: iteration 237/ 3814 | consumed samples: 121344 | consumed tokens: 248512512 | elapsed time per iteration (s): 5.35 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 9.005948E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.756 | TFLOPs: 72.33 | +[default7]: iteration 238/ 3814 | consumed samples: 121856 | consumed tokens: 249561088 | elapsed time per iteration (s): 5.34 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 8.982620E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.915 | TFLOPs: 72.45 | +[default7]: iteration 239/ 3814 | consumed samples: 122368 | consumed tokens: 250609664 | elapsed time per iteration (s): 5.34 | learning rate: 1.136E-04 | global batch size: 512 | lm loss: 8.971184E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.838 | TFLOPs: 72.39 | +[default7]: iteration 240/ 3814 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 5.34 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 8.958990E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.844 | TFLOPs: 72.39 | +[default7]: iteration 241/ 3814 | consumed samples: 123392 | consumed tokens: 252706816 | elapsed time per iteration (s): 5.34 | learning rate: 1.146E-04 | global batch size: 512 | lm loss: 8.946317E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.834 | TFLOPs: 72.38 | +[default7]: iteration 242/ 3814 | consumed samples: 123904 | consumed tokens: 253755392 | elapsed time per iteration (s): 5.30 | learning rate: 1.150E-04 | global batch size: 512 | lm loss: 8.936499E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.551 | TFLOPs: 72.93 | +[default7]: iteration 243/ 3814 | consumed samples: 124416 | consumed tokens: 254803968 | elapsed time per iteration (s): 5.34 | learning rate: 1.155E-04 | global batch size: 512 | lm loss: 8.908994E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.826 | TFLOPs: 72.38 | +[default7]: iteration 244/ 3814 | consumed samples: 124928 | consumed tokens: 255852544 | elapsed time per iteration (s): 5.34 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 8.910476E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.847 | TFLOPs: 72.39 | +[default7]: iteration 245/ 3814 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 5.34 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 8.894345E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.805 | TFLOPs: 72.36 | +[default7]: iteration 246/ 3814 | consumed samples: 125952 | consumed tokens: 257949696 | elapsed time per iteration (s): 5.37 | learning rate: 1.169E-04 | global batch size: 512 | lm loss: 8.884802E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.294 | TFLOPs: 71.98 | +[default7]: iteration 247/ 3814 | consumed samples: 126464 | consumed tokens: 258998272 | elapsed time per iteration (s): 5.35 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 8.853500E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.649 | TFLOPs: 72.24 | +[default7]: iteration 248/ 3814 | consumed samples: 126976 | consumed tokens: 260046848 | elapsed time per iteration (s): 5.35 | learning rate: 1.179E-04 | global batch size: 512 | lm loss: 8.842468E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.662 | TFLOPs: 72.25 | +[default7]: iteration 249/ 3814 | consumed samples: 127488 | consumed tokens: 261095424 | elapsed time per iteration (s): 5.36 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 8.847237E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.495 | TFLOPs: 72.13 | +[default0]:saving checkpoint at iteration 250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 11:42:45,675] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step250 is begin to save! +[default0]:[2023-02-16 11:42:45,686] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_00-model_states.pt... +[default7]: iteration 250/ 3814 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 5.33 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 8.823256E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.971 | TFLOPs: 72.49 | +[default1]:[2023-02-16 11:42:45,686] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:45,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:45,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:45,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:45,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:45,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:45,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:45,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:45,979] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:45,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:45,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,036] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,194] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,270] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,308] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,375] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,397] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,456] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,613] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,671] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,733] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:46,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:46,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,919] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:46,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:46,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:46,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:46,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,031] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,086] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,140] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,174] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,197] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,252] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,285] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,340] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,394] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,420] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,474] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,533] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,560] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,622] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 11:42:47,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,587] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 11:42:47,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,680] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:42:47,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 11:42:47,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 11:42:47,706] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 11:42:47,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 11:42:47,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:42:47,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,733] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 11:42:47,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 11:42:47,735] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt +[default0]:[2023-02-16 11:42:47,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 11:42:47,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:42:47,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:42:48,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,292] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,304] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,276] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,288] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,349] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,387] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,387] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,388] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,393] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,371] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,371] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,395] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,381] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,381] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,428] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,366] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,366] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,401] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,435] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,375] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,386] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,423] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,454] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,421] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,397] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,397] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,399] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,409] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,409] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,444] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,450] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,418] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,419] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,444] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,478] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,415] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,460] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,480] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,522] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,481] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,450] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,497] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,472] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,482] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,499] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,496] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,462] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,469] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,565] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,534] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,526] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,513] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,565] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,562] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,571] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,570] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,602] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,576] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,548] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,534] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,613] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 11:42:48,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:42:48,581] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:42:48,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,587] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 11:42:48,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:42:48,588] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:42:48,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 11:42:48,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:42:48,625] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:42:48,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 11:42:48,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:42:48,634] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:42:48,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 11:42:48,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:42:48,744] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:42:48,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 11:42:48,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:42:48,742] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:42:48,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 11:42:48,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:42:48,785] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:42:48,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 11:42:48,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:42:48,842] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:42:48,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]: successfully saved checkpoint at iteration 250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 3195.54 +[default7]: iteration 251/ 3814 | consumed samples: 128512 | consumed tokens: 263192576 | elapsed time per iteration (s): 8.51 | learning rate: 1.193E-04 | global batch size: 512 | lm loss: 8.811642E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 60.174 | TFLOPs: 45.45 | +[default7]: iteration 252/ 3814 | consumed samples: 129024 | consumed tokens: 264241152 | elapsed time per iteration (s): 5.32 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 8.793316E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.325 | TFLOPs: 72.75 | +[default7]: iteration 253/ 3814 | consumed samples: 129536 | consumed tokens: 265289728 | elapsed time per iteration (s): 5.31 | learning rate: 1.203E-04 | global batch size: 512 | lm loss: 8.783654E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.475 | TFLOPs: 72.87 | +[default7]: iteration 254/ 3814 | consumed samples: 130048 | consumed tokens: 266338304 | elapsed time per iteration (s): 5.33 | learning rate: 1.207E-04 | global batch size: 512 | lm loss: 8.753620E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.993 | TFLOPs: 72.50 | +[default7]: iteration 255/ 3814 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 5.31 | learning rate: 1.212E-04 | global batch size: 512 | lm loss: 8.749729E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.461 | TFLOPs: 72.86 | +[default7]: iteration 256/ 3814 | consumed samples: 131072 | consumed tokens: 268435456 | elapsed time per iteration (s): 5.35 | learning rate: 1.217E-04 | global batch size: 512 | lm loss: 8.737192E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.680 | TFLOPs: 72.27 | +[default7]: iteration 257/ 3814 | consumed samples: 131584 | consumed tokens: 269484032 | elapsed time per iteration (s): 5.32 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 8.729830E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.279 | TFLOPs: 72.72 | +[default7]: iteration 258/ 3814 | consumed samples: 132096 | consumed tokens: 270532608 | elapsed time per iteration (s): 5.32 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 8.708930E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.178 | TFLOPs: 72.64 | +[default7]: iteration 259/ 3814 | consumed samples: 132608 | consumed tokens: 271581184 | elapsed time per iteration (s): 5.33 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 8.684668E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.088 | TFLOPs: 72.58 | +[default7]: iteration 260/ 3814 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 5.36 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 8.673896E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.542 | TFLOPs: 72.16 | +[default7]: iteration 261/ 3814 | consumed samples: 133632 | consumed tokens: 273678336 | elapsed time per iteration (s): 5.34 | learning rate: 1.241E-04 | global batch size: 512 | lm loss: 8.667924E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.894 | TFLOPs: 72.43 | +[default7]: iteration 262/ 3814 | consumed samples: 134144 | consumed tokens: 274726912 | elapsed time per iteration (s): 5.34 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 8.651016E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.819 | TFLOPs: 72.37 | +[default7]: iteration 263/ 3814 | consumed samples: 134656 | consumed tokens: 275775488 | elapsed time per iteration (s): 5.31 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 8.637922E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.483 | TFLOPs: 72.87 | +[default7]: iteration 264/ 3814 | consumed samples: 135168 | consumed tokens: 276824064 | elapsed time per iteration (s): 5.31 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 8.606495E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.407 | TFLOPs: 72.82 | +[default7]: iteration 265/ 3814 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 5.32 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 8.622993E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.300 | TFLOPs: 72.74 | +[default7]: iteration 266/ 3814 | consumed samples: 136192 | consumed tokens: 278921216 | elapsed time per iteration (s): 5.31 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 8.605418E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.381 | TFLOPs: 72.80 | +[default7]: iteration 267/ 3814 | consumed samples: 136704 | consumed tokens: 279969792 | elapsed time per iteration (s): 5.32 | learning rate: 1.269E-04 | global batch size: 512 | lm loss: 8.583795E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.308 | TFLOPs: 72.74 | +[default7]: iteration 268/ 3814 | consumed samples: 137216 | consumed tokens: 281018368 | elapsed time per iteration (s): 5.32 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 8.577521E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.289 | TFLOPs: 72.73 | +[default7]: iteration 269/ 3814 | consumed samples: 137728 | consumed tokens: 282066944 | elapsed time per iteration (s): 5.31 | learning rate: 1.279E-04 | global batch size: 512 | lm loss: 8.561977E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.358 | TFLOPs: 72.78 | +[default7]: iteration 270/ 3814 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 5.34 | learning rate: 1.283E-04 | global batch size: 512 | lm loss: 8.535537E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.957 | TFLOPs: 72.48 | +[default7]: iteration 271/ 3814 | consumed samples: 138752 | consumed tokens: 284164096 | elapsed time per iteration (s): 5.32 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 8.536131E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.276 | TFLOPs: 72.72 | +[default7]: iteration 272/ 3814 | consumed samples: 139264 | consumed tokens: 285212672 | elapsed time per iteration (s): 5.32 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 8.514743E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.273 | TFLOPs: 72.72 | +[default7]: iteration 273/ 3814 | consumed samples: 139776 | consumed tokens: 286261248 | elapsed time per iteration (s): 5.31 | learning rate: 1.298E-04 | global batch size: 512 | lm loss: 8.488200E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.405 | TFLOPs: 72.82 | +[default7]: iteration 274/ 3814 | consumed samples: 140288 | consumed tokens: 287309824 | elapsed time per iteration (s): 5.30 | learning rate: 1.302E-04 | global batch size: 512 | lm loss: 8.496998E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.576 | TFLOPs: 72.94 | +[default7]: iteration 275/ 3814 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 5.29 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 8.470623E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.832 | TFLOPs: 73.14 | +[default7]: iteration 276/ 3814 | consumed samples: 141312 | consumed tokens: 289406976 | elapsed time per iteration (s): 5.29 | learning rate: 1.312E-04 | global batch size: 512 | lm loss: 8.450557E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.719 | TFLOPs: 73.05 | +[default7]: iteration 277/ 3814 | consumed samples: 141824 | consumed tokens: 290455552 | elapsed time per iteration (s): 5.33 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 8.433667E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.145 | TFLOPs: 72.62 | +[default7]: iteration 278/ 3814 | consumed samples: 142336 | consumed tokens: 291504128 | elapsed time per iteration (s): 5.34 | learning rate: 1.321E-04 | global batch size: 512 | lm loss: 8.430012E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.818 | TFLOPs: 72.37 | +[default7]: iteration 279/ 3814 | consumed samples: 142848 | consumed tokens: 292552704 | elapsed time per iteration (s): 5.33 | learning rate: 1.326E-04 | global batch size: 512 | lm loss: 8.418277E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.971 | TFLOPs: 72.49 | +[default7]: iteration 280/ 3814 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 5.31 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 8.391793E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.359 | TFLOPs: 72.78 | +[default7]: iteration 281/ 3814 | consumed samples: 143872 | consumed tokens: 294649856 | elapsed time per iteration (s): 5.32 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 8.407591E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.233 | TFLOPs: 72.69 | +[default7]: iteration 282/ 3814 | consumed samples: 144384 | consumed tokens: 295698432 | elapsed time per iteration (s): 5.30 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 8.371490E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.528 | TFLOPs: 72.91 | +[default7]: iteration 283/ 3814 | consumed samples: 144896 | consumed tokens: 296747008 | elapsed time per iteration (s): 5.30 | learning rate: 1.345E-04 | global batch size: 512 | lm loss: 8.368720E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.608 | TFLOPs: 72.97 | +[default7]: iteration 284/ 3814 | consumed samples: 145408 | consumed tokens: 297795584 | elapsed time per iteration (s): 5.31 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 8.341236E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.343 | TFLOPs: 72.77 | +[default7]: iteration 285/ 3814 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 5.31 | learning rate: 1.355E-04 | global batch size: 512 | lm loss: 8.341099E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.377 | TFLOPs: 72.79 | +[default7]: iteration 286/ 3814 | consumed samples: 146432 | consumed tokens: 299892736 | elapsed time per iteration (s): 5.34 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 8.310564E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.878 | TFLOPs: 72.42 | +[default7]: iteration 287/ 3814 | consumed samples: 146944 | consumed tokens: 300941312 | elapsed time per iteration (s): 5.34 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 8.299698E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.907 | TFLOPs: 72.44 | +[default7]: iteration 288/ 3814 | consumed samples: 147456 | consumed tokens: 301989888 | elapsed time per iteration (s): 5.34 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 8.295638E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.822 | TFLOPs: 72.38 | +[default7]: iteration 289/ 3814 | consumed samples: 147968 | consumed tokens: 303038464 | elapsed time per iteration (s): 5.33 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 8.273714E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.130 | TFLOPs: 72.61 | +[default7]: iteration 290/ 3814 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 5.34 | learning rate: 1.379E-04 | global batch size: 512 | lm loss: 8.262163E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.924 | TFLOPs: 72.45 | +[default7]: iteration 291/ 3814 | consumed samples: 148992 | consumed tokens: 305135616 | elapsed time per iteration (s): 5.36 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 8.248385E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.492 | TFLOPs: 72.13 | +[default7]: iteration 292/ 3814 | consumed samples: 149504 | consumed tokens: 306184192 | elapsed time per iteration (s): 5.33 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 8.245269E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.039 | TFLOPs: 72.54 | +[default7]: iteration 293/ 3814 | consumed samples: 150016 | consumed tokens: 307232768 | elapsed time per iteration (s): 5.32 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 8.210127E+00 | loss scale: 4096.0 | grad norm: 0.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.301 | TFLOPs: 72.74 | +[default7]: iteration 294/ 3814 | consumed samples: 150528 | consumed tokens: 308281344 | elapsed time per iteration (s): 5.34 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 8.185180E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.852 | TFLOPs: 72.40 | +[default7]: iteration 295/ 3814 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 5.33 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 8.190340E+00 | loss scale: 4096.0 | grad norm: 0.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.113 | TFLOPs: 72.59 | +[default7]: iteration 296/ 3814 | consumed samples: 151552 | consumed tokens: 310378496 | elapsed time per iteration (s): 5.36 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 8.167459E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.447 | TFLOPs: 72.09 | +[default7]: iteration 297/ 3814 | consumed samples: 152064 | consumed tokens: 311427072 | elapsed time per iteration (s): 5.34 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 8.178674E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.849 | TFLOPs: 72.40 | +[default7]: iteration 298/ 3814 | consumed samples: 152576 | consumed tokens: 312475648 | elapsed time per iteration (s): 5.35 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 8.183172E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.690 | TFLOPs: 72.28 | +[default7]: iteration 299/ 3814 | consumed samples: 153088 | consumed tokens: 313524224 | elapsed time per iteration (s): 5.31 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 8.149177E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.341 | TFLOPs: 72.77 | +[default7]: iteration 300/ 3814 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 5.33 | learning rate: 1.426E-04 | global batch size: 512 | lm loss: 8.152300E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.086 | TFLOPs: 72.57 | +[default7]: iteration 301/ 3814 | consumed samples: 154112 | consumed tokens: 315621376 | elapsed time per iteration (s): 5.33 | learning rate: 1.431E-04 | global batch size: 512 | lm loss: 8.126923E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.128 | TFLOPs: 72.61 | +[default7]: iteration 302/ 3814 | consumed samples: 154624 | consumed tokens: 316669952 | elapsed time per iteration (s): 5.33 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 8.108622E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.048 | TFLOPs: 72.55 | +[default7]: iteration 303/ 3814 | consumed samples: 155136 | consumed tokens: 317718528 | elapsed time per iteration (s): 5.31 | learning rate: 1.440E-04 | global batch size: 512 | lm loss: 8.092501E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.481 | TFLOPs: 72.87 | +[default7]: iteration 304/ 3814 | consumed samples: 155648 | consumed tokens: 318767104 | elapsed time per iteration (s): 5.32 | learning rate: 1.445E-04 | global batch size: 512 | lm loss: 8.097901E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.178 | TFLOPs: 72.64 | +[default7]: iteration 305/ 3814 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 5.32 | learning rate: 1.450E-04 | global batch size: 512 | lm loss: 8.062919E+00 | loss scale: 4096.0 | grad norm: 0.057 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.232 | TFLOPs: 72.69 | +[default7]: iteration 306/ 3814 | consumed samples: 156672 | consumed tokens: 320864256 | elapsed time per iteration (s): 5.35 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 8.051357E+00 | loss scale: 4096.0 | grad norm: 0.062 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.699 | TFLOPs: 72.28 | +[default7]: iteration 307/ 3814 | consumed samples: 157184 | consumed tokens: 321912832 | elapsed time per iteration (s): 5.33 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 8.039585E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.013 | TFLOPs: 72.52 | +[default7]: iteration 308/ 3814 | consumed samples: 157696 | consumed tokens: 322961408 | elapsed time per iteration (s): 5.33 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 8.029955E+00 | loss scale: 4096.0 | grad norm: 0.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.128 | TFLOPs: 72.61 | +[default7]: iteration 309/ 3814 | consumed samples: 158208 | consumed tokens: 324009984 | elapsed time per iteration (s): 5.33 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 8.012054E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.069 | TFLOPs: 72.56 | +[default7]: iteration 310/ 3814 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 5.31 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 7.999322E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.436 | TFLOPs: 72.84 | +[default7]: iteration 311/ 3814 | consumed samples: 159232 | consumed tokens: 326107136 | elapsed time per iteration (s): 5.30 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 7.988572E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.597 | TFLOPs: 72.96 | +[default7]: iteration 312/ 3814 | consumed samples: 159744 | consumed tokens: 327155712 | elapsed time per iteration (s): 5.33 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 7.984978E+00 | loss scale: 4096.0 | grad norm: 0.059 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.099 | TFLOPs: 72.58 | +[default7]: iteration 313/ 3814 | consumed samples: 160256 | consumed tokens: 328204288 | elapsed time per iteration (s): 5.32 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 7.968729E+00 | loss scale: 4096.0 | grad norm: 0.044 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.254 | TFLOPs: 72.70 | +[default7]: iteration 314/ 3814 | consumed samples: 160768 | consumed tokens: 329252864 | elapsed time per iteration (s): 5.33 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 7.948122E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.145 | TFLOPs: 72.62 | +[default7]: iteration 315/ 3814 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 5.33 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 7.939700E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.079 | TFLOPs: 72.57 | +[default7]: iteration 316/ 3814 | consumed samples: 161792 | consumed tokens: 331350016 | elapsed time per iteration (s): 5.32 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 7.921237E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.271 | TFLOPs: 72.71 | +[default7]: iteration 317/ 3814 | consumed samples: 162304 | consumed tokens: 332398592 | elapsed time per iteration (s): 5.31 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 7.911622E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.444 | TFLOPs: 72.85 | +[default7]: iteration 318/ 3814 | consumed samples: 162816 | consumed tokens: 333447168 | elapsed time per iteration (s): 5.32 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 7.903289E+00 | loss scale: 4096.0 | grad norm: 0.080 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.323 | TFLOPs: 72.75 | +[default7]: iteration 319/ 3814 | consumed samples: 163328 | consumed tokens: 334495744 | elapsed time per iteration (s): 5.32 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 7.891225E+00 | loss scale: 4096.0 | grad norm: 0.056 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.317 | TFLOPs: 72.75 | +[default7]: iteration 320/ 3814 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 5.32 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 7.893066E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.178 | TFLOPs: 72.64 | +[default7]: iteration 321/ 3814 | consumed samples: 164352 | consumed tokens: 336592896 | elapsed time per iteration (s): 5.33 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 7.883309E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.041 | TFLOPs: 72.54 | +[default7]: iteration 322/ 3814 | consumed samples: 164864 | consumed tokens: 337641472 | elapsed time per iteration (s): 5.33 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 7.852365E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.991 | TFLOPs: 72.50 | +[default7]: iteration 323/ 3814 | consumed samples: 165376 | consumed tokens: 338690048 | elapsed time per iteration (s): 5.32 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 7.852159E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.206 | TFLOPs: 72.67 | +[default7]: iteration 324/ 3814 | consumed samples: 165888 | consumed tokens: 339738624 | elapsed time per iteration (s): 5.33 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 7.814661E+00 | loss scale: 4096.0 | grad norm: 0.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.061 | TFLOPs: 72.56 | +[default7]: iteration 325/ 3814 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 5.31 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 7.814216E+00 | loss scale: 4096.0 | grad norm: 0.044 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.478 | TFLOPs: 72.87 | +[default7]: iteration 326/ 3814 | consumed samples: 166912 | consumed tokens: 341835776 | elapsed time per iteration (s): 5.32 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 7.823153E+00 | loss scale: 4096.0 | grad norm: 0.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.215 | TFLOPs: 72.67 | +[default7]: iteration 327/ 3814 | consumed samples: 167424 | consumed tokens: 342884352 | elapsed time per iteration (s): 5.32 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 7.826518E+00 | loss scale: 4096.0 | grad norm: 0.074 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.315 | TFLOPs: 72.75 | +[default7]: iteration 328/ 3814 | consumed samples: 167936 | consumed tokens: 343932928 | elapsed time per iteration (s): 5.33 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 7.808798E+00 | loss scale: 4096.0 | grad norm: 0.068 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.033 | TFLOPs: 72.53 | +[default7]: iteration 329/ 3814 | consumed samples: 168448 | consumed tokens: 344981504 | elapsed time per iteration (s): 5.34 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 7.767662E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.959 | TFLOPs: 72.48 | +[default7]: iteration 330/ 3814 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 5.32 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 7.779583E+00 | loss scale: 4096.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.229 | TFLOPs: 72.68 | +[default7]: iteration 331/ 3814 | consumed samples: 169472 | consumed tokens: 347078656 | elapsed time per iteration (s): 5.32 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 7.750802E+00 | loss scale: 4096.0 | grad norm: 0.062 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.151 | TFLOPs: 72.62 | +[default7]: iteration 332/ 3814 | consumed samples: 169984 | consumed tokens: 348127232 | elapsed time per iteration (s): 5.33 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 7.741921E+00 | loss scale: 4096.0 | grad norm: 0.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.112 | TFLOPs: 72.59 | +[default7]: iteration 333/ 3814 | consumed samples: 170496 | consumed tokens: 349175808 | elapsed time per iteration (s): 5.32 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 7.750774E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.224 | TFLOPs: 72.68 | +[default7]: iteration 334/ 3814 | consumed samples: 171008 | consumed tokens: 350224384 | elapsed time per iteration (s): 5.32 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 7.747494E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.259 | TFLOPs: 72.71 | +[default7]: iteration 335/ 3814 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 5.32 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 7.710798E+00 | loss scale: 4096.0 | grad norm: 0.044 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.312 | TFLOPs: 72.75 | +[default7]: iteration 336/ 3814 | consumed samples: 172032 | consumed tokens: 352321536 | elapsed time per iteration (s): 5.31 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 7.689782E+00 | loss scale: 4096.0 | grad norm: 0.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.447 | TFLOPs: 72.85 | +[default7]: iteration 337/ 3814 | consumed samples: 172544 | consumed tokens: 353370112 | elapsed time per iteration (s): 5.31 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 7.673282E+00 | loss scale: 4096.0 | grad norm: 0.048 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.378 | TFLOPs: 72.80 | +[default7]: iteration 338/ 3814 | consumed samples: 173056 | consumed tokens: 354418688 | elapsed time per iteration (s): 5.31 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 7.670710E+00 | loss scale: 4096.0 | grad norm: 0.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.440 | TFLOPs: 72.84 | +[default7]: iteration 339/ 3814 | consumed samples: 173568 | consumed tokens: 355467264 | elapsed time per iteration (s): 5.33 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 7.679615E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.035 | TFLOPs: 72.54 | +[default7]: iteration 340/ 3814 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 5.33 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 7.645390E+00 | loss scale: 4096.0 | grad norm: 0.065 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.075 | TFLOPs: 72.57 | +[default7]: iteration 341/ 3814 | consumed samples: 174592 | consumed tokens: 357564416 | elapsed time per iteration (s): 5.35 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 7.668277E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.683 | TFLOPs: 72.27 | +[default7]: iteration 342/ 3814 | consumed samples: 175104 | consumed tokens: 358612992 | elapsed time per iteration (s): 5.34 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 7.634766E+00 | loss scale: 4096.0 | grad norm: 0.076 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.850 | TFLOPs: 72.40 | +[default7]: iteration 343/ 3814 | consumed samples: 175616 | consumed tokens: 359661568 | elapsed time per iteration (s): 5.34 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 7.611529E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.882 | TFLOPs: 72.42 | +[default7]: iteration 344/ 3814 | consumed samples: 176128 | consumed tokens: 360710144 | elapsed time per iteration (s): 5.34 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 7.627497E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.843 | TFLOPs: 72.39 | +[default7]: iteration 345/ 3814 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 5.35 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 7.610418E+00 | loss scale: 4096.0 | grad norm: 0.081 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.715 | TFLOPs: 72.29 | +[default7]: iteration 346/ 3814 | consumed samples: 177152 | consumed tokens: 362807296 | elapsed time per iteration (s): 5.32 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 7.599296E+00 | loss scale: 4096.0 | grad norm: 0.069 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.219 | TFLOPs: 72.68 | +[default7]: iteration 347/ 3814 | consumed samples: 177664 | consumed tokens: 363855872 | elapsed time per iteration (s): 5.32 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 7.569544E+00 | loss scale: 4096.0 | grad norm: 0.062 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.291 | TFLOPs: 72.73 | +[default7]: iteration 348/ 3814 | consumed samples: 178176 | consumed tokens: 364904448 | elapsed time per iteration (s): 5.34 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 7.593052E+00 | loss scale: 4096.0 | grad norm: 0.050 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.960 | TFLOPs: 72.48 | +[default7]: iteration 349/ 3814 | consumed samples: 178688 | consumed tokens: 365953024 | elapsed time per iteration (s): 5.33 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 7.557647E+00 | loss scale: 4096.0 | grad norm: 0.063 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.134 | TFLOPs: 72.61 | +[default7]: iteration 350/ 3814 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 5.36 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 7.549578E+00 | loss scale: 4096.0 | grad norm: 0.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.605 | TFLOPs: 72.21 | +[default7]: iteration 351/ 3814 | consumed samples: 179712 | consumed tokens: 368050176 | elapsed time per iteration (s): 5.33 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 7.553605E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.101 | TFLOPs: 72.59 | +[default7]: iteration 352/ 3814 | consumed samples: 180224 | consumed tokens: 369098752 | elapsed time per iteration (s): 5.35 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 7.544461E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.754 | TFLOPs: 72.32 | +[default7]: iteration 353/ 3814 | consumed samples: 180736 | consumed tokens: 370147328 | elapsed time per iteration (s): 5.36 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 7.500840E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.568 | TFLOPs: 72.18 | +[default7]: iteration 354/ 3814 | consumed samples: 181248 | consumed tokens: 371195904 | elapsed time per iteration (s): 5.35 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 7.512877E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.701 | TFLOPs: 72.28 | +[default7]: iteration 355/ 3814 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 5.31 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 7.497238E+00 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.360 | TFLOPs: 72.78 | +[default7]: iteration 356/ 3814 | consumed samples: 182272 | consumed tokens: 373293056 | elapsed time per iteration (s): 5.33 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 7.482638E+00 | loss scale: 4096.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.057 | TFLOPs: 72.55 | +[default7]: iteration 357/ 3814 | consumed samples: 182784 | consumed tokens: 374341632 | elapsed time per iteration (s): 5.33 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 7.493682E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.984 | TFLOPs: 72.50 | +[default7]: iteration 358/ 3814 | consumed samples: 183296 | consumed tokens: 375390208 | elapsed time per iteration (s): 5.36 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.464834E+00 | loss scale: 4096.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.554 | TFLOPs: 72.17 | +[default7]: iteration 359/ 3814 | consumed samples: 183808 | consumed tokens: 376438784 | elapsed time per iteration (s): 5.39 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.426903E+00 | loss scale: 4096.0 | grad norm: 0.063 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.079 | TFLOPs: 71.81 | +[default7]: iteration 360/ 3814 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 5.36 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.425906E+00 | loss scale: 4096.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.606 | TFLOPs: 72.21 | +[default7]: iteration 361/ 3814 | consumed samples: 184832 | consumed tokens: 378535936 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.436962E+00 | loss scale: 4096.0 | grad norm: 0.079 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.730 | TFLOPs: 72.31 | +[default7]: iteration 362/ 3814 | consumed samples: 185344 | consumed tokens: 379584512 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.418443E+00 | loss scale: 4096.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.932 | TFLOPs: 72.46 | +[default7]: iteration 363/ 3814 | consumed samples: 185856 | consumed tokens: 380633088 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.427726E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.631 | TFLOPs: 72.23 | +[default7]: iteration 364/ 3814 | consumed samples: 186368 | consumed tokens: 381681664 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.416316E+00 | loss scale: 4096.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.880 | TFLOPs: 72.42 | +[default7]: iteration 365/ 3814 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 5.39 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.403872E+00 | loss scale: 4096.0 | grad norm: 0.063 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.953 | TFLOPs: 71.72 | +[default7]: iteration 366/ 3814 | consumed samples: 187392 | consumed tokens: 383778816 | elapsed time per iteration (s): 5.38 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.397701E+00 | loss scale: 4096.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.201 | TFLOPs: 71.91 | +[default7]: iteration 367/ 3814 | consumed samples: 187904 | consumed tokens: 384827392 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.396944E+00 | loss scale: 4096.0 | grad norm: 0.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.285 | TFLOPs: 71.97 | +[default7]: iteration 368/ 3814 | consumed samples: 188416 | consumed tokens: 385875968 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.363578E+00 | loss scale: 4096.0 | grad norm: 0.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.373 | TFLOPs: 72.04 | +[default7]: iteration 369/ 3814 | consumed samples: 188928 | consumed tokens: 386924544 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.370751E+00 | loss scale: 4096.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.394 | TFLOPs: 72.05 | +[default7]: iteration 370/ 3814 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.338654E+00 | loss scale: 4096.0 | grad norm: 0.067 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.663 | TFLOPs: 72.26 | +[default7]: iteration 371/ 3814 | consumed samples: 189952 | consumed tokens: 389021696 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.346876E+00 | loss scale: 4096.0 | grad norm: 0.061 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.635 | TFLOPs: 72.23 | +[default7]: iteration 372/ 3814 | consumed samples: 190464 | consumed tokens: 390070272 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.346931E+00 | loss scale: 4096.0 | grad norm: 0.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.761 | TFLOPs: 72.33 | +[default7]: iteration 373/ 3814 | consumed samples: 190976 | consumed tokens: 391118848 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.332341E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.358 | TFLOPs: 72.02 | +[default7]: iteration 374/ 3814 | consumed samples: 191488 | consumed tokens: 392167424 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.337538E+00 | loss scale: 4096.0 | grad norm: 0.051 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.301 | TFLOPs: 71.98 | +[default7]: iteration 375/ 3814 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.336811E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.355 | TFLOPs: 72.02 | +[default7]: iteration 376/ 3814 | consumed samples: 192512 | consumed tokens: 394264576 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.299364E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.672 | TFLOPs: 72.26 | +[default7]: iteration 377/ 3814 | consumed samples: 193024 | consumed tokens: 395313152 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.285187E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.859 | TFLOPs: 72.40 | +[default7]: iteration 378/ 3814 | consumed samples: 193536 | consumed tokens: 396361728 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.270714E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.739 | TFLOPs: 72.31 | +[default7]: iteration 379/ 3814 | consumed samples: 194048 | consumed tokens: 397410304 | elapsed time per iteration (s): 5.38 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.287101E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.164 | TFLOPs: 71.88 | +[default7]: iteration 380/ 3814 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.269789E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.642 | TFLOPs: 72.24 | +[default7]: iteration 381/ 3814 | consumed samples: 195072 | consumed tokens: 399507456 | elapsed time per iteration (s): 5.36 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.271759E+00 | loss scale: 4096.0 | grad norm: 0.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.608 | TFLOPs: 72.21 | +[default7]: iteration 382/ 3814 | consumed samples: 195584 | consumed tokens: 400556032 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.255646E+00 | loss scale: 4096.0 | grad norm: 0.076 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.324 | TFLOPs: 72.00 | +[default7]: iteration 383/ 3814 | consumed samples: 196096 | consumed tokens: 401604608 | elapsed time per iteration (s): 5.38 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.274929E+00 | loss scale: 4096.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.189 | TFLOPs: 71.90 | +[default7]: iteration 384/ 3814 | consumed samples: 196608 | consumed tokens: 402653184 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.256707E+00 | loss scale: 4096.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.296 | TFLOPs: 71.98 | +[default7]: iteration 385/ 3814 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.241549E+00 | loss scale: 4096.0 | grad norm: 0.075 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.274 | TFLOPs: 71.96 | +[default7]: iteration 386/ 3814 | consumed samples: 197632 | consumed tokens: 404750336 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.244162E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.934 | TFLOPs: 72.46 | +[default7]: iteration 387/ 3814 | consumed samples: 198144 | consumed tokens: 405798912 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.218838E+00 | loss scale: 4096.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.969 | TFLOPs: 72.49 | +[default7]: iteration 388/ 3814 | consumed samples: 198656 | consumed tokens: 406847488 | elapsed time per iteration (s): 5.36 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.226381E+00 | loss scale: 4096.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.611 | TFLOPs: 72.22 | +[default7]: iteration 389/ 3814 | consumed samples: 199168 | consumed tokens: 407896064 | elapsed time per iteration (s): 5.33 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.180012E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.981 | TFLOPs: 72.50 | +[default7]: iteration 390/ 3814 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.220870E+00 | loss scale: 4096.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.838 | TFLOPs: 72.39 | +[default7]: iteration 391/ 3814 | consumed samples: 200192 | consumed tokens: 409993216 | elapsed time per iteration (s): 5.34 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.206747E+00 | loss scale: 4096.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.795 | TFLOPs: 72.36 | +[default7]: iteration 392/ 3814 | consumed samples: 200704 | consumed tokens: 411041792 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.159625E+00 | loss scale: 4096.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.698 | TFLOPs: 72.28 | +[default7]: iteration 393/ 3814 | consumed samples: 201216 | consumed tokens: 412090368 | elapsed time per iteration (s): 5.36 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.193634E+00 | loss scale: 4096.0 | grad norm: 0.072 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.585 | TFLOPs: 72.20 | +[default7]: iteration 394/ 3814 | consumed samples: 201728 | consumed tokens: 413138944 | elapsed time per iteration (s): 5.37 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.188359E+00 | loss scale: 4096.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.378 | TFLOPs: 72.04 | +[default7]: iteration 395/ 3814 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 5.35 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 7.168452E+00 | loss scale: 4096.0 | grad norm: 0.070 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.731 | TFLOPs: 72.31 | +[default7]: iteration 396/ 3814 | consumed samples: 202752 | consumed tokens: 415236096 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.150616E+00 | loss scale: 4096.0 | grad norm: 0.072 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.816 | TFLOPs: 72.37 | +[default7]: iteration 397/ 3814 | consumed samples: 203264 | consumed tokens: 416284672 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.156130E+00 | loss scale: 4096.0 | grad norm: 0.082 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.599 | TFLOPs: 72.21 | +[default7]: iteration 398/ 3814 | consumed samples: 203776 | consumed tokens: 417333248 | elapsed time per iteration (s): 5.33 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.147235E+00 | loss scale: 4096.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.000 | TFLOPs: 72.51 | +[default7]: iteration 399/ 3814 | consumed samples: 204288 | consumed tokens: 418381824 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.156435E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.921 | TFLOPs: 72.45 | +[default7]: iteration 400/ 3814 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 5.35 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.138625E+00 | loss scale: 4096.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.684 | TFLOPs: 72.27 | +[default7]: iteration 401/ 3814 | consumed samples: 205312 | consumed tokens: 420478976 | elapsed time per iteration (s): 5.35 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.123762E+00 | loss scale: 4096.0 | grad norm: 0.064 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.645 | TFLOPs: 72.24 | +[default7]: iteration 402/ 3814 | consumed samples: 205824 | consumed tokens: 421527552 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.138614E+00 | loss scale: 4096.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.591 | TFLOPs: 72.20 | +[default7]: iteration 403/ 3814 | consumed samples: 206336 | consumed tokens: 422576128 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.103990E+00 | loss scale: 4096.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.821 | TFLOPs: 72.37 | +[default7]: iteration 404/ 3814 | consumed samples: 206848 | consumed tokens: 423624704 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.096107E+00 | loss scale: 4096.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.398 | TFLOPs: 72.05 | +[default7]: iteration 405/ 3814 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.082436E+00 | loss scale: 4096.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.932 | TFLOPs: 72.46 | +[default7]: iteration 406/ 3814 | consumed samples: 207872 | consumed tokens: 425721856 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.095372E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.608 | TFLOPs: 72.21 | +[default7]: iteration 407/ 3814 | consumed samples: 208384 | consumed tokens: 426770432 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.103911E+00 | loss scale: 4096.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.275 | TFLOPs: 71.96 | +[default7]: iteration 408/ 3814 | consumed samples: 208896 | consumed tokens: 427819008 | elapsed time per iteration (s): 5.39 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.073391E+00 | loss scale: 4096.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.982 | TFLOPs: 71.74 | +[default7]: iteration 409/ 3814 | consumed samples: 209408 | consumed tokens: 428867584 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.074179E+00 | loss scale: 4096.0 | grad norm: 0.074 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.305 | TFLOPs: 71.98 | +[default7]: iteration 410/ 3814 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.053823E+00 | loss scale: 4096.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.540 | TFLOPs: 72.16 | +[default7]: iteration 411/ 3814 | consumed samples: 210432 | consumed tokens: 430964736 | elapsed time per iteration (s): 5.38 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.036213E+00 | loss scale: 4096.0 | grad norm: 0.081 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.216 | TFLOPs: 71.92 | +[default7]: iteration 412/ 3814 | consumed samples: 210944 | consumed tokens: 432013312 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.043305E+00 | loss scale: 4096.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.278 | TFLOPs: 71.96 | +[default7]: iteration 413/ 3814 | consumed samples: 211456 | consumed tokens: 433061888 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.044082E+00 | loss scale: 4096.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.602 | TFLOPs: 72.21 | +[default7]: iteration 414/ 3814 | consumed samples: 211968 | consumed tokens: 434110464 | elapsed time per iteration (s): 5.35 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.010863E+00 | loss scale: 4096.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.655 | TFLOPs: 72.25 | +[default7]: iteration 415/ 3814 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.021451E+00 | loss scale: 4096.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.791 | TFLOPs: 72.35 | +[default7]: iteration 416/ 3814 | consumed samples: 212992 | consumed tokens: 436207616 | elapsed time per iteration (s): 5.36 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.002195E+00 | loss scale: 4096.0 | grad norm: 0.068 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.452 | TFLOPs: 72.10 | +[default7]: iteration 417/ 3814 | consumed samples: 213504 | consumed tokens: 437256192 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 6.986784E+00 | loss scale: 4096.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.388 | TFLOPs: 72.05 | +[default7]: iteration 418/ 3814 | consumed samples: 214016 | consumed tokens: 438304768 | elapsed time per iteration (s): 5.38 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 6.992204E+00 | loss scale: 4096.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.081 | TFLOPs: 71.82 | +[default7]: iteration 419/ 3814 | consumed samples: 214528 | consumed tokens: 439353344 | elapsed time per iteration (s): 5.39 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.028359E+00 | loss scale: 4096.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.984 | TFLOPs: 71.74 | +[default7]: iteration 420/ 3814 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 7.013838E+00 | loss scale: 4096.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.336 | TFLOPs: 72.01 | +[default7]: iteration 421/ 3814 | consumed samples: 215552 | consumed tokens: 441450496 | elapsed time per iteration (s): 5.37 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 6.991523E+00 | loss scale: 4096.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.416 | TFLOPs: 72.07 | +[default7]: iteration 422/ 3814 | consumed samples: 216064 | consumed tokens: 442499072 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 6.972072E+00 | loss scale: 4096.0 | grad norm: 0.060 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.840 | TFLOPs: 72.39 | +[default7]: iteration 423/ 3814 | consumed samples: 216576 | consumed tokens: 443547648 | elapsed time per iteration (s): 5.34 | learning rate: 1.699E-04 | global batch size: 512 | lm loss: 6.959115E+00 | loss scale: 4096.0 | grad norm: 0.065 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.901 | TFLOPs: 72.44 | +[default7]: iteration 424/ 3814 | consumed samples: 217088 | consumed tokens: 444596224 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.990119E+00 | loss scale: 4096.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.495 | TFLOPs: 72.13 | +[default7]: iteration 425/ 3814 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 5.33 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.964822E+00 | loss scale: 4096.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.983 | TFLOPs: 72.50 | +[default7]: iteration 426/ 3814 | consumed samples: 218112 | consumed tokens: 446693376 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.939382E+00 | loss scale: 4096.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.715 | TFLOPs: 72.29 | +[default7]: iteration 427/ 3814 | consumed samples: 218624 | consumed tokens: 447741952 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.934473E+00 | loss scale: 4096.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.624 | TFLOPs: 72.23 | +[default7]: iteration 428/ 3814 | consumed samples: 219136 | consumed tokens: 448790528 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.950829E+00 | loss scale: 4096.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.492 | TFLOPs: 72.13 | +[default7]: iteration 429/ 3814 | consumed samples: 219648 | consumed tokens: 449839104 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.917488E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.547 | TFLOPs: 72.17 | +[default7]: iteration 430/ 3814 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.945871E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.677 | TFLOPs: 72.27 | +[default7]: iteration 431/ 3814 | consumed samples: 220672 | consumed tokens: 451936256 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.878938E+00 | loss scale: 4096.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.512 | TFLOPs: 72.14 | +[default7]: iteration 432/ 3814 | consumed samples: 221184 | consumed tokens: 452984832 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.916042E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.637 | TFLOPs: 72.24 | +[default7]: iteration 433/ 3814 | consumed samples: 221696 | consumed tokens: 454033408 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.897357E+00 | loss scale: 4096.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.562 | TFLOPs: 72.18 | +[default7]: iteration 434/ 3814 | consumed samples: 222208 | consumed tokens: 455081984 | elapsed time per iteration (s): 5.37 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.902483E+00 | loss scale: 4096.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.419 | TFLOPs: 72.07 | +[default7]: iteration 435/ 3814 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 5.37 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.895911E+00 | loss scale: 4096.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.367 | TFLOPs: 72.03 | +[default7]: iteration 436/ 3814 | consumed samples: 223232 | consumed tokens: 457179136 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.923548E+00 | loss scale: 4096.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.747 | TFLOPs: 72.32 | +[default7]: iteration 437/ 3814 | consumed samples: 223744 | consumed tokens: 458227712 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.861038E+00 | loss scale: 4096.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.674 | TFLOPs: 72.26 | +[default7]: iteration 438/ 3814 | consumed samples: 224256 | consumed tokens: 459276288 | elapsed time per iteration (s): 5.39 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.886221E+00 | loss scale: 4096.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.998 | TFLOPs: 71.75 | +[default7]: iteration 439/ 3814 | consumed samples: 224768 | consumed tokens: 460324864 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.895135E+00 | loss scale: 4096.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.482 | TFLOPs: 72.12 | +[default7]: iteration 440/ 3814 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 5.35 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.870699E+00 | loss scale: 4096.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.620 | TFLOPs: 72.22 | +[default7]: iteration 441/ 3814 | consumed samples: 225792 | consumed tokens: 462422016 | elapsed time per iteration (s): 5.36 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.884587E+00 | loss scale: 4096.0 | grad norm: 0.076 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.528 | TFLOPs: 72.15 | +[default7]: iteration 442/ 3814 | consumed samples: 226304 | consumed tokens: 463470592 | elapsed time per iteration (s): 5.39 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 6.871584E+00 | loss scale: 4096.0 | grad norm: 0.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.964 | TFLOPs: 71.73 | +[default7]: iteration 443/ 3814 | consumed samples: 226816 | consumed tokens: 464519168 | elapsed time per iteration (s): 5.39 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.829201E+00 | loss scale: 4096.0 | grad norm: 0.090 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.065 | TFLOPs: 71.80 | +[default7]: iteration 444/ 3814 | consumed samples: 227328 | consumed tokens: 465567744 | elapsed time per iteration (s): 5.38 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.845695E+00 | loss scale: 4096.0 | grad norm: 0.091 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.115 | TFLOPs: 71.84 | +[default7]: iteration 445/ 3814 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 5.37 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.838239E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.368 | TFLOPs: 72.03 | +[default7]: iteration 446/ 3814 | consumed samples: 228352 | consumed tokens: 467664896 | elapsed time per iteration (s): 5.35 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.841359E+00 | loss scale: 4096.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.753 | TFLOPs: 72.32 | +[default7]: iteration 447/ 3814 | consumed samples: 228864 | consumed tokens: 468713472 | elapsed time per iteration (s): 5.36 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.823277E+00 | loss scale: 4096.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.471 | TFLOPs: 72.11 | +[default7]: iteration 448/ 3814 | consumed samples: 229376 | consumed tokens: 469762048 | elapsed time per iteration (s): 5.36 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.848153E+00 | loss scale: 4096.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.545 | TFLOPs: 72.17 | +[default7]: iteration 449/ 3814 | consumed samples: 229888 | consumed tokens: 470810624 | elapsed time per iteration (s): 5.34 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.789059E+00 | loss scale: 4096.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.941 | TFLOPs: 72.46 | +[default7]: iteration 450/ 3814 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 5.35 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.815103E+00 | loss scale: 4096.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.764 | TFLOPs: 72.33 | +[default7]: iteration 451/ 3814 | consumed samples: 230912 | consumed tokens: 472907776 | elapsed time per iteration (s): 5.36 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.795317E+00 | loss scale: 4096.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.595 | TFLOPs: 72.20 | +[default7]: iteration 452/ 3814 | consumed samples: 231424 | consumed tokens: 473956352 | elapsed time per iteration (s): 5.37 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.822940E+00 | loss scale: 4096.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.286 | TFLOPs: 71.97 | +[default7]: iteration 453/ 3814 | consumed samples: 231936 | consumed tokens: 475004928 | elapsed time per iteration (s): 5.35 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.772912E+00 | loss scale: 4096.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.718 | TFLOPs: 72.30 | +[default7]: iteration 454/ 3814 | consumed samples: 232448 | consumed tokens: 476053504 | elapsed time per iteration (s): 5.35 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.763817E+00 | loss scale: 4096.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.655 | TFLOPs: 72.25 | +[default7]: iteration 455/ 3814 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 5.40 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.772449E+00 | loss scale: 4096.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.871 | TFLOPs: 71.66 | +[default7]: iteration 456/ 3814 | consumed samples: 233472 | consumed tokens: 478150656 | elapsed time per iteration (s): 5.39 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.785627E+00 | loss scale: 4096.0 | grad norm: 0.084 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.989 | TFLOPs: 71.75 | +[default7]: iteration 457/ 3814 | consumed samples: 233984 | consumed tokens: 479199232 | elapsed time per iteration (s): 5.37 | learning rate: 1.697E-04 | global batch size: 512 | lm loss: 6.774328E+00 | loss scale: 4096.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.276 | TFLOPs: 71.96 | +[default7]: iteration 458/ 3814 | consumed samples: 234496 | consumed tokens: 480247808 | elapsed time per iteration (s): 5.36 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.767707E+00 | loss scale: 4096.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.491 | TFLOPs: 72.13 | +[default7]: iteration 459/ 3814 | consumed samples: 235008 | consumed tokens: 481296384 | elapsed time per iteration (s): 5.41 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.732229E+00 | loss scale: 4096.0 | grad norm: 0.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.600 | TFLOPs: 71.45 | +[default7]: iteration 460/ 3814 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 5.39 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.754882E+00 | loss scale: 4096.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.916 | TFLOPs: 71.69 | +[default7]: iteration 461/ 3814 | consumed samples: 236032 | consumed tokens: 483393536 | elapsed time per iteration (s): 5.43 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.742878E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.369 | TFLOPs: 71.28 | +[default7]: iteration 462/ 3814 | consumed samples: 236544 | consumed tokens: 484442112 | elapsed time per iteration (s): 5.38 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.727132E+00 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.105 | TFLOPs: 71.83 | +[default7]: iteration 463/ 3814 | consumed samples: 237056 | consumed tokens: 485490688 | elapsed time per iteration (s): 5.40 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.727827E+00 | loss scale: 4096.0 | grad norm: 0.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.731 | TFLOPs: 71.55 | +[default7]: iteration 464/ 3814 | consumed samples: 237568 | consumed tokens: 486539264 | elapsed time per iteration (s): 5.39 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.721567E+00 | loss scale: 4096.0 | grad norm: 0.072 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.048 | TFLOPs: 71.79 | +[default7]: iteration 465/ 3814 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 5.37 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.733825E+00 | loss scale: 4096.0 | grad norm: 0.068 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.367 | TFLOPs: 72.03 | +[default7]: iteration 466/ 3814 | consumed samples: 238592 | consumed tokens: 488636416 | elapsed time per iteration (s): 5.36 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.766405E+00 | loss scale: 4096.0 | grad norm: 0.058 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.486 | TFLOPs: 72.12 | +[default7]: iteration 467/ 3814 | consumed samples: 239104 | consumed tokens: 489684992 | elapsed time per iteration (s): 5.36 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.712663E+00 | loss scale: 4096.0 | grad norm: 0.065 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.485 | TFLOPs: 72.12 | +[default7]: iteration 468/ 3814 | consumed samples: 239616 | consumed tokens: 490733568 | elapsed time per iteration (s): 5.35 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.710913E+00 | loss scale: 4096.0 | grad norm: 0.074 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.711 | TFLOPs: 72.29 | +[default7]: iteration 469/ 3814 | consumed samples: 240128 | consumed tokens: 491782144 | elapsed time per iteration (s): 5.39 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.683928E+00 | loss scale: 4096.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.936 | TFLOPs: 71.71 | +[default7]: iteration 470/ 3814 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 5.36 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 6.692328E+00 | loss scale: 4096.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.456 | TFLOPs: 72.10 | +[default7]: iteration 471/ 3814 | consumed samples: 241152 | consumed tokens: 493879296 | elapsed time per iteration (s): 5.34 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.718852E+00 | loss scale: 4096.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.794 | TFLOPs: 72.35 | +[default7]: iteration 472/ 3814 | consumed samples: 241664 | consumed tokens: 494927872 | elapsed time per iteration (s): 5.38 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.697626E+00 | loss scale: 4096.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.150 | TFLOPs: 71.87 | +[default7]: iteration 473/ 3814 | consumed samples: 242176 | consumed tokens: 495976448 | elapsed time per iteration (s): 5.35 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.706548E+00 | loss scale: 4096.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.720 | TFLOPs: 72.30 | +[default7]: iteration 474/ 3814 | consumed samples: 242688 | consumed tokens: 497025024 | elapsed time per iteration (s): 5.35 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.693522E+00 | loss scale: 4096.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.617 | TFLOPs: 72.22 | +[default7]: iteration 475/ 3814 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 5.37 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.669992E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.381 | TFLOPs: 72.04 | +[default7]: iteration 476/ 3814 | consumed samples: 243712 | consumed tokens: 499122176 | elapsed time per iteration (s): 5.35 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.679455E+00 | loss scale: 4096.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.622 | TFLOPs: 72.22 | +[default7]: iteration 477/ 3814 | consumed samples: 244224 | consumed tokens: 500170752 | elapsed time per iteration (s): 5.39 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.670889E+00 | loss scale: 4096.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.027 | TFLOPs: 71.77 | +[default7]: iteration 478/ 3814 | consumed samples: 244736 | consumed tokens: 501219328 | elapsed time per iteration (s): 5.36 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.626238E+00 | loss scale: 4096.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.538 | TFLOPs: 72.16 | +[default7]: iteration 479/ 3814 | consumed samples: 245248 | consumed tokens: 502267904 | elapsed time per iteration (s): 5.37 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.633219E+00 | loss scale: 4096.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.342 | TFLOPs: 72.01 | +[default7]: iteration 480/ 3814 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 5.34 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.659575E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.870 | TFLOPs: 72.41 | +[default7]: iteration 481/ 3814 | consumed samples: 246272 | consumed tokens: 504365056 | elapsed time per iteration (s): 5.33 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.633385E+00 | loss scale: 4096.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.977 | TFLOPs: 72.49 | +[default7]: iteration 482/ 3814 | consumed samples: 246784 | consumed tokens: 505413632 | elapsed time per iteration (s): 5.35 | learning rate: 1.695E-04 | global batch size: 512 | lm loss: 6.635938E+00 | loss scale: 4096.0 | grad norm: 0.087 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.624 | TFLOPs: 72.23 | +[default7]: iteration 483/ 3814 | consumed samples: 247296 | consumed tokens: 506462208 | elapsed time per iteration (s): 5.35 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.627094E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.616 | TFLOPs: 72.22 | +[default7]: iteration 484/ 3814 | consumed samples: 247808 | consumed tokens: 507510784 | elapsed time per iteration (s): 5.33 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.625707E+00 | loss scale: 4096.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.136 | TFLOPs: 72.61 | +[default7]: iteration 485/ 3814 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 5.35 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.634046E+00 | loss scale: 4096.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.621 | TFLOPs: 72.22 | +[default7]: iteration 486/ 3814 | consumed samples: 248832 | consumed tokens: 509607936 | elapsed time per iteration (s): 5.36 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.620330E+00 | loss scale: 4096.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.604 | TFLOPs: 72.21 | +[default7]: iteration 487/ 3814 | consumed samples: 249344 | consumed tokens: 510656512 | elapsed time per iteration (s): 5.35 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.620696E+00 | loss scale: 4096.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.668 | TFLOPs: 72.26 | +[default7]: iteration 488/ 3814 | consumed samples: 249856 | consumed tokens: 511705088 | elapsed time per iteration (s): 5.34 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.597885E+00 | loss scale: 4096.0 | grad norm: 0.090 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.825 | TFLOPs: 72.38 | +[default7]: iteration 489/ 3814 | consumed samples: 250368 | consumed tokens: 512753664 | elapsed time per iteration (s): 5.34 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.620809E+00 | loss scale: 4096.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.841 | TFLOPs: 72.39 | +[default7]: iteration 490/ 3814 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 5.36 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.585564E+00 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.572 | TFLOPs: 72.19 | +[default7]: iteration 491/ 3814 | consumed samples: 251392 | consumed tokens: 514850816 | elapsed time per iteration (s): 5.36 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.570176E+00 | loss scale: 4096.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.512 | TFLOPs: 72.14 | +[default7]: iteration 492/ 3814 | consumed samples: 251904 | consumed tokens: 515899392 | elapsed time per iteration (s): 5.36 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.594709E+00 | loss scale: 4096.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.455 | TFLOPs: 72.10 | +[default7]: iteration 493/ 3814 | consumed samples: 252416 | consumed tokens: 516947968 | elapsed time per iteration (s): 5.36 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 6.579369E+00 | loss scale: 4096.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.547 | TFLOPs: 72.17 | +[default7]: iteration 494/ 3814 | consumed samples: 252928 | consumed tokens: 517996544 | elapsed time per iteration (s): 5.36 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.581556E+00 | loss scale: 4096.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.543 | TFLOPs: 72.16 | +[default7]: iteration 495/ 3814 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 5.37 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.554482E+00 | loss scale: 4096.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.292 | TFLOPs: 71.98 | +[default7]: iteration 496/ 3814 | consumed samples: 253952 | consumed tokens: 520093696 | elapsed time per iteration (s): 5.35 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.560294E+00 | loss scale: 4096.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.774 | TFLOPs: 72.34 | +[default7]: iteration 497/ 3814 | consumed samples: 254464 | consumed tokens: 521142272 | elapsed time per iteration (s): 5.34 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.545712E+00 | loss scale: 4096.0 | grad norm: 0.090 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.828 | TFLOPs: 72.38 | +[default7]: iteration 498/ 3814 | consumed samples: 254976 | consumed tokens: 522190848 | elapsed time per iteration (s): 5.33 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.536245E+00 | loss scale: 4096.0 | grad norm: 0.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.994 | TFLOPs: 72.51 | +[default7]: iteration 499/ 3814 | consumed samples: 255488 | consumed tokens: 523239424 | elapsed time per iteration (s): 5.35 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.537013E+00 | loss scale: 4096.0 | grad norm: 0.087 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.653 | TFLOPs: 72.25 | +[default1]:[2023-02-16 12:05:05,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_01-model_states.pt... +[default7]: iteration 500/ 3814 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 5.32 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.554545E+00 | loss scale: 8192.0 | grad norm: 0.056 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 96.199 | TFLOPs: 72.66 | +[default0]:saving checkpoint at iteration 500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 12:05:05,257] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step500 is begin to save! +[default0]:[2023-02-16 12:05:05,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:05,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,592] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:05,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:05,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,716] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:05,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,827] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:05,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,887] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:05,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:05,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:05,950] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:05,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:05,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,011] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,060] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,114] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,125] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,181] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,236] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,224] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,355] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,401] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,633] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,742] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,798] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,822] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:06,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,881] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,856] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:06,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:06,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:06,973] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:06,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:06,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:07,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:07,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:07,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,095] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:07,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:07,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:07,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:07,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,201] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:07,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 12:05:07,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,258] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 12:05:07,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,320] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_00-model_states.pt... +[default1]:[2023-02-16 12:05:07,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:07,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,356] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:05:07,357] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 12:05:07,358] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 12:05:07,358] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 12:05:07,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:05:07,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 12:05:07,322] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 12:05:07,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 12:05:07,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:05:07,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:05:07,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:07,825] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:07,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,851] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:07,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:07,906] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:07,907] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,906] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,906] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,923] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,913] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:07,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:07,922] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:07,923] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:07,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:07,915] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:07,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:07,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:07,919] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:07,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:07,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:07,968] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:07,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:07,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:07,929] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:07,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:07,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:07,919] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:07,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:07,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:07,976] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:07,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:07,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:07,939] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:07,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,998] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:07,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:07,998] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:07,998] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:07,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:07,946] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:07,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:07,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:07,996] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:07,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:07,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:07,943] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:07,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:07,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:07,983] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:07,983] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,019] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:07,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:07,989] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:07,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,974] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,026] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:07,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:07,989] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:07,989] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:07,983] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:07,983] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:07,984] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:07,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:07,972] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:07,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:07,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:07,982] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:07,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,004] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:08,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:08,043] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:08,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:08,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:08,057] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:08,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:08,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:08,042] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:08,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,044] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:08,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:08,029] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:08,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:08,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:08,072] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:08,072] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,043] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:08,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:08,026] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:08,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,049] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,032] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 12:05:08,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:05:08,105] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:05:08,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,074] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,074] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:08,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:08,058] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:08,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:08,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:08,093] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:08,093] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:08,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:08,139] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:08,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,101] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,153] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,151] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:08,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:08,106] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:08,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,078] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,078] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,187] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,154] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,181] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:08,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:08,155] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:08,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 12:05:08,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:05:08,187] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:05:08,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:08,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:08,175] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:08,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:08,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:08,170] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:08,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 12:05:08,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:05:08,166] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:05:08,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:08,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:08,183] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:08,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:08,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:08,202] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:08,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 12:05:08,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:05:08,225] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:05:08,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 12:05:08,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:05:08,237] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:05:08,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 12:05:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:05:08,325] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:05:08,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 12:05:08,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:05:08,322] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:05:08,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 12:05:08,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:05:08,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:05:08,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:time (ms) | save-checkpoint: 3093.42 +[default0]: successfully saved checkpoint at iteration 500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 501/ 3814 | consumed samples: 256512 | consumed tokens: 525336576 | elapsed time per iteration (s): 8.47 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.532092E+00 | loss scale: 8192.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 60.468 | TFLOPs: 45.67 | +[default7]: iteration 502/ 3814 | consumed samples: 257024 | consumed tokens: 526385152 | elapsed time per iteration (s): 5.37 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.560713E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.299 | TFLOPs: 71.98 | +[default7]: iteration 503/ 3814 | consumed samples: 257536 | consumed tokens: 527433728 | elapsed time per iteration (s): 5.37 | learning rate: 1.693E-04 | global batch size: 512 | lm loss: 6.531688E+00 | loss scale: 8192.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.259 | TFLOPs: 71.95 | +[default7]: iteration 504/ 3814 | consumed samples: 258048 | consumed tokens: 528482304 | elapsed time per iteration (s): 5.37 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.560142E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.404 | TFLOPs: 72.06 | +[default7]: iteration 505/ 3814 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 5.37 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.516154E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.368 | TFLOPs: 72.03 | +[default7]: iteration 506/ 3814 | consumed samples: 259072 | consumed tokens: 530579456 | elapsed time per iteration (s): 5.38 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.527365E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.133 | TFLOPs: 71.85 | +[default7]: iteration 507/ 3814 | consumed samples: 259584 | consumed tokens: 531628032 | elapsed time per iteration (s): 5.38 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.526836E+00 | loss scale: 8192.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.145 | TFLOPs: 71.86 | +[default7]: iteration 508/ 3814 | consumed samples: 260096 | consumed tokens: 532676608 | elapsed time per iteration (s): 5.38 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.536401E+00 | loss scale: 8192.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.184 | TFLOPs: 71.89 | +[default7]: iteration 509/ 3814 | consumed samples: 260608 | consumed tokens: 533725184 | elapsed time per iteration (s): 5.38 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.517500E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.130 | TFLOPs: 71.85 | +[default7]: iteration 510/ 3814 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 5.41 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.522256E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.717 | TFLOPs: 71.54 | +[default7]: iteration 511/ 3814 | consumed samples: 261632 | consumed tokens: 535822336 | elapsed time per iteration (s): 5.41 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.507563E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.670 | TFLOPs: 71.51 | +[default7]: iteration 512/ 3814 | consumed samples: 262144 | consumed tokens: 536870912 | elapsed time per iteration (s): 5.39 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.525630E+00 | loss scale: 8192.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.935 | TFLOPs: 71.71 | +[default7]: iteration 513/ 3814 | consumed samples: 262656 | consumed tokens: 537919488 | elapsed time per iteration (s): 5.39 | learning rate: 1.692E-04 | global batch size: 512 | lm loss: 6.483363E+00 | loss scale: 8192.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.919 | TFLOPs: 71.69 | +[default7]: iteration 514/ 3814 | consumed samples: 263168 | consumed tokens: 538968064 | elapsed time per iteration (s): 5.40 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.484970E+00 | loss scale: 8192.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.783 | TFLOPs: 71.59 | +[default7]: iteration 515/ 3814 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 5.40 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.486080E+00 | loss scale: 8192.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.891 | TFLOPs: 71.67 | +[default7]: iteration 516/ 3814 | consumed samples: 264192 | consumed tokens: 541065216 | elapsed time per iteration (s): 5.38 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.468889E+00 | loss scale: 8192.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.079 | TFLOPs: 71.81 | +[default7]: iteration 517/ 3814 | consumed samples: 264704 | consumed tokens: 542113792 | elapsed time per iteration (s): 5.41 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.476698E+00 | loss scale: 8192.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.589 | TFLOPs: 71.44 | +[default7]: iteration 518/ 3814 | consumed samples: 265216 | consumed tokens: 543162368 | elapsed time per iteration (s): 5.41 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.479772E+00 | loss scale: 8192.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.614 | TFLOPs: 71.46 | +[default7]: iteration 519/ 3814 | consumed samples: 265728 | consumed tokens: 544210944 | elapsed time per iteration (s): 5.41 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.466921E+00 | loss scale: 8192.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.619 | TFLOPs: 71.47 | +[default7]: iteration 520/ 3814 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 5.38 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.472250E+00 | loss scale: 8192.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.238 | TFLOPs: 71.93 | +[default7]: iteration 521/ 3814 | consumed samples: 266752 | consumed tokens: 546308096 | elapsed time per iteration (s): 5.39 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.434220E+00 | loss scale: 8192.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.910 | TFLOPs: 71.69 | +[default7]: iteration 522/ 3814 | consumed samples: 267264 | consumed tokens: 547356672 | elapsed time per iteration (s): 5.38 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 6.450847E+00 | loss scale: 8192.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.081 | TFLOPs: 71.82 | +[default7]: iteration 523/ 3814 | consumed samples: 267776 | consumed tokens: 548405248 | elapsed time per iteration (s): 5.39 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.457996E+00 | loss scale: 8192.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.916 | TFLOPs: 71.69 | +[default7]: iteration 524/ 3814 | consumed samples: 268288 | consumed tokens: 549453824 | elapsed time per iteration (s): 5.38 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.458824E+00 | loss scale: 8192.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.152 | TFLOPs: 71.87 | +[default7]: iteration 525/ 3814 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 5.38 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.481187E+00 | loss scale: 8192.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.161 | TFLOPs: 71.88 | +[default7]: iteration 526/ 3814 | consumed samples: 269312 | consumed tokens: 551550976 | elapsed time per iteration (s): 5.39 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.455653E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.989 | TFLOPs: 71.75 | +[default7]: iteration 527/ 3814 | consumed samples: 269824 | consumed tokens: 552599552 | elapsed time per iteration (s): 5.39 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.452464E+00 | loss scale: 8192.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.948 | TFLOPs: 71.72 | +[default7]: iteration 528/ 3814 | consumed samples: 270336 | consumed tokens: 553648128 | elapsed time per iteration (s): 5.38 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.448640E+00 | loss scale: 8192.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.203 | TFLOPs: 71.91 | +[default7]: iteration 529/ 3814 | consumed samples: 270848 | consumed tokens: 554696704 | elapsed time per iteration (s): 5.40 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.470457E+00 | loss scale: 8192.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.825 | TFLOPs: 71.62 | +[default7]: iteration 530/ 3814 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 5.37 | learning rate: 1.690E-04 | global batch size: 512 | lm loss: 6.419222E+00 | loss scale: 8192.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.256 | TFLOPs: 71.95 | +[default7]: iteration 531/ 3814 | consumed samples: 271872 | consumed tokens: 556793856 | elapsed time per iteration (s): 5.38 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.442293E+00 | loss scale: 8192.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.136 | TFLOPs: 71.86 | +[default7]: iteration 532/ 3814 | consumed samples: 272384 | consumed tokens: 557842432 | elapsed time per iteration (s): 5.39 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.446114E+00 | loss scale: 8192.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.078 | TFLOPs: 71.81 | +[default7]: iteration 533/ 3814 | consumed samples: 272896 | consumed tokens: 558891008 | elapsed time per iteration (s): 5.39 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.440521E+00 | loss scale: 8192.0 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.926 | TFLOPs: 71.70 | +[default7]: iteration 534/ 3814 | consumed samples: 273408 | consumed tokens: 559939584 | elapsed time per iteration (s): 5.43 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.414691E+00 | loss scale: 8192.0 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.358 | TFLOPs: 71.27 | +[default7]: iteration 535/ 3814 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 5.39 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.430233E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.990 | TFLOPs: 71.75 | +[default7]: iteration 536/ 3814 | consumed samples: 274432 | consumed tokens: 562036736 | elapsed time per iteration (s): 5.40 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.437981E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.865 | TFLOPs: 71.65 | +[default7]: iteration 537/ 3814 | consumed samples: 274944 | consumed tokens: 563085312 | elapsed time per iteration (s): 5.41 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.412109E+00 | loss scale: 8192.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.632 | TFLOPs: 71.48 | +[default7]: iteration 538/ 3814 | consumed samples: 275456 | consumed tokens: 564133888 | elapsed time per iteration (s): 5.40 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 6.415247E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.784 | TFLOPs: 71.59 | +[default7]: iteration 539/ 3814 | consumed samples: 275968 | consumed tokens: 565182464 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.424036E+00 | loss scale: 8192.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.767 | TFLOPs: 71.58 | +[default7]: iteration 540/ 3814 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.419887E+00 | loss scale: 8192.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.901 | TFLOPs: 71.68 | +[default7]: iteration 541/ 3814 | consumed samples: 276992 | consumed tokens: 567279616 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.397782E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.876 | TFLOPs: 71.66 | +[default7]: iteration 542/ 3814 | consumed samples: 277504 | consumed tokens: 568328192 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.391806E+00 | loss scale: 8192.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.790 | TFLOPs: 71.60 | +[default7]: iteration 543/ 3814 | consumed samples: 278016 | consumed tokens: 569376768 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.383320E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.823 | TFLOPs: 71.62 | +[default7]: iteration 544/ 3814 | consumed samples: 278528 | consumed tokens: 570425344 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.417713E+00 | loss scale: 8192.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.855 | TFLOPs: 71.64 | +[default7]: iteration 545/ 3814 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 5.39 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.340552E+00 | loss scale: 8192.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.959 | TFLOPs: 71.72 | +[default7]: iteration 546/ 3814 | consumed samples: 279552 | consumed tokens: 572522496 | elapsed time per iteration (s): 5.40 | learning rate: 1.688E-04 | global batch size: 512 | lm loss: 6.370675E+00 | loss scale: 8192.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.844 | TFLOPs: 71.64 | +[default7]: iteration 547/ 3814 | consumed samples: 280064 | consumed tokens: 573571072 | elapsed time per iteration (s): 5.39 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.405163E+00 | loss scale: 8192.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.011 | TFLOPs: 71.76 | +[default7]: iteration 548/ 3814 | consumed samples: 280576 | consumed tokens: 574619648 | elapsed time per iteration (s): 5.41 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.349636E+00 | loss scale: 8192.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.655 | TFLOPs: 71.49 | +[default7]: iteration 549/ 3814 | consumed samples: 281088 | consumed tokens: 575668224 | elapsed time per iteration (s): 5.40 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.388384E+00 | loss scale: 8192.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.782 | TFLOPs: 71.59 | +[default7]: iteration 550/ 3814 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 5.40 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.338520E+00 | loss scale: 8192.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.739 | TFLOPs: 71.56 | +[default7]: iteration 551/ 3814 | consumed samples: 282112 | consumed tokens: 577765376 | elapsed time per iteration (s): 5.40 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.363245E+00 | loss scale: 8192.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.808 | TFLOPs: 71.61 | +[default7]: iteration 552/ 3814 | consumed samples: 282624 | consumed tokens: 578813952 | elapsed time per iteration (s): 5.41 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.334118E+00 | loss scale: 8192.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.707 | TFLOPs: 71.53 | +[default7]: iteration 553/ 3814 | consumed samples: 283136 | consumed tokens: 579862528 | elapsed time per iteration (s): 5.41 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.359723E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.673 | TFLOPs: 71.51 | +[default7]: iteration 554/ 3814 | consumed samples: 283648 | consumed tokens: 580911104 | elapsed time per iteration (s): 5.41 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 6.351055E+00 | loss scale: 8192.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.690 | TFLOPs: 71.52 | +[default7]: iteration 555/ 3814 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 5.40 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.339527E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.863 | TFLOPs: 71.65 | +[default7]: iteration 556/ 3814 | consumed samples: 284672 | consumed tokens: 583008256 | elapsed time per iteration (s): 5.40 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.354596E+00 | loss scale: 8192.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.812 | TFLOPs: 71.61 | +[default7]: iteration 557/ 3814 | consumed samples: 285184 | consumed tokens: 584056832 | elapsed time per iteration (s): 5.42 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.339110E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.528 | TFLOPs: 71.40 | +[default7]: iteration 558/ 3814 | consumed samples: 285696 | consumed tokens: 585105408 | elapsed time per iteration (s): 5.41 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.363990E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.644 | TFLOPs: 71.49 | +[default7]: iteration 559/ 3814 | consumed samples: 286208 | consumed tokens: 586153984 | elapsed time per iteration (s): 5.38 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.332726E+00 | loss scale: 8192.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.089 | TFLOPs: 71.82 | +[default7]: iteration 560/ 3814 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 5.41 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.307502E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.715 | TFLOPs: 71.54 | +[default7]: iteration 561/ 3814 | consumed samples: 287232 | consumed tokens: 588251136 | elapsed time per iteration (s): 5.41 | learning rate: 1.686E-04 | global batch size: 512 | lm loss: 6.344262E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.707 | TFLOPs: 71.53 | +[default7]: iteration 562/ 3814 | consumed samples: 287744 | consumed tokens: 589299712 | elapsed time per iteration (s): 5.41 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.327391E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.611 | TFLOPs: 71.46 | +[default7]: iteration 563/ 3814 | consumed samples: 288256 | consumed tokens: 590348288 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.289438E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.831 | TFLOPs: 71.63 | +[default7]: iteration 564/ 3814 | consumed samples: 288768 | consumed tokens: 591396864 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.312262E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.852 | TFLOPs: 71.64 | +[default7]: iteration 565/ 3814 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.320117E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.751 | TFLOPs: 71.57 | +[default7]: iteration 566/ 3814 | consumed samples: 289792 | consumed tokens: 593494016 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.307928E+00 | loss scale: 8192.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.849 | TFLOPs: 71.64 | +[default7]: iteration 567/ 3814 | consumed samples: 290304 | consumed tokens: 594542592 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.276004E+00 | loss scale: 8192.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.744 | TFLOPs: 71.56 | +[default7]: iteration 568/ 3814 | consumed samples: 290816 | consumed tokens: 595591168 | elapsed time per iteration (s): 5.40 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 6.273190E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.883 | TFLOPs: 71.67 | +[default7]: iteration 569/ 3814 | consumed samples: 291328 | consumed tokens: 596639744 | elapsed time per iteration (s): 5.42 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.287543E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.482 | TFLOPs: 71.36 | +[default7]: iteration 570/ 3814 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 5.40 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.305054E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.732 | TFLOPs: 71.55 | +[default7]: iteration 571/ 3814 | consumed samples: 292352 | consumed tokens: 598736896 | elapsed time per iteration (s): 5.40 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.309064E+00 | loss scale: 8192.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.867 | TFLOPs: 71.65 | +[default7]: iteration 572/ 3814 | consumed samples: 292864 | consumed tokens: 599785472 | elapsed time per iteration (s): 5.40 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.306753E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.896 | TFLOPs: 71.68 | +[default7]: iteration 573/ 3814 | consumed samples: 293376 | consumed tokens: 600834048 | elapsed time per iteration (s): 5.39 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.274761E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.063 | TFLOPs: 71.80 | +[default7]: iteration 574/ 3814 | consumed samples: 293888 | consumed tokens: 601882624 | elapsed time per iteration (s): 5.39 | learning rate: 1.684E-04 | global batch size: 512 | lm loss: 6.317622E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.998 | TFLOPs: 71.75 | +[default7]: iteration 575/ 3814 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 5.40 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.283443E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.812 | TFLOPs: 71.61 | +[default7]: iteration 576/ 3814 | consumed samples: 294912 | consumed tokens: 603979776 | elapsed time per iteration (s): 5.41 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.294074E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.627 | TFLOPs: 71.47 | +[default7]: iteration 577/ 3814 | consumed samples: 295424 | consumed tokens: 605028352 | elapsed time per iteration (s): 5.43 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.269750E+00 | loss scale: 8192.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.340 | TFLOPs: 71.26 | +[default7]: iteration 578/ 3814 | consumed samples: 295936 | consumed tokens: 606076928 | elapsed time per iteration (s): 5.41 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.283820E+00 | loss scale: 8192.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.593 | TFLOPs: 71.45 | +[default7]: iteration 579/ 3814 | consumed samples: 296448 | consumed tokens: 607125504 | elapsed time per iteration (s): 5.39 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.273713E+00 | loss scale: 8192.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.903 | TFLOPs: 71.68 | +[default7]: iteration 580/ 3814 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 5.43 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.258425E+00 | loss scale: 8192.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.326 | TFLOPs: 71.25 | +[default7]: iteration 581/ 3814 | consumed samples: 297472 | consumed tokens: 609222656 | elapsed time per iteration (s): 5.42 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 6.259685E+00 | loss scale: 8192.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.431 | TFLOPs: 71.32 | +[default7]: iteration 582/ 3814 | consumed samples: 297984 | consumed tokens: 610271232 | elapsed time per iteration (s): 5.41 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.270973E+00 | loss scale: 8192.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.600 | TFLOPs: 71.45 | +[default7]: iteration 583/ 3814 | consumed samples: 298496 | consumed tokens: 611319808 | elapsed time per iteration (s): 5.41 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.254884E+00 | loss scale: 8192.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.632 | TFLOPs: 71.48 | +[default7]: iteration 584/ 3814 | consumed samples: 299008 | consumed tokens: 612368384 | elapsed time per iteration (s): 5.43 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.253541E+00 | loss scale: 8192.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.328 | TFLOPs: 71.25 | +[default7]: iteration 585/ 3814 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 5.43 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.278913E+00 | loss scale: 8192.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.334 | TFLOPs: 71.25 | +[default7]: iteration 586/ 3814 | consumed samples: 300032 | consumed tokens: 614465536 | elapsed time per iteration (s): 5.41 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.260659E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.653 | TFLOPs: 71.49 | +[default7]: iteration 587/ 3814 | consumed samples: 300544 | consumed tokens: 615514112 | elapsed time per iteration (s): 5.43 | learning rate: 1.682E-04 | global batch size: 512 | lm loss: 6.246169E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.371 | TFLOPs: 71.28 | +[default7]: iteration 588/ 3814 | consumed samples: 301056 | consumed tokens: 616562688 | elapsed time per iteration (s): 5.42 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.252624E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.499 | TFLOPs: 71.38 | +[default7]: iteration 589/ 3814 | consumed samples: 301568 | consumed tokens: 617611264 | elapsed time per iteration (s): 5.42 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.248983E+00 | loss scale: 8192.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.386 | TFLOPs: 71.29 | +[default7]: iteration 590/ 3814 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 5.42 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.195771E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.497 | TFLOPs: 71.37 | +[default7]: iteration 591/ 3814 | consumed samples: 302592 | consumed tokens: 619708416 | elapsed time per iteration (s): 5.42 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.255544E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.388 | TFLOPs: 71.29 | +[default7]: iteration 592/ 3814 | consumed samples: 303104 | consumed tokens: 620756992 | elapsed time per iteration (s): 5.41 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.214597E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.616 | TFLOPs: 71.46 | +[default7]: iteration 593/ 3814 | consumed samples: 303616 | consumed tokens: 621805568 | elapsed time per iteration (s): 5.43 | learning rate: 1.681E-04 | global batch size: 512 | lm loss: 6.227179E+00 | loss scale: 8192.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 594/ 3814 | consumed samples: 304128 | consumed tokens: 622854144 | elapsed time per iteration (s): 5.42 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.234500E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.423 | TFLOPs: 71.32 | +[default7]: iteration 595/ 3814 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 5.42 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.232759E+00 | loss scale: 8192.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.388 | TFLOPs: 71.29 | +[default7]: iteration 596/ 3814 | consumed samples: 305152 | consumed tokens: 624951296 | elapsed time per iteration (s): 5.41 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.207989E+00 | loss scale: 8192.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.563 | TFLOPs: 71.42 | +[default7]: iteration 597/ 3814 | consumed samples: 305664 | consumed tokens: 625999872 | elapsed time per iteration (s): 5.41 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.236081E+00 | loss scale: 8192.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.632 | TFLOPs: 71.48 | +[default7]: iteration 598/ 3814 | consumed samples: 306176 | consumed tokens: 627048448 | elapsed time per iteration (s): 5.40 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.219731E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.841 | TFLOPs: 71.63 | +[default7]: iteration 599/ 3814 | consumed samples: 306688 | consumed tokens: 628097024 | elapsed time per iteration (s): 5.37 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 6.228459E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.257 | TFLOPs: 71.95 | +[default7]: iteration 600/ 3814 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 5.40 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.231198E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.873 | TFLOPs: 71.66 | +[default7]: iteration 601/ 3814 | consumed samples: 307712 | consumed tokens: 630194176 | elapsed time per iteration (s): 5.41 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.240305E+00 | loss scale: 8192.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.660 | TFLOPs: 71.50 | +[default7]: iteration 602/ 3814 | consumed samples: 308224 | consumed tokens: 631242752 | elapsed time per iteration (s): 5.42 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.216270E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.437 | TFLOPs: 71.33 | +[default7]: iteration 603/ 3814 | consumed samples: 308736 | consumed tokens: 632291328 | elapsed time per iteration (s): 5.42 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.237883E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.419 | TFLOPs: 71.32 | +[default7]: iteration 604/ 3814 | consumed samples: 309248 | consumed tokens: 633339904 | elapsed time per iteration (s): 5.42 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.223955E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.534 | TFLOPs: 71.40 | +[default7]: iteration 605/ 3814 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 5.40 | learning rate: 1.679E-04 | global batch size: 512 | lm loss: 6.192775E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.769 | TFLOPs: 71.58 | +[default7]: iteration 606/ 3814 | consumed samples: 310272 | consumed tokens: 635437056 | elapsed time per iteration (s): 5.43 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.212539E+00 | loss scale: 8192.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.312 | TFLOPs: 71.24 | +[default7]: iteration 607/ 3814 | consumed samples: 310784 | consumed tokens: 636485632 | elapsed time per iteration (s): 5.42 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.173277E+00 | loss scale: 8192.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.528 | TFLOPs: 71.40 | +[default7]: iteration 608/ 3814 | consumed samples: 311296 | consumed tokens: 637534208 | elapsed time per iteration (s): 5.42 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.158289E+00 | loss scale: 8192.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.473 | TFLOPs: 71.36 | +[default7]: iteration 609/ 3814 | consumed samples: 311808 | consumed tokens: 638582784 | elapsed time per iteration (s): 5.41 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.212314E+00 | loss scale: 8192.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.649 | TFLOPs: 71.49 | +[default7]: iteration 610/ 3814 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 5.42 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.190392E+00 | loss scale: 8192.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.436 | TFLOPs: 71.33 | +[default7]: iteration 611/ 3814 | consumed samples: 312832 | consumed tokens: 640679936 | elapsed time per iteration (s): 5.42 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 6.189454E+00 | loss scale: 8192.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.466 | TFLOPs: 71.35 | +[default7]: iteration 612/ 3814 | consumed samples: 313344 | consumed tokens: 641728512 | elapsed time per iteration (s): 5.42 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 6.204041E+00 | loss scale: 8192.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.514 | TFLOPs: 71.39 | +[default7]: iteration 613/ 3814 | consumed samples: 313856 | consumed tokens: 642777088 | elapsed time per iteration (s): 5.42 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 6.181291E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.467 | TFLOPs: 71.35 | +[default7]: iteration 614/ 3814 | consumed samples: 314368 | consumed tokens: 643825664 | elapsed time per iteration (s): 5.41 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 6.211952E+00 | loss scale: 8192.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.572 | TFLOPs: 71.43 | +[default7]: iteration 615/ 3814 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 5.41 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 6.186111E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.680 | TFLOPs: 71.51 | +[default7]: iteration 616/ 3814 | consumed samples: 315392 | consumed tokens: 645922816 | elapsed time per iteration (s): 5.42 | learning rate: 1.677E-04 | global batch size: 512 | lm loss: 6.191184E+00 | loss scale: 8192.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.525 | TFLOPs: 71.40 | +[default7]: iteration 617/ 3814 | consumed samples: 315904 | consumed tokens: 646971392 | elapsed time per iteration (s): 5.42 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.186390E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.498 | TFLOPs: 71.38 | +[default7]: iteration 618/ 3814 | consumed samples: 316416 | consumed tokens: 648019968 | elapsed time per iteration (s): 5.41 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.172863E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.648 | TFLOPs: 71.49 | +[default7]: iteration 619/ 3814 | consumed samples: 316928 | consumed tokens: 649068544 | elapsed time per iteration (s): 5.42 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.171152E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.535 | TFLOPs: 71.40 | +[default7]: iteration 620/ 3814 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 5.43 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.144162E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.268 | TFLOPs: 71.20 | +[default7]: iteration 621/ 3814 | consumed samples: 317952 | consumed tokens: 651165696 | elapsed time per iteration (s): 5.41 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.155664E+00 | loss scale: 8192.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.595 | TFLOPs: 71.45 | +[default7]: iteration 622/ 3814 | consumed samples: 318464 | consumed tokens: 652214272 | elapsed time per iteration (s): 5.41 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 6.178432E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.632 | TFLOPs: 71.48 | +[default7]: iteration 623/ 3814 | consumed samples: 318976 | consumed tokens: 653262848 | elapsed time per iteration (s): 5.41 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 6.179622E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.679 | TFLOPs: 71.51 | +[default7]: iteration 624/ 3814 | consumed samples: 319488 | consumed tokens: 654311424 | elapsed time per iteration (s): 5.40 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 6.136059E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.801 | TFLOPs: 71.60 | +[default7]: iteration 625/ 3814 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 5.41 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 6.177284E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.691 | TFLOPs: 71.52 | +[default7]: iteration 626/ 3814 | consumed samples: 320512 | consumed tokens: 656408576 | elapsed time per iteration (s): 5.42 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 6.139664E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.511 | TFLOPs: 71.39 | +[default7]: iteration 627/ 3814 | consumed samples: 321024 | consumed tokens: 657457152 | elapsed time per iteration (s): 5.41 | learning rate: 1.675E-04 | global batch size: 512 | lm loss: 6.149980E+00 | loss scale: 8192.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.596 | TFLOPs: 71.45 | +[default7]: iteration 628/ 3814 | consumed samples: 321536 | consumed tokens: 658505728 | elapsed time per iteration (s): 5.41 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.124447E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.601 | TFLOPs: 71.45 | +[default7]: iteration 629/ 3814 | consumed samples: 322048 | consumed tokens: 659554304 | elapsed time per iteration (s): 5.42 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.139877E+00 | loss scale: 8192.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.535 | TFLOPs: 71.40 | +[default7]: iteration 630/ 3814 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 5.44 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.129098E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.178 | TFLOPs: 71.13 | +[default7]: iteration 631/ 3814 | consumed samples: 323072 | consumed tokens: 661651456 | elapsed time per iteration (s): 5.42 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.133514E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.402 | TFLOPs: 71.30 | +[default7]: iteration 632/ 3814 | consumed samples: 323584 | consumed tokens: 662700032 | elapsed time per iteration (s): 5.42 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.125999E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.509 | TFLOPs: 71.38 | +[default7]: iteration 633/ 3814 | consumed samples: 324096 | consumed tokens: 663748608 | elapsed time per iteration (s): 5.42 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 6.159780E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.485 | TFLOPs: 71.37 | +[default7]: iteration 634/ 3814 | consumed samples: 324608 | consumed tokens: 664797184 | elapsed time per iteration (s): 5.42 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 6.156163E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.471 | TFLOPs: 71.36 | +[default7]: iteration 635/ 3814 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 5.43 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 6.133920E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.340 | TFLOPs: 71.26 | +[default7]: iteration 636/ 3814 | consumed samples: 325632 | consumed tokens: 666894336 | elapsed time per iteration (s): 5.42 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 6.161877E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.438 | TFLOPs: 71.33 | +[default7]: iteration 637/ 3814 | consumed samples: 326144 | consumed tokens: 667942912 | elapsed time per iteration (s): 5.42 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 6.116105E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.448 | TFLOPs: 71.34 | +[default7]: iteration 638/ 3814 | consumed samples: 326656 | consumed tokens: 668991488 | elapsed time per iteration (s): 5.41 | learning rate: 1.673E-04 | global batch size: 512 | lm loss: 6.148498E+00 | loss scale: 8192.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.725 | TFLOPs: 71.55 | +[default7]: iteration 639/ 3814 | consumed samples: 327168 | consumed tokens: 670040064 | elapsed time per iteration (s): 5.44 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 6.132923E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.151 | TFLOPs: 71.11 | +[default7]: iteration 640/ 3814 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 5.40 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 6.109055E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.823 | TFLOPs: 71.62 | +[default7]: iteration 641/ 3814 | consumed samples: 328192 | consumed tokens: 672137216 | elapsed time per iteration (s): 5.41 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 6.116686E+00 | loss scale: 8192.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.685 | TFLOPs: 71.52 | +[default7]: iteration 642/ 3814 | consumed samples: 328704 | consumed tokens: 673185792 | elapsed time per iteration (s): 5.41 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 6.145401E+00 | loss scale: 8192.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.587 | TFLOPs: 71.44 | +[default7]: iteration 643/ 3814 | consumed samples: 329216 | consumed tokens: 674234368 | elapsed time per iteration (s): 5.41 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 6.141491E+00 | loss scale: 8192.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.616 | TFLOPs: 71.46 | +[default7]: iteration 644/ 3814 | consumed samples: 329728 | consumed tokens: 675282944 | elapsed time per iteration (s): 5.41 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 6.105099E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.637 | TFLOPs: 71.48 | +[default7]: iteration 645/ 3814 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 5.42 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 6.109425E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.404 | TFLOPs: 71.30 | +[default7]: iteration 646/ 3814 | consumed samples: 330752 | consumed tokens: 677380096 | elapsed time per iteration (s): 5.42 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 6.104946E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.448 | TFLOPs: 71.34 | +[default7]: iteration 647/ 3814 | consumed samples: 331264 | consumed tokens: 678428672 | elapsed time per iteration (s): 5.43 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 6.108871E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.350 | TFLOPs: 71.26 | +[default7]: iteration 648/ 3814 | consumed samples: 331776 | consumed tokens: 679477248 | elapsed time per iteration (s): 5.42 | learning rate: 1.671E-04 | global batch size: 512 | lm loss: 6.108392E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.498 | TFLOPs: 71.38 | +[default7]: iteration 649/ 3814 | consumed samples: 332288 | consumed tokens: 680525824 | elapsed time per iteration (s): 5.42 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 6.086980E+00 | loss scale: 8192.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.381 | TFLOPs: 71.29 | +[default7]: iteration 650/ 3814 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 5.44 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 6.110054E+00 | loss scale: 8192.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.090 | TFLOPs: 71.07 | +[default7]: iteration 651/ 3814 | consumed samples: 333312 | consumed tokens: 682622976 | elapsed time per iteration (s): 5.42 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 6.084722E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.462 | TFLOPs: 71.35 | +[default7]: iteration 652/ 3814 | consumed samples: 333824 | consumed tokens: 683671552 | elapsed time per iteration (s): 5.41 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 6.136062E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.700 | TFLOPs: 71.53 | +[default7]: iteration 653/ 3814 | consumed samples: 334336 | consumed tokens: 684720128 | elapsed time per iteration (s): 5.41 | learning rate: 1.670E-04 | global batch size: 512 | lm loss: 6.102092E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.699 | TFLOPs: 71.53 | +[default7]: iteration 654/ 3814 | consumed samples: 334848 | consumed tokens: 685768704 | elapsed time per iteration (s): 5.41 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 6.104562E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.552 | TFLOPs: 71.42 | +[default7]: iteration 655/ 3814 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 5.42 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 6.091110E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.514 | TFLOPs: 71.39 | +[default7]: iteration 656/ 3814 | consumed samples: 335872 | consumed tokens: 687865856 | elapsed time per iteration (s): 5.41 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 6.058205E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.691 | TFLOPs: 71.52 | +[default7]: iteration 657/ 3814 | consumed samples: 336384 | consumed tokens: 688914432 | elapsed time per iteration (s): 5.43 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 6.094417E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.334 | TFLOPs: 71.25 | +[default7]: iteration 658/ 3814 | consumed samples: 336896 | consumed tokens: 689963008 | elapsed time per iteration (s): 5.46 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 6.077289E+00 | loss scale: 8192.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.859 | TFLOPs: 70.89 | +[default7]: iteration 659/ 3814 | consumed samples: 337408 | consumed tokens: 691011584 | elapsed time per iteration (s): 5.41 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 6.057516E+00 | loss scale: 8192.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.575 | TFLOPs: 71.43 | +[default7]: iteration 660/ 3814 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 5.43 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 6.058960E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.216 | TFLOPs: 71.16 | +[default7]: iteration 661/ 3814 | consumed samples: 338432 | consumed tokens: 693108736 | elapsed time per iteration (s): 5.45 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 6.086177E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.968 | TFLOPs: 70.97 | +[default7]: iteration 662/ 3814 | consumed samples: 338944 | consumed tokens: 694157312 | elapsed time per iteration (s): 5.43 | learning rate: 1.668E-04 | global batch size: 512 | lm loss: 6.100446E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.274 | TFLOPs: 71.21 | +[default7]: iteration 663/ 3814 | consumed samples: 339456 | consumed tokens: 695205888 | elapsed time per iteration (s): 5.44 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 6.099791E+00 | loss scale: 8192.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.126 | TFLOPs: 71.09 | +[default7]: iteration 664/ 3814 | consumed samples: 339968 | consumed tokens: 696254464 | elapsed time per iteration (s): 5.45 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 6.059440E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.925 | TFLOPs: 70.94 | +[default7]: iteration 665/ 3814 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 5.45 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 6.082562E+00 | loss scale: 8192.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.986 | TFLOPs: 70.99 | +[default7]: iteration 666/ 3814 | consumed samples: 340992 | consumed tokens: 698351616 | elapsed time per iteration (s): 5.46 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 6.077115E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.694 | TFLOPs: 70.77 | +[default7]: iteration 667/ 3814 | consumed samples: 341504 | consumed tokens: 699400192 | elapsed time per iteration (s): 5.45 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 6.081102E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.957 | TFLOPs: 70.97 | +[default7]: iteration 668/ 3814 | consumed samples: 342016 | consumed tokens: 700448768 | elapsed time per iteration (s): 5.45 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 6.025935E+00 | loss scale: 8192.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.007 | TFLOPs: 71.00 | +[default7]: iteration 669/ 3814 | consumed samples: 342528 | consumed tokens: 701497344 | elapsed time per iteration (s): 5.46 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 6.043136E+00 | loss scale: 8192.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.820 | TFLOPs: 70.86 | +[default7]: iteration 670/ 3814 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 5.45 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 6.020181E+00 | loss scale: 8192.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.866 | TFLOPs: 70.90 | +[default7]: iteration 671/ 3814 | consumed samples: 343552 | consumed tokens: 703594496 | elapsed time per iteration (s): 5.42 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 6.053498E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.493 | TFLOPs: 71.37 | +[default7]: iteration 672/ 3814 | consumed samples: 344064 | consumed tokens: 704643072 | elapsed time per iteration (s): 5.43 | learning rate: 1.666E-04 | global batch size: 512 | lm loss: 6.045217E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.362 | TFLOPs: 71.27 | +[default7]: iteration 673/ 3814 | consumed samples: 344576 | consumed tokens: 705691648 | elapsed time per iteration (s): 5.43 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 6.056764E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.220 | TFLOPs: 71.16 | +[default7]: iteration 674/ 3814 | consumed samples: 345088 | consumed tokens: 706740224 | elapsed time per iteration (s): 5.42 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 6.023982E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.381 | TFLOPs: 71.29 | +[default7]: iteration 675/ 3814 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 5.43 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 6.030875E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.371 | TFLOPs: 71.28 | +[default7]: iteration 676/ 3814 | consumed samples: 346112 | consumed tokens: 708837376 | elapsed time per iteration (s): 5.44 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 6.050308E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.096 | TFLOPs: 71.07 | +[default7]: iteration 677/ 3814 | consumed samples: 346624 | consumed tokens: 709885952 | elapsed time per iteration (s): 5.40 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 6.041246E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.752 | TFLOPs: 71.57 | +[default7]: iteration 678/ 3814 | consumed samples: 347136 | consumed tokens: 710934528 | elapsed time per iteration (s): 5.42 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 6.023898E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.541 | TFLOPs: 71.41 | +[default7]: iteration 679/ 3814 | consumed samples: 347648 | consumed tokens: 711983104 | elapsed time per iteration (s): 5.42 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 6.012403E+00 | loss scale: 8192.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.434 | TFLOPs: 71.33 | +[default7]: iteration 680/ 3814 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 5.43 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 6.035626E+00 | loss scale: 8192.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.348 | TFLOPs: 71.26 | +[default7]: iteration 681/ 3814 | consumed samples: 348672 | consumed tokens: 714080256 | elapsed time per iteration (s): 5.41 | learning rate: 1.664E-04 | global batch size: 512 | lm loss: 6.030519E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.585 | TFLOPs: 71.44 | +[default7]: iteration 682/ 3814 | consumed samples: 349184 | consumed tokens: 715128832 | elapsed time per iteration (s): 5.41 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 6.037071E+00 | loss scale: 8192.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.639 | TFLOPs: 71.48 | +[default7]: iteration 683/ 3814 | consumed samples: 349696 | consumed tokens: 716177408 | elapsed time per iteration (s): 5.41 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 6.021775E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.666 | TFLOPs: 71.50 | +[default7]: iteration 684/ 3814 | consumed samples: 350208 | consumed tokens: 717225984 | elapsed time per iteration (s): 5.42 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 6.005135E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.548 | TFLOPs: 71.41 | +[default7]: iteration 685/ 3814 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 5.42 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 6.051075E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.518 | TFLOPs: 71.39 | +[default7]: iteration 686/ 3814 | consumed samples: 351232 | consumed tokens: 719323136 | elapsed time per iteration (s): 5.42 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 5.990885E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.379 | TFLOPs: 71.29 | +[default7]: iteration 687/ 3814 | consumed samples: 351744 | consumed tokens: 720371712 | elapsed time per iteration (s): 5.41 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 6.009043E+00 | loss scale: 8192.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.666 | TFLOPs: 71.50 | +[default7]: iteration 688/ 3814 | consumed samples: 352256 | consumed tokens: 721420288 | elapsed time per iteration (s): 5.43 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 6.013269E+00 | loss scale: 8192.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.350 | TFLOPs: 71.26 | +[default7]: iteration 689/ 3814 | consumed samples: 352768 | consumed tokens: 722468864 | elapsed time per iteration (s): 5.43 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 6.013196E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.369 | TFLOPs: 71.28 | +[default7]: iteration 690/ 3814 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 5.41 | learning rate: 1.662E-04 | global batch size: 512 | lm loss: 6.016838E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.624 | TFLOPs: 71.47 | +[default7]: iteration 691/ 3814 | consumed samples: 353792 | consumed tokens: 724566016 | elapsed time per iteration (s): 5.40 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 6.009407E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.808 | TFLOPs: 71.61 | +[default7]: iteration 692/ 3814 | consumed samples: 354304 | consumed tokens: 725614592 | elapsed time per iteration (s): 5.40 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 5.997999E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.756 | TFLOPs: 71.57 | +[default7]: iteration 693/ 3814 | consumed samples: 354816 | consumed tokens: 726663168 | elapsed time per iteration (s): 5.41 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 5.978921E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.625 | TFLOPs: 71.47 | +[default7]: iteration 694/ 3814 | consumed samples: 355328 | consumed tokens: 727711744 | elapsed time per iteration (s): 5.44 | learning rate: 1.661E-04 | global batch size: 512 | lm loss: 5.975759E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.060 | TFLOPs: 71.04 | +[default7]: iteration 695/ 3814 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 5.42 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 6.016912E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.398 | TFLOPs: 71.30 | +[default7]: iteration 696/ 3814 | consumed samples: 356352 | consumed tokens: 729808896 | elapsed time per iteration (s): 5.40 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 5.971983E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.791 | TFLOPs: 71.60 | +[default7]: iteration 697/ 3814 | consumed samples: 356864 | consumed tokens: 730857472 | elapsed time per iteration (s): 5.41 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 5.976766E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.553 | TFLOPs: 71.42 | +[default7]: iteration 698/ 3814 | consumed samples: 357376 | consumed tokens: 731906048 | elapsed time per iteration (s): 5.39 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 5.992822E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.917 | TFLOPs: 71.69 | +[default7]: iteration 699/ 3814 | consumed samples: 357888 | consumed tokens: 732954624 | elapsed time per iteration (s): 5.40 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 5.960050E+00 | loss scale: 8192.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.745 | TFLOPs: 71.56 | +[default7]: iteration 700/ 3814 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 5.42 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 5.975015E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.385 | TFLOPs: 71.29 | +[default7]: iteration 701/ 3814 | consumed samples: 358912 | consumed tokens: 735051776 | elapsed time per iteration (s): 5.46 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 5.966243E+00 | loss scale: 8192.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.738 | TFLOPs: 70.80 | +[default7]: iteration 702/ 3814 | consumed samples: 359424 | consumed tokens: 736100352 | elapsed time per iteration (s): 5.44 | learning rate: 1.659E-04 | global batch size: 512 | lm loss: 5.990894E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.059 | TFLOPs: 71.04 | +[default7]: iteration 703/ 3814 | consumed samples: 359936 | consumed tokens: 737148928 | elapsed time per iteration (s): 5.43 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 5.989687E+00 | loss scale: 8192.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.324 | TFLOPs: 71.24 | +[default7]: iteration 704/ 3814 | consumed samples: 360448 | consumed tokens: 738197504 | elapsed time per iteration (s): 5.43 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 5.977324E+00 | loss scale: 8192.0 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.309 | TFLOPs: 71.23 | +[default7]: iteration 705/ 3814 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 5.41 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 5.962548E+00 | loss scale: 8192.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.671 | TFLOPs: 71.51 | +[default7]: iteration 706/ 3814 | consumed samples: 361472 | consumed tokens: 740294656 | elapsed time per iteration (s): 5.41 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 5.987010E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.634 | TFLOPs: 71.48 | +[default7]: iteration 707/ 3814 | consumed samples: 361984 | consumed tokens: 741343232 | elapsed time per iteration (s): 5.41 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 5.981858E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.552 | TFLOPs: 71.42 | +[default7]: iteration 708/ 3814 | consumed samples: 362496 | consumed tokens: 742391808 | elapsed time per iteration (s): 5.42 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 5.979402E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.429 | TFLOPs: 71.32 | +[default7]: iteration 709/ 3814 | consumed samples: 363008 | consumed tokens: 743440384 | elapsed time per iteration (s): 5.43 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 5.974354E+00 | loss scale: 8192.0 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.370 | TFLOPs: 71.28 | +[default7]: iteration 710/ 3814 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 5.44 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 5.973994E+00 | loss scale: 8192.0 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.143 | TFLOPs: 71.11 | +[default7]: iteration 711/ 3814 | consumed samples: 364032 | consumed tokens: 745537536 | elapsed time per iteration (s): 5.43 | learning rate: 1.657E-04 | global batch size: 512 | lm loss: 5.964932E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.319 | TFLOPs: 71.24 | +[default7]: iteration 712/ 3814 | consumed samples: 364544 | consumed tokens: 746586112 | elapsed time per iteration (s): 5.42 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 5.957611E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.478 | TFLOPs: 71.36 | +[default7]: iteration 713/ 3814 | consumed samples: 365056 | consumed tokens: 747634688 | elapsed time per iteration (s): 5.40 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 5.951418E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.773 | TFLOPs: 71.58 | +[default7]: iteration 714/ 3814 | consumed samples: 365568 | consumed tokens: 748683264 | elapsed time per iteration (s): 5.43 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 5.979712E+00 | loss scale: 8192.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 715/ 3814 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 5.42 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 5.941887E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.422 | TFLOPs: 71.32 | +[default7]: iteration 716/ 3814 | consumed samples: 366592 | consumed tokens: 750780416 | elapsed time per iteration (s): 5.43 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 5.959307E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.355 | TFLOPs: 71.27 | +[default7]: iteration 717/ 3814 | consumed samples: 367104 | consumed tokens: 751828992 | elapsed time per iteration (s): 5.41 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 5.934158E+00 | loss scale: 8192.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.594 | TFLOPs: 71.45 | +[default7]: iteration 718/ 3814 | consumed samples: 367616 | consumed tokens: 752877568 | elapsed time per iteration (s): 5.42 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 5.952499E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.531 | TFLOPs: 71.40 | +[default7]: iteration 719/ 3814 | consumed samples: 368128 | consumed tokens: 753926144 | elapsed time per iteration (s): 5.42 | learning rate: 1.655E-04 | global batch size: 512 | lm loss: 5.956738E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.490 | TFLOPs: 71.37 | +[default7]: iteration 720/ 3814 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 5.42 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 5.958854E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.400 | TFLOPs: 71.30 | +[default7]: iteration 721/ 3814 | consumed samples: 369152 | consumed tokens: 756023296 | elapsed time per iteration (s): 5.44 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 5.953454E+00 | loss scale: 8192.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.189 | TFLOPs: 71.14 | +[default7]: iteration 722/ 3814 | consumed samples: 369664 | consumed tokens: 757071872 | elapsed time per iteration (s): 5.43 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 5.956723E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.310 | TFLOPs: 71.23 | +[default7]: iteration 723/ 3814 | consumed samples: 370176 | consumed tokens: 758120448 | elapsed time per iteration (s): 5.43 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 5.944064E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.329 | TFLOPs: 71.25 | +[default7]: iteration 724/ 3814 | consumed samples: 370688 | consumed tokens: 759169024 | elapsed time per iteration (s): 5.44 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 5.908057E+00 | loss scale: 8192.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.136 | TFLOPs: 71.10 | +[default7]: iteration 725/ 3814 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 5.42 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 5.947763E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.451 | TFLOPs: 71.34 | +[default7]: iteration 726/ 3814 | consumed samples: 371712 | consumed tokens: 761266176 | elapsed time per iteration (s): 5.44 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 5.949288E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.158 | TFLOPs: 71.12 | +[default7]: iteration 727/ 3814 | consumed samples: 372224 | consumed tokens: 762314752 | elapsed time per iteration (s): 5.42 | learning rate: 1.653E-04 | global batch size: 512 | lm loss: 5.930746E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.428 | TFLOPs: 71.32 | +[default7]: iteration 728/ 3814 | consumed samples: 372736 | consumed tokens: 763363328 | elapsed time per iteration (s): 5.43 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 5.923387E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.293 | TFLOPs: 71.22 | +[default7]: iteration 729/ 3814 | consumed samples: 373248 | consumed tokens: 764411904 | elapsed time per iteration (s): 5.44 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 5.909809E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 730/ 3814 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 5.41 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 5.942175E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.572 | TFLOPs: 71.43 | +[default7]: iteration 731/ 3814 | consumed samples: 374272 | consumed tokens: 766509056 | elapsed time per iteration (s): 5.41 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 5.914283E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.558 | TFLOPs: 71.42 | +[default7]: iteration 732/ 3814 | consumed samples: 374784 | consumed tokens: 767557632 | elapsed time per iteration (s): 5.43 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 5.941054E+00 | loss scale: 8192.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.329 | TFLOPs: 71.25 | +[default7]: iteration 733/ 3814 | consumed samples: 375296 | consumed tokens: 768606208 | elapsed time per iteration (s): 5.43 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 5.935675E+00 | loss scale: 8192.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.317 | TFLOPs: 71.24 | +[default7]: iteration 734/ 3814 | consumed samples: 375808 | consumed tokens: 769654784 | elapsed time per iteration (s): 5.41 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 5.903219E+00 | loss scale: 8192.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.671 | TFLOPs: 71.51 | +[default7]: iteration 735/ 3814 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 5.45 | learning rate: 1.651E-04 | global batch size: 512 | lm loss: 5.898514E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.980 | TFLOPs: 70.98 | +[default7]: iteration 736/ 3814 | consumed samples: 376832 | consumed tokens: 771751936 | elapsed time per iteration (s): 5.43 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 5.940041E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.220 | TFLOPs: 71.17 | +[default7]: iteration 737/ 3814 | consumed samples: 377344 | consumed tokens: 772800512 | elapsed time per iteration (s): 5.40 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 5.902273E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.823 | TFLOPs: 71.62 | +[default7]: iteration 738/ 3814 | consumed samples: 377856 | consumed tokens: 773849088 | elapsed time per iteration (s): 5.42 | learning rate: 1.650E-04 | global batch size: 512 | lm loss: 5.927811E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.462 | TFLOPs: 71.35 | +[default7]: iteration 739/ 3814 | consumed samples: 378368 | consumed tokens: 774897664 | elapsed time per iteration (s): 5.43 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 5.905412E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.250 | TFLOPs: 71.19 | +[default7]: iteration 740/ 3814 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 5.44 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 5.914158E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.189 | TFLOPs: 71.14 | +[default7]: iteration 741/ 3814 | consumed samples: 379392 | consumed tokens: 776994816 | elapsed time per iteration (s): 5.43 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 5.898336E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.319 | TFLOPs: 71.24 | +[default7]: iteration 742/ 3814 | consumed samples: 379904 | consumed tokens: 778043392 | elapsed time per iteration (s): 5.43 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 5.886751E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.368 | TFLOPs: 71.28 | +[default7]: iteration 743/ 3814 | consumed samples: 380416 | consumed tokens: 779091968 | elapsed time per iteration (s): 5.41 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 5.883355E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.594 | TFLOPs: 71.45 | +[default7]: iteration 744/ 3814 | consumed samples: 380928 | consumed tokens: 780140544 | elapsed time per iteration (s): 5.41 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 5.893945E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.626 | TFLOPs: 71.47 | +[default7]: iteration 745/ 3814 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 5.42 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 5.868671E+00 | loss scale: 8192.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.468 | TFLOPs: 71.35 | +[default7]: iteration 746/ 3814 | consumed samples: 381952 | consumed tokens: 782237696 | elapsed time per iteration (s): 5.42 | learning rate: 1.648E-04 | global batch size: 512 | lm loss: 5.910399E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.539 | TFLOPs: 71.41 | +[default7]: iteration 747/ 3814 | consumed samples: 382464 | consumed tokens: 783286272 | elapsed time per iteration (s): 5.42 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 5.913574E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.493 | TFLOPs: 71.37 | +[default7]: iteration 748/ 3814 | consumed samples: 382976 | consumed tokens: 784334848 | elapsed time per iteration (s): 5.43 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 5.876530E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.371 | TFLOPs: 71.28 | +[default7]: iteration 749/ 3814 | consumed samples: 383488 | consumed tokens: 785383424 | elapsed time per iteration (s): 5.41 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 5.916028E+00 | loss scale: 8192.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.640 | TFLOPs: 71.48 | +[default0]:saving checkpoint at iteration 750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 12:27:41,684] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step750 is begin to save! +[default0]:[2023-02-16 12:27:41,688] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_00-model_states.pt... +[default7]: iteration 750/ 3814 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 5.43 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 5.891957E+00 | loss scale: 8192.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.375 | TFLOPs: 71.28 | +[default1]:[2023-02-16 12:27:41,688] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:41,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:41,853] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:41,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:41,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:41,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:41,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:41,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:41,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:41,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:41,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:41,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:41,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,027] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,026] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,114] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,176] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,174] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,233] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,283] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,392] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,403] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,467] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,537] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,592] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,680] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,791] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,814] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:42,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:42,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:42,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:42,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,927] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,928] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,014] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:42,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:42,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,040] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,137] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,252] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,237] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,317] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,305] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,432] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,474] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,485] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,531] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 12:27:43,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,647] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 12:27:43,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 12:27:43,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 12:27:43,728] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 12:27:43,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 12:27:43,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt. +[default1]:[2023-02-16 12:27:43,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 12:27:43,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 12:27:43,782] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 12:27:43,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:27:43,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:27:43,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:27:44,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,273] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,305] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,351] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,343] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,343] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,375] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,391] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,352] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,316] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,344] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,408] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,398] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,339] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,435] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,435] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,398] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,355] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,392] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,450] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,374] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,470] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,471] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,390] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,469] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,459] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,481] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,434] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,475] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,389] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,430] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,468] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,426] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,460] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,424] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,424] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,482] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,515] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,519] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,452] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,461] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,473] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,513] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,476] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,560] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,536] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,542] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,573] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,603] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,585] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,575] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,511] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,544] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,530] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 12:27:44,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:27:44,546] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:27:44,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,541] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,609] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 12:27:44,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:27:44,570] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:27:44,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,606] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 12:27:44,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:27:44,623] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:27:44,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 12:27:44,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:27:44,585] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:27:44,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,586] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 12:27:44,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:27:44,685] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:27:44,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 12:27:44,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:27:44,661] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:27:44,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 12:27:44,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:27:44,780] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:27:44,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 12:27:44,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:27:44,770] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:27:44,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]: successfully saved checkpoint at iteration 750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 3097.29 +[default7]: iteration 751/ 3814 | consumed samples: 384512 | consumed tokens: 787480576 | elapsed time per iteration (s): 8.51 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 5.902260E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 60.163 | TFLOPs: 45.44 | +[default7]: iteration 752/ 3814 | consumed samples: 385024 | consumed tokens: 788529152 | elapsed time per iteration (s): 5.41 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 5.917446E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.649 | TFLOPs: 71.49 | +[default7]: iteration 753/ 3814 | consumed samples: 385536 | consumed tokens: 789577728 | elapsed time per iteration (s): 5.43 | learning rate: 1.646E-04 | global batch size: 512 | lm loss: 5.876194E+00 | loss scale: 8192.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.341 | TFLOPs: 71.26 | +[default7]: iteration 754/ 3814 | consumed samples: 386048 | consumed tokens: 790626304 | elapsed time per iteration (s): 5.39 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 5.872040E+00 | loss scale: 8192.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.917 | TFLOPs: 71.69 | +[default7]: iteration 755/ 3814 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 5.42 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 5.896158E+00 | loss scale: 8192.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.540 | TFLOPs: 71.41 | +[default7]: iteration 756/ 3814 | consumed samples: 387072 | consumed tokens: 792723456 | elapsed time per iteration (s): 5.42 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 5.896800E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.404 | TFLOPs: 71.30 | +[default7]: iteration 757/ 3814 | consumed samples: 387584 | consumed tokens: 793772032 | elapsed time per iteration (s): 5.41 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 5.900323E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.725 | TFLOPs: 71.55 | +[default7]: iteration 758/ 3814 | consumed samples: 388096 | consumed tokens: 794820608 | elapsed time per iteration (s): 5.42 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 5.872563E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.539 | TFLOPs: 71.41 | +[default7]: iteration 759/ 3814 | consumed samples: 388608 | consumed tokens: 795869184 | elapsed time per iteration (s): 5.41 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 5.866800E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.721 | TFLOPs: 71.54 | +[default7]: iteration 760/ 3814 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 5.42 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 5.850535E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.484 | TFLOPs: 71.36 | +[default7]: iteration 761/ 3814 | consumed samples: 389632 | consumed tokens: 797966336 | elapsed time per iteration (s): 5.43 | learning rate: 1.644E-04 | global batch size: 512 | lm loss: 5.855239E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 762/ 3814 | consumed samples: 390144 | consumed tokens: 799014912 | elapsed time per iteration (s): 5.41 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 5.852764E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.568 | TFLOPs: 71.43 | +[default7]: iteration 763/ 3814 | consumed samples: 390656 | consumed tokens: 800063488 | elapsed time per iteration (s): 5.40 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 5.853951E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.872 | TFLOPs: 71.66 | +[default7]: iteration 764/ 3814 | consumed samples: 391168 | consumed tokens: 801112064 | elapsed time per iteration (s): 5.41 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 5.861470E+00 | loss scale: 8192.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.709 | TFLOPs: 71.53 | +[default7]: iteration 765/ 3814 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 5.44 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 5.870966E+00 | loss scale: 8192.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.119 | TFLOPs: 71.09 | +[default7]: iteration 766/ 3814 | consumed samples: 392192 | consumed tokens: 803209216 | elapsed time per iteration (s): 5.44 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 5.852050E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.191 | TFLOPs: 71.14 | +[default7]: iteration 767/ 3814 | consumed samples: 392704 | consumed tokens: 804257792 | elapsed time per iteration (s): 5.42 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 5.894067E+00 | loss scale: 8192.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.506 | TFLOPs: 71.38 | +[default7]: iteration 768/ 3814 | consumed samples: 393216 | consumed tokens: 805306368 | elapsed time per iteration (s): 5.42 | learning rate: 1.642E-04 | global batch size: 512 | lm loss: 5.856753E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.497 | TFLOPs: 71.37 | +[default7]: iteration 769/ 3814 | consumed samples: 393728 | consumed tokens: 806354944 | elapsed time per iteration (s): 5.41 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 5.835691E+00 | loss scale: 8192.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.725 | TFLOPs: 71.55 | +[default7]: iteration 770/ 3814 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 5.41 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 5.838207E+00 | loss scale: 8192.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.605 | TFLOPs: 71.46 | +[default7]: iteration 771/ 3814 | consumed samples: 394752 | consumed tokens: 808452096 | elapsed time per iteration (s): 5.41 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 5.824872E+00 | loss scale: 8192.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.568 | TFLOPs: 71.43 | +[default7]: iteration 772/ 3814 | consumed samples: 395264 | consumed tokens: 809500672 | elapsed time per iteration (s): 5.42 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 5.837815E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.398 | TFLOPs: 71.30 | +[default7]: iteration 773/ 3814 | consumed samples: 395776 | consumed tokens: 810549248 | elapsed time per iteration (s): 5.42 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 5.830763E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.440 | TFLOPs: 71.33 | +[default7]: iteration 774/ 3814 | consumed samples: 396288 | consumed tokens: 811597824 | elapsed time per iteration (s): 5.42 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 5.852273E+00 | loss scale: 8192.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.545 | TFLOPs: 71.41 | +[default7]: iteration 775/ 3814 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 5.45 | learning rate: 1.640E-04 | global batch size: 512 | lm loss: 5.847666E+00 | loss scale: 8192.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 776/ 3814 | consumed samples: 397312 | consumed tokens: 813694976 | elapsed time per iteration (s): 5.42 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 5.846380E+00 | loss scale: 8192.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.485 | TFLOPs: 71.37 | +[default7]: iteration 777/ 3814 | consumed samples: 397824 | consumed tokens: 814743552 | elapsed time per iteration (s): 5.46 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 5.875813E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.822 | TFLOPs: 70.86 | +[default7]: iteration 778/ 3814 | consumed samples: 398336 | consumed tokens: 815792128 | elapsed time per iteration (s): 5.55 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 5.824536E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 92.195 | TFLOPs: 69.64 | +[default7]: iteration 779/ 3814 | consumed samples: 398848 | consumed tokens: 816840704 | elapsed time per iteration (s): 5.44 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 5.832495E+00 | loss scale: 8192.0 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.141 | TFLOPs: 71.11 | +[default7]: iteration 780/ 3814 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 5.43 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 5.830336E+00 | loss scale: 8192.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.259 | TFLOPs: 71.19 | +[default7]: iteration 781/ 3814 | consumed samples: 399872 | consumed tokens: 818937856 | elapsed time per iteration (s): 5.41 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 5.865227E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.580 | TFLOPs: 71.44 | +[default7]: iteration 782/ 3814 | consumed samples: 400384 | consumed tokens: 819986432 | elapsed time per iteration (s): 5.40 | learning rate: 1.638E-04 | global batch size: 512 | lm loss: 5.818711E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.784 | TFLOPs: 71.59 | +[default7]: iteration 783/ 3814 | consumed samples: 400896 | consumed tokens: 821035008 | elapsed time per iteration (s): 5.42 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 5.854019E+00 | loss scale: 8192.0 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.510 | TFLOPs: 71.38 | +[default7]: iteration 784/ 3814 | consumed samples: 401408 | consumed tokens: 822083584 | elapsed time per iteration (s): 5.41 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 5.806298E+00 | loss scale: 8192.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.653 | TFLOPs: 71.49 | +[default7]: iteration 785/ 3814 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 5.42 | learning rate: 1.637E-04 | global batch size: 512 | lm loss: 5.818822E+00 | loss scale: 8192.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.512 | TFLOPs: 71.39 | +[default7]: iteration 786/ 3814 | consumed samples: 402432 | consumed tokens: 824180736 | elapsed time per iteration (s): 5.44 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 5.835362E+00 | loss scale: 8192.0 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.145 | TFLOPs: 71.11 | +[default7]: iteration 787/ 3814 | consumed samples: 402944 | consumed tokens: 825229312 | elapsed time per iteration (s): 5.45 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 5.824984E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.868 | TFLOPs: 70.90 | +[default7]: iteration 788/ 3814 | consumed samples: 403456 | consumed tokens: 826277888 | elapsed time per iteration (s): 5.40 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 5.821757E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.740 | TFLOPs: 71.56 | +[default7]: iteration 789/ 3814 | consumed samples: 403968 | consumed tokens: 827326464 | elapsed time per iteration (s): 5.40 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 5.817170E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.772 | TFLOPs: 71.58 | +[default7]: iteration 790/ 3814 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 5.40 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 5.807108E+00 | loss scale: 8192.0 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.834 | TFLOPs: 71.63 | +[default7]: iteration 791/ 3814 | consumed samples: 404992 | consumed tokens: 829423616 | elapsed time per iteration (s): 5.41 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 5.802562E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.683 | TFLOPs: 71.51 | +[default7]: iteration 792/ 3814 | consumed samples: 405504 | consumed tokens: 830472192 | elapsed time per iteration (s): 5.40 | learning rate: 1.635E-04 | global batch size: 512 | lm loss: 5.820928E+00 | loss scale: 8192.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.761 | TFLOPs: 71.57 | +[default7]: iteration 793/ 3814 | consumed samples: 406016 | consumed tokens: 831520768 | elapsed time per iteration (s): 5.44 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 5.810729E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.050 | TFLOPs: 71.04 | +[default7]: iteration 794/ 3814 | consumed samples: 406528 | consumed tokens: 832569344 | elapsed time per iteration (s): 5.40 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 5.784995E+00 | loss scale: 8192.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.853 | TFLOPs: 71.64 | +[default7]: iteration 795/ 3814 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 5.40 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 5.789858E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.761 | TFLOPs: 71.57 | +[default7]: iteration 796/ 3814 | consumed samples: 407552 | consumed tokens: 834666496 | elapsed time per iteration (s): 5.42 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 5.800179E+00 | loss scale: 8192.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.506 | TFLOPs: 71.38 | +[default7]: iteration 797/ 3814 | consumed samples: 408064 | consumed tokens: 835715072 | elapsed time per iteration (s): 5.40 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 5.813584E+00 | loss scale: 8192.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.899 | TFLOPs: 71.68 | +[default7]: iteration 798/ 3814 | consumed samples: 408576 | consumed tokens: 836763648 | elapsed time per iteration (s): 5.43 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 5.760669E+00 | loss scale: 8192.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.344 | TFLOPs: 71.26 | +[default7]: iteration 799/ 3814 | consumed samples: 409088 | consumed tokens: 837812224 | elapsed time per iteration (s): 5.41 | learning rate: 1.633E-04 | global batch size: 512 | lm loss: 5.797873E+00 | loss scale: 8192.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.651 | TFLOPs: 71.49 | +[default7]: iteration 800/ 3814 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 5.41 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 5.810727E+00 | loss scale: 8192.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.720 | TFLOPs: 71.54 | +[default7]: iteration 801/ 3814 | consumed samples: 410112 | consumed tokens: 839909376 | elapsed time per iteration (s): 5.41 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 5.788215E+00 | loss scale: 8192.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.629 | TFLOPs: 71.47 | +[default7]: iteration 802/ 3814 | consumed samples: 410624 | consumed tokens: 840957952 | elapsed time per iteration (s): 5.41 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 5.774993E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.661 | TFLOPs: 71.50 | +[default7]: iteration 803/ 3814 | consumed samples: 411136 | consumed tokens: 842006528 | elapsed time per iteration (s): 5.42 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 5.800402E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.493 | TFLOPs: 71.37 | +[default7]: iteration 804/ 3814 | consumed samples: 411648 | consumed tokens: 843055104 | elapsed time per iteration (s): 5.41 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 5.801908E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.635 | TFLOPs: 71.48 | +[default7]: iteration 805/ 3814 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 5.41 | learning rate: 1.631E-04 | global batch size: 512 | lm loss: 5.789254E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.671 | TFLOPs: 71.51 | +[default7]: iteration 806/ 3814 | consumed samples: 412672 | consumed tokens: 845152256 | elapsed time per iteration (s): 5.42 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 5.789211E+00 | loss scale: 8192.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.472 | TFLOPs: 71.36 | +[default7]: iteration 807/ 3814 | consumed samples: 413184 | consumed tokens: 846200832 | elapsed time per iteration (s): 5.40 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 5.794410E+00 | loss scale: 8192.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.788 | TFLOPs: 71.59 | +[default7]: iteration 808/ 3814 | consumed samples: 413696 | consumed tokens: 847249408 | elapsed time per iteration (s): 5.41 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 5.757307E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.718 | TFLOPs: 71.54 | +[default7]: iteration 809/ 3814 | consumed samples: 414208 | consumed tokens: 848297984 | elapsed time per iteration (s): 5.39 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 5.783245E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.926 | TFLOPs: 71.70 | +[default7]: iteration 810/ 3814 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 5.44 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 5.744136E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.148 | TFLOPs: 71.11 | +[default7]: iteration 811/ 3814 | consumed samples: 415232 | consumed tokens: 850395136 | elapsed time per iteration (s): 5.43 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 5.742691E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.369 | TFLOPs: 71.28 | +[default7]: iteration 812/ 3814 | consumed samples: 415744 | consumed tokens: 851443712 | elapsed time per iteration (s): 5.43 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 5.761222E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 813/ 3814 | consumed samples: 416256 | consumed tokens: 852492288 | elapsed time per iteration (s): 5.41 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 5.741351E+00 | loss scale: 8192.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.722 | TFLOPs: 71.54 | +[default7]: iteration 814/ 3814 | consumed samples: 416768 | consumed tokens: 853540864 | elapsed time per iteration (s): 5.43 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 5.792952E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 815/ 3814 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 5.46 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 5.785017E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.762 | TFLOPs: 70.82 | +[default7]: iteration 816/ 3814 | consumed samples: 417792 | consumed tokens: 855638016 | elapsed time per iteration (s): 5.45 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 5.787508E+00 | loss scale: 8192.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.942 | TFLOPs: 70.96 | +[default7]: iteration 817/ 3814 | consumed samples: 418304 | consumed tokens: 856686592 | elapsed time per iteration (s): 5.45 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 5.780310E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.964 | TFLOPs: 70.97 | +[default7]: iteration 818/ 3814 | consumed samples: 418816 | consumed tokens: 857735168 | elapsed time per iteration (s): 5.43 | learning rate: 1.627E-04 | global batch size: 512 | lm loss: 5.785414E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 819/ 3814 | consumed samples: 419328 | consumed tokens: 858783744 | elapsed time per iteration (s): 5.41 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 5.757354E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.633 | TFLOPs: 71.48 | +[default7]: iteration 820/ 3814 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 5.43 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 5.742674E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.315 | TFLOPs: 71.24 | +[default7]: iteration 821/ 3814 | consumed samples: 420352 | consumed tokens: 860880896 | elapsed time per iteration (s): 5.43 | learning rate: 1.626E-04 | global batch size: 512 | lm loss: 5.763113E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.310 | TFLOPs: 71.23 | +[default7]: iteration 822/ 3814 | consumed samples: 420864 | consumed tokens: 861929472 | elapsed time per iteration (s): 5.41 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 5.754019E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.640 | TFLOPs: 71.48 | +[default7]: iteration 823/ 3814 | consumed samples: 421376 | consumed tokens: 862978048 | elapsed time per iteration (s): 5.43 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 5.763148E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.255 | TFLOPs: 71.19 | +[default7]: iteration 824/ 3814 | consumed samples: 421888 | consumed tokens: 864026624 | elapsed time per iteration (s): 5.43 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 5.749018E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 825/ 3814 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 5.39 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 5.757254E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.972 | TFLOPs: 71.73 | +[default7]: iteration 826/ 3814 | consumed samples: 422912 | consumed tokens: 866123776 | elapsed time per iteration (s): 5.39 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 5.750185E+00 | loss scale: 8192.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.947 | TFLOPs: 71.71 | +[default7]: iteration 827/ 3814 | consumed samples: 423424 | consumed tokens: 867172352 | elapsed time per iteration (s): 5.42 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 5.763986E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.495 | TFLOPs: 71.37 | +[default7]: iteration 828/ 3814 | consumed samples: 423936 | consumed tokens: 868220928 | elapsed time per iteration (s): 5.43 | learning rate: 1.624E-04 | global batch size: 512 | lm loss: 5.759533E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.329 | TFLOPs: 71.25 | +[default7]: iteration 829/ 3814 | consumed samples: 424448 | consumed tokens: 869269504 | elapsed time per iteration (s): 5.42 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 5.735839E+00 | loss scale: 8192.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.380 | TFLOPs: 71.29 | +[default7]: iteration 830/ 3814 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 5.43 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 5.736191E+00 | loss scale: 8192.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.375 | TFLOPs: 71.28 | +[default7]: iteration 831/ 3814 | consumed samples: 425472 | consumed tokens: 871366656 | elapsed time per iteration (s): 5.41 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 5.728599E+00 | loss scale: 8192.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.638 | TFLOPs: 71.48 | +[default7]: iteration 832/ 3814 | consumed samples: 425984 | consumed tokens: 872415232 | elapsed time per iteration (s): 5.42 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 5.739847E+00 | loss scale: 8192.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.541 | TFLOPs: 71.41 | +[default7]: iteration 833/ 3814 | consumed samples: 426496 | consumed tokens: 873463808 | elapsed time per iteration (s): 5.41 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 5.729636E+00 | loss scale: 8192.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.565 | TFLOPs: 71.43 | +[default7]: iteration 834/ 3814 | consumed samples: 427008 | consumed tokens: 874512384 | elapsed time per iteration (s): 5.42 | learning rate: 1.622E-04 | global batch size: 512 | lm loss: 5.752030E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.534 | TFLOPs: 71.40 | +[default7]: iteration 835/ 3814 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 5.42 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 5.701564E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.415 | TFLOPs: 71.31 | +[default7]: iteration 836/ 3814 | consumed samples: 428032 | consumed tokens: 876609536 | elapsed time per iteration (s): 5.42 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 5.732773E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.427 | TFLOPs: 71.32 | +[default7]: iteration 837/ 3814 | consumed samples: 428544 | consumed tokens: 877658112 | elapsed time per iteration (s): 5.44 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 5.721278E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.141 | TFLOPs: 71.11 | +[default7]: iteration 838/ 3814 | consumed samples: 429056 | consumed tokens: 878706688 | elapsed time per iteration (s): 5.42 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 5.724745E+00 | loss scale: 8192.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.511 | TFLOPs: 71.38 | +[default7]: iteration 839/ 3814 | consumed samples: 429568 | consumed tokens: 879755264 | elapsed time per iteration (s): 5.42 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 5.733029E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.447 | TFLOPs: 71.34 | +[default7]: iteration 840/ 3814 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 5.42 | learning rate: 1.620E-04 | global batch size: 512 | lm loss: 5.719972E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.492 | TFLOPs: 71.37 | +[default7]: iteration 841/ 3814 | consumed samples: 430592 | consumed tokens: 881852416 | elapsed time per iteration (s): 5.42 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 5.748042E+00 | loss scale: 8192.0 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.493 | TFLOPs: 71.37 | +[default7]: iteration 842/ 3814 | consumed samples: 431104 | consumed tokens: 882900992 | elapsed time per iteration (s): 5.42 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 5.748866E+00 | loss scale: 8192.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.468 | TFLOPs: 71.35 | +[default7]: iteration 843/ 3814 | consumed samples: 431616 | consumed tokens: 883949568 | elapsed time per iteration (s): 5.42 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 5.730688E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.488 | TFLOPs: 71.37 | +[default7]: iteration 844/ 3814 | consumed samples: 432128 | consumed tokens: 884998144 | elapsed time per iteration (s): 5.45 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 5.721995E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.885 | TFLOPs: 70.91 | +[default7]: iteration 845/ 3814 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 5.46 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 5.746090E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.769 | TFLOPs: 70.82 | +[default7]: iteration 846/ 3814 | consumed samples: 433152 | consumed tokens: 887095296 | elapsed time per iteration (s): 5.44 | learning rate: 1.618E-04 | global batch size: 512 | lm loss: 5.724790E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.174 | TFLOPs: 71.13 | +[default7]: iteration 847/ 3814 | consumed samples: 433664 | consumed tokens: 888143872 | elapsed time per iteration (s): 5.43 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 5.709589E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.301 | TFLOPs: 71.23 | +[default7]: iteration 848/ 3814 | consumed samples: 434176 | consumed tokens: 889192448 | elapsed time per iteration (s): 5.42 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 5.710266E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.464 | TFLOPs: 71.35 | +[default7]: iteration 849/ 3814 | consumed samples: 434688 | consumed tokens: 890241024 | elapsed time per iteration (s): 5.44 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 5.707035E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.041 | TFLOPs: 71.03 | +[default7]: iteration 850/ 3814 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 5.44 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 5.699962E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.180 | TFLOPs: 71.14 | +[default7]: iteration 851/ 3814 | consumed samples: 435712 | consumed tokens: 892338176 | elapsed time per iteration (s): 5.42 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 5.716024E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.511 | TFLOPs: 71.39 | +[default7]: iteration 852/ 3814 | consumed samples: 436224 | consumed tokens: 893386752 | elapsed time per iteration (s): 5.43 | learning rate: 1.616E-04 | global batch size: 512 | lm loss: 5.705326E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.255 | TFLOPs: 71.19 | +[default7]: iteration 853/ 3814 | consumed samples: 436736 | consumed tokens: 894435328 | elapsed time per iteration (s): 5.43 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 5.696209E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.213 | TFLOPs: 71.16 | +[default7]: iteration 854/ 3814 | consumed samples: 437248 | consumed tokens: 895483904 | elapsed time per iteration (s): 5.43 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 5.689899E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.252 | TFLOPs: 71.19 | +[default7]: iteration 855/ 3814 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 5.44 | learning rate: 1.615E-04 | global batch size: 512 | lm loss: 5.688207E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.140 | TFLOPs: 71.10 | +[default7]: iteration 856/ 3814 | consumed samples: 438272 | consumed tokens: 897581056 | elapsed time per iteration (s): 5.44 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 5.714338E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.100 | TFLOPs: 71.07 | +[default7]: iteration 857/ 3814 | consumed samples: 438784 | consumed tokens: 898629632 | elapsed time per iteration (s): 5.46 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 5.681346E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.827 | TFLOPs: 70.87 | +[default7]: iteration 858/ 3814 | consumed samples: 439296 | consumed tokens: 899678208 | elapsed time per iteration (s): 5.42 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 5.684147E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.395 | TFLOPs: 71.30 | +[default7]: iteration 859/ 3814 | consumed samples: 439808 | consumed tokens: 900726784 | elapsed time per iteration (s): 5.44 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 5.704052E+00 | loss scale: 8192.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.064 | TFLOPs: 71.05 | +[default7]: iteration 860/ 3814 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 5.44 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 5.693681E+00 | loss scale: 8192.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 861/ 3814 | consumed samples: 440832 | consumed tokens: 902823936 | elapsed time per iteration (s): 5.42 | learning rate: 1.613E-04 | global batch size: 512 | lm loss: 5.684240E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.436 | TFLOPs: 71.33 | +[default7]: iteration 862/ 3814 | consumed samples: 441344 | consumed tokens: 903872512 | elapsed time per iteration (s): 5.43 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 5.668405E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.229 | TFLOPs: 71.17 | +[default7]: iteration 863/ 3814 | consumed samples: 441856 | consumed tokens: 904921088 | elapsed time per iteration (s): 5.46 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 5.687077E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.811 | TFLOPs: 70.86 | +[default7]: iteration 864/ 3814 | consumed samples: 442368 | consumed tokens: 905969664 | elapsed time per iteration (s): 5.42 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 5.726224E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.453 | TFLOPs: 71.34 | +[default7]: iteration 865/ 3814 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 5.42 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 5.675307E+00 | loss scale: 8192.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.495 | TFLOPs: 71.37 | +[default7]: iteration 866/ 3814 | consumed samples: 443392 | consumed tokens: 908066816 | elapsed time per iteration (s): 5.43 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 5.665883E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.370 | TFLOPs: 71.28 | +[default7]: iteration 867/ 3814 | consumed samples: 443904 | consumed tokens: 909115392 | elapsed time per iteration (s): 5.43 | learning rate: 1.611E-04 | global batch size: 512 | lm loss: 5.679478E+00 | loss scale: 8192.0 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.352 | TFLOPs: 71.26 | +[default7]: iteration 868/ 3814 | consumed samples: 444416 | consumed tokens: 910163968 | elapsed time per iteration (s): 5.43 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 5.655764E+00 | loss scale: 8192.0 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.258 | TFLOPs: 71.19 | +[default7]: iteration 869/ 3814 | consumed samples: 444928 | consumed tokens: 911212544 | elapsed time per iteration (s): 5.43 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 5.670961E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.359 | TFLOPs: 71.27 | +[default7]: iteration 870/ 3814 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 5.42 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 5.687082E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.460 | TFLOPs: 71.35 | +[default7]: iteration 871/ 3814 | consumed samples: 445952 | consumed tokens: 913309696 | elapsed time per iteration (s): 5.44 | learning rate: 1.609E-04 | global batch size: 512 | lm loss: 5.671935E+00 | loss scale: 8192.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.183 | TFLOPs: 71.14 | +[default7]: iteration 872/ 3814 | consumed samples: 446464 | consumed tokens: 914358272 | elapsed time per iteration (s): 5.46 | learning rate: 1.609E-04 | global batch size: 512 | lm loss: 5.698963E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.845 | TFLOPs: 70.88 | +[default7]: iteration 873/ 3814 | consumed samples: 446976 | consumed tokens: 915406848 | elapsed time per iteration (s): 5.43 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 5.693606E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.370 | TFLOPs: 71.28 | +[default7]: iteration 874/ 3814 | consumed samples: 447488 | consumed tokens: 916455424 | elapsed time per iteration (s): 5.42 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 5.671922E+00 | loss scale: 8192.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.439 | TFLOPs: 71.33 | +[default7]: iteration 875/ 3814 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 5.42 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 5.640342E+00 | loss scale: 8192.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.488 | TFLOPs: 71.37 | +[default7]: iteration 876/ 3814 | consumed samples: 448512 | consumed tokens: 918552576 | elapsed time per iteration (s): 5.42 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 5.673882E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.433 | TFLOPs: 71.33 | +[default7]: iteration 877/ 3814 | consumed samples: 449024 | consumed tokens: 919601152 | elapsed time per iteration (s): 5.41 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 5.651658E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.626 | TFLOPs: 71.47 | +[default7]: iteration 878/ 3814 | consumed samples: 449536 | consumed tokens: 920649728 | elapsed time per iteration (s): 5.41 | learning rate: 1.607E-04 | global batch size: 512 | lm loss: 5.697679E+00 | loss scale: 8192.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.679 | TFLOPs: 71.51 | +[default7]: iteration 879/ 3814 | consumed samples: 450048 | consumed tokens: 921698304 | elapsed time per iteration (s): 5.42 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 5.645874E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.427 | TFLOPs: 71.32 | +[default7]: iteration 880/ 3814 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 5.42 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 5.632046E+00 | loss scale: 8192.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.427 | TFLOPs: 71.32 | +[default7]: iteration 881/ 3814 | consumed samples: 451072 | consumed tokens: 923795456 | elapsed time per iteration (s): 5.43 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 5.641343E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.247 | TFLOPs: 71.19 | +[default7]: iteration 882/ 3814 | consumed samples: 451584 | consumed tokens: 924844032 | elapsed time per iteration (s): 5.43 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 5.644068E+00 | loss scale: 8192.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.341 | TFLOPs: 71.26 | +[default7]: iteration 883/ 3814 | consumed samples: 452096 | consumed tokens: 925892608 | elapsed time per iteration (s): 5.43 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 5.655687E+00 | loss scale: 8192.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.277 | TFLOPs: 71.21 | +[default7]: iteration 884/ 3814 | consumed samples: 452608 | consumed tokens: 926941184 | elapsed time per iteration (s): 5.42 | learning rate: 1.605E-04 | global batch size: 512 | lm loss: 5.653400E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.400 | TFLOPs: 71.30 | +[default7]: iteration 885/ 3814 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 5.43 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 5.631056E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.358 | TFLOPs: 71.27 | +[default7]: iteration 886/ 3814 | consumed samples: 453632 | consumed tokens: 929038336 | elapsed time per iteration (s): 5.41 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 5.631901E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.663 | TFLOPs: 71.50 | +[default7]: iteration 887/ 3814 | consumed samples: 454144 | consumed tokens: 930086912 | elapsed time per iteration (s): 5.41 | learning rate: 1.604E-04 | global batch size: 512 | lm loss: 5.630525E+00 | loss scale: 8192.0 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.564 | TFLOPs: 71.42 | +[default7]: iteration 888/ 3814 | consumed samples: 454656 | consumed tokens: 931135488 | elapsed time per iteration (s): 5.42 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 5.627024E+00 | loss scale: 8192.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.425 | TFLOPs: 71.32 | +[default7]: iteration 889/ 3814 | consumed samples: 455168 | consumed tokens: 932184064 | elapsed time per iteration (s): 5.43 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 5.631187E+00 | loss scale: 8192.0 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.359 | TFLOPs: 71.27 | +[default7]: iteration 890/ 3814 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 5.44 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 5.656582E+00 | loss scale: 8192.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.099 | TFLOPs: 71.07 | +[default7]: iteration 891/ 3814 | consumed samples: 456192 | consumed tokens: 934281216 | elapsed time per iteration (s): 5.43 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 5.634030E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.326 | TFLOPs: 71.25 | +[default7]: iteration 892/ 3814 | consumed samples: 456704 | consumed tokens: 935329792 | elapsed time per iteration (s): 5.42 | learning rate: 1.602E-04 | global batch size: 512 | lm loss: 5.637053E+00 | loss scale: 8192.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.502 | TFLOPs: 71.38 | +[default7]: iteration 893/ 3814 | consumed samples: 457216 | consumed tokens: 936378368 | elapsed time per iteration (s): 5.45 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 5.638049E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.966 | TFLOPs: 70.97 | +[default7]: iteration 894/ 3814 | consumed samples: 457728 | consumed tokens: 937426944 | elapsed time per iteration (s): 5.43 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 5.658305E+00 | loss scale: 8192.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.228 | TFLOPs: 71.17 | +[default7]: iteration 895/ 3814 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 5.44 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 5.627588E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.039 | TFLOPs: 71.03 | +[default7]: iteration 896/ 3814 | consumed samples: 458752 | consumed tokens: 939524096 | elapsed time per iteration (s): 5.43 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 5.642129E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 897/ 3814 | consumed samples: 459264 | consumed tokens: 940572672 | elapsed time per iteration (s): 5.43 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 5.631107E+00 | loss scale: 8192.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.303 | TFLOPs: 71.23 | +[default7]: iteration 898/ 3814 | consumed samples: 459776 | consumed tokens: 941621248 | elapsed time per iteration (s): 5.45 | learning rate: 1.600E-04 | global batch size: 512 | lm loss: 5.619021E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 899/ 3814 | consumed samples: 460288 | consumed tokens: 942669824 | elapsed time per iteration (s): 5.44 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 5.640927E+00 | loss scale: 8192.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.136 | TFLOPs: 71.10 | +[default7]: iteration 900/ 3814 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 5.46 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 5.619699E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.804 | TFLOPs: 70.85 | +[default7]: iteration 901/ 3814 | consumed samples: 461312 | consumed tokens: 944766976 | elapsed time per iteration (s): 5.46 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 5.629069E+00 | loss scale: 8192.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.699 | TFLOPs: 70.77 | +[default7]: iteration 902/ 3814 | consumed samples: 461824 | consumed tokens: 945815552 | elapsed time per iteration (s): 5.47 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 5.612776E+00 | loss scale: 8192.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.625 | TFLOPs: 70.72 | +[default7]: iteration 903/ 3814 | consumed samples: 462336 | consumed tokens: 946864128 | elapsed time per iteration (s): 5.44 | learning rate: 1.598E-04 | global batch size: 512 | lm loss: 5.626229E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.186 | TFLOPs: 71.14 | +[default7]: iteration 904/ 3814 | consumed samples: 462848 | consumed tokens: 947912704 | elapsed time per iteration (s): 5.46 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 5.605964E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.704 | TFLOPs: 70.78 | +[default7]: iteration 905/ 3814 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 5.45 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 5.622900E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.941 | TFLOPs: 70.95 | +[default7]: iteration 906/ 3814 | consumed samples: 463872 | consumed tokens: 950009856 | elapsed time per iteration (s): 5.44 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 5.615075E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.189 | TFLOPs: 71.14 | +[default7]: iteration 907/ 3814 | consumed samples: 464384 | consumed tokens: 951058432 | elapsed time per iteration (s): 5.46 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 5.634010E+00 | loss scale: 8192.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.799 | TFLOPs: 70.85 | +[default7]: iteration 908/ 3814 | consumed samples: 464896 | consumed tokens: 952107008 | elapsed time per iteration (s): 5.45 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 5.601571E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.893 | TFLOPs: 70.92 | +[default7]: iteration 909/ 3814 | consumed samples: 465408 | consumed tokens: 953155584 | elapsed time per iteration (s): 5.46 | learning rate: 1.596E-04 | global batch size: 512 | lm loss: 5.594862E+00 | loss scale: 8192.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.777 | TFLOPs: 70.83 | +[default7]: iteration 910/ 3814 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 5.47 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 5.623746E+00 | loss scale: 8192.0 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.564 | TFLOPs: 70.67 | +[default7]: iteration 911/ 3814 | consumed samples: 466432 | consumed tokens: 955252736 | elapsed time per iteration (s): 5.46 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 5.583330E+00 | loss scale: 8192.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.748 | TFLOPs: 70.81 | +[default7]: iteration 912/ 3814 | consumed samples: 466944 | consumed tokens: 956301312 | elapsed time per iteration (s): 5.44 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 5.593667E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.036 | TFLOPs: 71.03 | +[default7]: iteration 913/ 3814 | consumed samples: 467456 | consumed tokens: 957349888 | elapsed time per iteration (s): 5.44 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 5.608074E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.110 | TFLOPs: 71.08 | +[default7]: iteration 914/ 3814 | consumed samples: 467968 | consumed tokens: 958398464 | elapsed time per iteration (s): 5.44 | learning rate: 1.594E-04 | global batch size: 512 | lm loss: 5.607291E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.162 | TFLOPs: 71.12 | +[default7]: iteration 915/ 3814 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 5.45 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 5.618135E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.930 | TFLOPs: 70.95 | +[default7]: iteration 916/ 3814 | consumed samples: 468992 | consumed tokens: 960495616 | elapsed time per iteration (s): 5.44 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 5.604283E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.040 | TFLOPs: 71.03 | +[default7]: iteration 917/ 3814 | consumed samples: 469504 | consumed tokens: 961544192 | elapsed time per iteration (s): 5.45 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 5.588953E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.960 | TFLOPs: 70.97 | +[default7]: iteration 918/ 3814 | consumed samples: 470016 | consumed tokens: 962592768 | elapsed time per iteration (s): 5.45 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 5.597758E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.871 | TFLOPs: 70.90 | +[default7]: iteration 919/ 3814 | consumed samples: 470528 | consumed tokens: 963641344 | elapsed time per iteration (s): 5.44 | learning rate: 1.592E-04 | global batch size: 512 | lm loss: 5.578715E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.113 | TFLOPs: 71.08 | +[default7]: iteration 920/ 3814 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 5.44 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 5.582951E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.069 | TFLOPs: 71.05 | +[default7]: iteration 921/ 3814 | consumed samples: 471552 | consumed tokens: 965738496 | elapsed time per iteration (s): 5.45 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 5.578246E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.882 | TFLOPs: 70.91 | +[default7]: iteration 922/ 3814 | consumed samples: 472064 | consumed tokens: 966787072 | elapsed time per iteration (s): 5.45 | learning rate: 1.591E-04 | global batch size: 512 | lm loss: 5.581979E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.924 | TFLOPs: 70.94 | +[default7]: iteration 923/ 3814 | consumed samples: 472576 | consumed tokens: 967835648 | elapsed time per iteration (s): 5.44 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 5.601779E+00 | loss scale: 8192.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.150 | TFLOPs: 71.11 | +[default7]: iteration 924/ 3814 | consumed samples: 473088 | consumed tokens: 968884224 | elapsed time per iteration (s): 5.44 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 5.585618E+00 | loss scale: 8192.0 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.134 | TFLOPs: 71.10 | +[default7]: iteration 925/ 3814 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 5.46 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 5.576370E+00 | loss scale: 8192.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.798 | TFLOPs: 70.85 | +[default7]: iteration 926/ 3814 | consumed samples: 474112 | consumed tokens: 970981376 | elapsed time per iteration (s): 5.45 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 5.590146E+00 | loss scale: 8192.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.958 | TFLOPs: 70.97 | +[default7]: iteration 927/ 3814 | consumed samples: 474624 | consumed tokens: 972029952 | elapsed time per iteration (s): 5.45 | learning rate: 1.589E-04 | global batch size: 512 | lm loss: 5.571093E+00 | loss scale: 8192.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.925 | TFLOPs: 70.94 | +[default7]: iteration 928/ 3814 | consumed samples: 475136 | consumed tokens: 973078528 | elapsed time per iteration (s): 5.45 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 5.571169E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.870 | TFLOPs: 70.90 | +[default7]: iteration 929/ 3814 | consumed samples: 475648 | consumed tokens: 974127104 | elapsed time per iteration (s): 5.44 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 5.586102E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.203 | TFLOPs: 71.15 | +[default7]: iteration 930/ 3814 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 5.44 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 5.591135E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.102 | TFLOPs: 71.08 | +[default7]: iteration 931/ 3814 | consumed samples: 476672 | consumed tokens: 976224256 | elapsed time per iteration (s): 5.45 | learning rate: 1.587E-04 | global batch size: 512 | lm loss: 5.569630E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.024 | TFLOPs: 71.02 | +[default7]: iteration 932/ 3814 | consumed samples: 477184 | consumed tokens: 977272832 | elapsed time per iteration (s): 5.45 | learning rate: 1.587E-04 | global batch size: 512 | lm loss: 5.572428E+00 | loss scale: 8192.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.022 | TFLOPs: 71.02 | +[default7]: iteration 933/ 3814 | consumed samples: 477696 | consumed tokens: 978321408 | elapsed time per iteration (s): 5.43 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 5.550314E+00 | loss scale: 8192.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.277 | TFLOPs: 71.21 | +[default7]: iteration 934/ 3814 | consumed samples: 478208 | consumed tokens: 979369984 | elapsed time per iteration (s): 5.44 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 5.551087E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.114 | TFLOPs: 71.09 | +[default7]: iteration 935/ 3814 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 5.42 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 5.562121E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.394 | TFLOPs: 71.30 | +[default7]: iteration 936/ 3814 | consumed samples: 479232 | consumed tokens: 981467136 | elapsed time per iteration (s): 5.43 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 5.554811E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.261 | TFLOPs: 71.20 | +[default7]: iteration 937/ 3814 | consumed samples: 479744 | consumed tokens: 982515712 | elapsed time per iteration (s): 5.44 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 5.575952E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.070 | TFLOPs: 71.05 | +[default7]: iteration 938/ 3814 | consumed samples: 480256 | consumed tokens: 983564288 | elapsed time per iteration (s): 5.44 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 5.553935E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.192 | TFLOPs: 71.14 | +[default7]: iteration 939/ 3814 | consumed samples: 480768 | consumed tokens: 984612864 | elapsed time per iteration (s): 5.42 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 5.565741E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.404 | TFLOPs: 71.30 | +[default7]: iteration 940/ 3814 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 5.44 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 5.544237E+00 | loss scale: 8192.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.115 | TFLOPs: 71.09 | +[default7]: iteration 941/ 3814 | consumed samples: 481792 | consumed tokens: 986710016 | elapsed time per iteration (s): 5.45 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 5.560743E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.932 | TFLOPs: 70.95 | +[default7]: iteration 942/ 3814 | consumed samples: 482304 | consumed tokens: 987758592 | elapsed time per iteration (s): 5.43 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 5.536145E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.362 | TFLOPs: 71.27 | +[default7]: iteration 943/ 3814 | consumed samples: 482816 | consumed tokens: 988807168 | elapsed time per iteration (s): 5.42 | learning rate: 1.583E-04 | global batch size: 512 | lm loss: 5.559805E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.477 | TFLOPs: 71.36 | +[default7]: iteration 944/ 3814 | consumed samples: 483328 | consumed tokens: 989855744 | elapsed time per iteration (s): 5.42 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 5.563787E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.460 | TFLOPs: 71.35 | +[default7]: iteration 945/ 3814 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 5.42 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 5.573863E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.518 | TFLOPs: 71.39 | +[default7]: iteration 946/ 3814 | consumed samples: 484352 | consumed tokens: 991952896 | elapsed time per iteration (s): 5.43 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 5.541657E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.242 | TFLOPs: 71.18 | +[default7]: iteration 947/ 3814 | consumed samples: 484864 | consumed tokens: 993001472 | elapsed time per iteration (s): 5.44 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 5.531697E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.147 | TFLOPs: 71.11 | +[default7]: iteration 948/ 3814 | consumed samples: 485376 | consumed tokens: 994050048 | elapsed time per iteration (s): 5.44 | learning rate: 1.581E-04 | global batch size: 512 | lm loss: 5.550935E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.187 | TFLOPs: 71.14 | +[default7]: iteration 949/ 3814 | consumed samples: 485888 | consumed tokens: 995098624 | elapsed time per iteration (s): 5.41 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 5.556999E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.573 | TFLOPs: 71.43 | +[default7]: iteration 950/ 3814 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 5.45 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 5.555193E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.999 | TFLOPs: 71.00 | +[default7]: iteration 951/ 3814 | consumed samples: 486912 | consumed tokens: 997195776 | elapsed time per iteration (s): 5.43 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 5.519404E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.334 | TFLOPs: 71.25 | +[default7]: iteration 952/ 3814 | consumed samples: 487424 | consumed tokens: 998244352 | elapsed time per iteration (s): 5.45 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 5.531510E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.918 | TFLOPs: 70.94 | +[default7]: iteration 953/ 3814 | consumed samples: 487936 | consumed tokens: 999292928 | elapsed time per iteration (s): 5.42 | learning rate: 1.579E-04 | global batch size: 512 | lm loss: 5.534720E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.456 | TFLOPs: 71.34 | +[default7]: iteration 954/ 3814 | consumed samples: 488448 | consumed tokens: 1000341504 | elapsed time per iteration (s): 5.44 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 5.536528E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.146 | TFLOPs: 71.11 | +[default7]: iteration 955/ 3814 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 5.44 | learning rate: 1.578E-04 | global batch size: 512 | lm loss: 5.537789E+00 | loss scale: 8192.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 956/ 3814 | consumed samples: 489472 | consumed tokens: 1002438656 | elapsed time per iteration (s): 5.42 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 5.540904E+00 | loss scale: 8192.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.498 | TFLOPs: 71.37 | +[default7]: iteration 957/ 3814 | consumed samples: 489984 | consumed tokens: 1003487232 | elapsed time per iteration (s): 5.42 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 5.520471E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.391 | TFLOPs: 71.29 | +[default7]: iteration 958/ 3814 | consumed samples: 490496 | consumed tokens: 1004535808 | elapsed time per iteration (s): 5.42 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 5.532674E+00 | loss scale: 8192.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.534 | TFLOPs: 71.40 | +[default7]: iteration 959/ 3814 | consumed samples: 491008 | consumed tokens: 1005584384 | elapsed time per iteration (s): 5.48 | learning rate: 1.576E-04 | global batch size: 512 | lm loss: 5.526995E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.457 | TFLOPs: 70.59 | +[default7]: iteration 960/ 3814 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 5.46 | learning rate: 1.576E-04 | global batch size: 512 | lm loss: 5.529991E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.781 | TFLOPs: 70.83 | +[default7]: iteration 961/ 3814 | consumed samples: 492032 | consumed tokens: 1007681536 | elapsed time per iteration (s): 5.45 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 5.519286E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.925 | TFLOPs: 70.94 | +[default7]: iteration 962/ 3814 | consumed samples: 492544 | consumed tokens: 1008730112 | elapsed time per iteration (s): 5.47 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 5.509708E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.529 | TFLOPs: 70.64 | +[default7]: iteration 963/ 3814 | consumed samples: 493056 | consumed tokens: 1009778688 | elapsed time per iteration (s): 5.44 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 5.494215E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.196 | TFLOPs: 71.15 | +[default7]: iteration 964/ 3814 | consumed samples: 493568 | consumed tokens: 1010827264 | elapsed time per iteration (s): 5.45 | learning rate: 1.574E-04 | global batch size: 512 | lm loss: 5.516660E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.965 | TFLOPs: 70.97 | +[default7]: iteration 965/ 3814 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 5.44 | learning rate: 1.574E-04 | global batch size: 512 | lm loss: 5.526014E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.135 | TFLOPs: 71.10 | +[default7]: iteration 966/ 3814 | consumed samples: 494592 | consumed tokens: 1012924416 | elapsed time per iteration (s): 5.45 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 5.520139E+00 | loss scale: 8192.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.976 | TFLOPs: 70.98 | +[default7]: iteration 967/ 3814 | consumed samples: 495104 | consumed tokens: 1013972992 | elapsed time per iteration (s): 5.45 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 5.521511E+00 | loss scale: 8192.0 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.016 | TFLOPs: 71.01 | +[default7]: iteration 968/ 3814 | consumed samples: 495616 | consumed tokens: 1015021568 | elapsed time per iteration (s): 5.42 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 5.491033E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.433 | TFLOPs: 71.33 | +[default7]: iteration 969/ 3814 | consumed samples: 496128 | consumed tokens: 1016070144 | elapsed time per iteration (s): 5.43 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 5.501743E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.304 | TFLOPs: 71.23 | +[default7]: iteration 970/ 3814 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 5.43 | learning rate: 1.572E-04 | global batch size: 512 | lm loss: 5.513185E+00 | loss scale: 8192.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.243 | TFLOPs: 71.18 | +[default7]: iteration 971/ 3814 | consumed samples: 497152 | consumed tokens: 1018167296 | elapsed time per iteration (s): 5.43 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 5.504729E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.373 | TFLOPs: 71.28 | +[default7]: iteration 972/ 3814 | consumed samples: 497664 | consumed tokens: 1019215872 | elapsed time per iteration (s): 5.42 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 5.508371E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.451 | TFLOPs: 71.34 | +[default7]: iteration 973/ 3814 | consumed samples: 498176 | consumed tokens: 1020264448 | elapsed time per iteration (s): 5.43 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 5.487924E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.272 | TFLOPs: 71.20 | +[default7]: iteration 974/ 3814 | consumed samples: 498688 | consumed tokens: 1021313024 | elapsed time per iteration (s): 5.42 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 5.508398E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.397 | TFLOPs: 71.30 | +[default7]: iteration 975/ 3814 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 5.43 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 5.516397E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.240 | TFLOPs: 71.18 | +[default7]: iteration 976/ 3814 | consumed samples: 499712 | consumed tokens: 1023410176 | elapsed time per iteration (s): 5.43 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 5.509086E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.350 | TFLOPs: 71.26 | +[default7]: iteration 977/ 3814 | consumed samples: 500224 | consumed tokens: 1024458752 | elapsed time per iteration (s): 5.41 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 5.504997E+00 | loss scale: 8192.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.591 | TFLOPs: 71.45 | +[default7]: iteration 978/ 3814 | consumed samples: 500736 | consumed tokens: 1025507328 | elapsed time per iteration (s): 5.42 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 5.500931E+00 | loss scale: 8192.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.485 | TFLOPs: 71.37 | +[default7]: iteration 979/ 3814 | consumed samples: 501248 | consumed tokens: 1026555904 | elapsed time per iteration (s): 5.43 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 5.511948E+00 | loss scale: 8192.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.254 | TFLOPs: 71.19 | +[default7]: iteration 980/ 3814 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 5.44 | learning rate: 1.568E-04 | global batch size: 512 | lm loss: 5.489116E+00 | loss scale: 8192.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 981/ 3814 | consumed samples: 502272 | consumed tokens: 1028653056 | elapsed time per iteration (s): 5.42 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 5.480037E+00 | loss scale: 8192.0 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.476 | TFLOPs: 71.36 | +[default7]: iteration 982/ 3814 | consumed samples: 502784 | consumed tokens: 1029701632 | elapsed time per iteration (s): 5.44 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 5.489281E+00 | loss scale: 8192.0 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.137 | TFLOPs: 71.10 | +[default7]: iteration 983/ 3814 | consumed samples: 503296 | consumed tokens: 1030750208 | elapsed time per iteration (s): 5.43 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 5.513854E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.296 | TFLOPs: 71.22 | +[default7]: iteration 984/ 3814 | consumed samples: 503808 | consumed tokens: 1031798784 | elapsed time per iteration (s): 5.42 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 5.463278E+00 | loss scale: 8192.0 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.549 | TFLOPs: 71.41 | +[default7]: iteration 985/ 3814 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 5.43 | learning rate: 1.566E-04 | global batch size: 512 | lm loss: 5.515403E+00 | loss scale: 8192.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.249 | TFLOPs: 71.19 | +[default7]: iteration 986/ 3814 | consumed samples: 504832 | consumed tokens: 1033895936 | elapsed time per iteration (s): 5.44 | learning rate: 1.565E-04 | global batch size: 512 | lm loss: 5.484814E+00 | loss scale: 8192.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.043 | TFLOPs: 71.03 | +[default7]: iteration 987/ 3814 | consumed samples: 505344 | consumed tokens: 1034944512 | elapsed time per iteration (s): 5.45 | learning rate: 1.565E-04 | global batch size: 512 | lm loss: 5.498119E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.975 | TFLOPs: 70.98 | +[default7]: iteration 988/ 3814 | consumed samples: 505856 | consumed tokens: 1035993088 | elapsed time per iteration (s): 5.44 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 5.461794E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.119 | TFLOPs: 71.09 | +[default7]: iteration 989/ 3814 | consumed samples: 506368 | consumed tokens: 1037041664 | elapsed time per iteration (s): 5.45 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 5.477571E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.008 | TFLOPs: 71.01 | +[default7]: iteration 990/ 3814 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 5.42 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 5.495689E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.468 | TFLOPs: 71.35 | +[default7]: iteration 991/ 3814 | consumed samples: 507392 | consumed tokens: 1039138816 | elapsed time per iteration (s): 5.41 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 5.480731E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.557 | TFLOPs: 71.42 | +[default7]: iteration 992/ 3814 | consumed samples: 507904 | consumed tokens: 1040187392 | elapsed time per iteration (s): 5.42 | learning rate: 1.563E-04 | global batch size: 512 | lm loss: 5.459850E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.447 | TFLOPs: 71.34 | +[default7]: iteration 993/ 3814 | consumed samples: 508416 | consumed tokens: 1041235968 | elapsed time per iteration (s): 5.42 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 5.449988E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 994/ 3814 | consumed samples: 508928 | consumed tokens: 1042284544 | elapsed time per iteration (s): 5.42 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 5.476115E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.421 | TFLOPs: 71.32 | +[default7]: iteration 995/ 3814 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 5.42 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 5.485628E+00 | loss scale: 8192.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.407 | TFLOPs: 71.31 | +[default7]: iteration 996/ 3814 | consumed samples: 509952 | consumed tokens: 1044381696 | elapsed time per iteration (s): 5.42 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 5.440630E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.405 | TFLOPs: 71.30 | +[default7]: iteration 997/ 3814 | consumed samples: 510464 | consumed tokens: 1045430272 | elapsed time per iteration (s): 5.42 | learning rate: 1.561E-04 | global batch size: 512 | lm loss: 5.460223E+00 | loss scale: 8192.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.443 | TFLOPs: 71.33 | +[default7]: iteration 998/ 3814 | consumed samples: 510976 | consumed tokens: 1046478848 | elapsed time per iteration (s): 5.43 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 5.472120E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.232 | TFLOPs: 71.17 | +[default7]: iteration 999/ 3814 | consumed samples: 511488 | consumed tokens: 1047527424 | elapsed time per iteration (s): 5.48 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 5.428623E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.414 | TFLOPs: 70.56 | +[default7]: iteration 1000/ 3814 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 5.43 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 5.479703E+00 | loss scale: 16384.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.373 | TFLOPs: 71.28 | +[default7]:------------------------------------------------------------------------------------------ +[default7]:valid loss at iteration 1000 | lm loss value: 5.400693E+00 | lm loss PPL: 2.215600E+02 | +[default7]:------------------------------------------------------------------------------------------ +[default1]:[2023-02-16 12:50:23,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 1000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 12:50:23,310] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +[default0]:[2023-02-16 12:50:23,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:23,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,481] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,483] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:23,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:23,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:23,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:23,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:23,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:23,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:23,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,790] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,795] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:23,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,856] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:23,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:23,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,914] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:23,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:23,974] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:23,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:23,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,039] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,103] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,226] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,221] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,282] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,346] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,417] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,470] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,541] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,610] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,664] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,674] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,788] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:24,935] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,935] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:24,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,928] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:24,991] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:24,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:24,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:24,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:25,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:25,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,055] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:25,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,123] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:25,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,116] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:25,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:25,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,184] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:25,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,250] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:25,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,239] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:25,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:25,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,300] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:25,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 12:50:25,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,374] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:25,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 12:50:25,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,422] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:25,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,489] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 12:50:25,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 12:50:25,491] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt +[default0]:[2023-02-16 12:50:25,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 12:50:25,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt. +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:50:25,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,501] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 12:50:25,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 12:50:25,503] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt +[default1]:[2023-02-16 12:50:25,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 12:50:25,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:50:25,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:50:26,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,063] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,082] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,062] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,067] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,061] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,092] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,148] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,113] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,083] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,083] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,183] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,207] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,188] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,153] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,182] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,229] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,209] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,188] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,207] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,221] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,235] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,248] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,191] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,257] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,233] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,259] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,171] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,245] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,230] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,207] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,254] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,268] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,238] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,281] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,255] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,231] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,243] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,240] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,252] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,296] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,255] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,298] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,279] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,231] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,239] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,283] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,263] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,297] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,273] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,269] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,282] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 12:50:26,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:50:26,290] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:50:26,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,285] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,284] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 12:50:26,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:50:26,301] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:50:26,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,286] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,341] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 12:50:26,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:50:26,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:50:26,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 12:50:26,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,307] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 12:50:26,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:50:26,337] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:50:26,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 12:50:26,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:50:26,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:50:26,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 12:50:26,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,345] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,345] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 12:50:26,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:50:26,385] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:50:26,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:time (ms) | save-checkpoint: 3108.93 +[default4]:[2023-02-16 12:50:26,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:50:26,415] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:50:26,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]: successfully saved checkpoint at iteration 1000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default5]:[2023-02-16 12:50:26,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:50:26,415] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:50:26,415] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]: iteration 1001/ 3814 | consumed samples: 512512 | consumed tokens: 1049624576 | elapsed time per iteration (s): 9.58 | learning rate: 1.559E-04 | global batch size: 512 | lm loss: 5.482691E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 53.465 | TFLOPs: 40.38 | +[default7]: iteration 1002/ 3814 | consumed samples: 513024 | consumed tokens: 1050673152 | elapsed time per iteration (s): 5.44 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 5.514534E+00 | loss scale: 16384.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.053 | TFLOPs: 71.04 | +[default7]: iteration 1003/ 3814 | consumed samples: 513536 | consumed tokens: 1051721728 | elapsed time per iteration (s): 5.46 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 5.422524E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.827 | TFLOPs: 70.87 | +[default7]: iteration 1004/ 3814 | consumed samples: 514048 | consumed tokens: 1052770304 | elapsed time per iteration (s): 5.43 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 5.484854E+00 | loss scale: 16384.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 1005/ 3814 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 5.44 | learning rate: 1.557E-04 | global batch size: 512 | lm loss: 5.467092E+00 | loss scale: 16384.0 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.180 | TFLOPs: 71.14 | +[default7]: iteration 1006/ 3814 | consumed samples: 515072 | consumed tokens: 1054867456 | elapsed time per iteration (s): 5.42 | learning rate: 1.557E-04 | global batch size: 512 | lm loss: 5.501474E+00 | loss scale: 16384.0 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.397 | TFLOPs: 71.30 | +[default7]: iteration 1007/ 3814 | consumed samples: 515584 | consumed tokens: 1055916032 | elapsed time per iteration (s): 5.42 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 5.459929E+00 | loss scale: 16384.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.538 | TFLOPs: 71.41 | +[default7]: iteration 1008/ 3814 | consumed samples: 516096 | consumed tokens: 1056964608 | elapsed time per iteration (s): 5.42 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 5.459518E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.423 | TFLOPs: 71.32 | +[default7]: iteration 1009/ 3814 | consumed samples: 516608 | consumed tokens: 1058013184 | elapsed time per iteration (s): 5.42 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 5.441891E+00 | loss scale: 16384.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.433 | TFLOPs: 71.33 | +[default7]: iteration 1010/ 3814 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 5.44 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 5.474944E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.166 | TFLOPs: 71.12 | +[default7]: iteration 1011/ 3814 | consumed samples: 517632 | consumed tokens: 1060110336 | elapsed time per iteration (s): 5.42 | learning rate: 1.555E-04 | global batch size: 512 | lm loss: 5.433230E+00 | loss scale: 16384.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.424 | TFLOPs: 71.32 | +[default7]: iteration 1012/ 3814 | consumed samples: 518144 | consumed tokens: 1061158912 | elapsed time per iteration (s): 5.44 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 5.421378E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.160 | TFLOPs: 71.12 | +[default7]: iteration 1013/ 3814 | consumed samples: 518656 | consumed tokens: 1062207488 | elapsed time per iteration (s): 5.43 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 5.440079E+00 | loss scale: 16384.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.296 | TFLOPs: 71.22 | +[default7]: iteration 1014/ 3814 | consumed samples: 519168 | consumed tokens: 1063256064 | elapsed time per iteration (s): 5.44 | learning rate: 1.553E-04 | global batch size: 512 | lm loss: 5.459206E+00 | loss scale: 16384.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.061 | TFLOPs: 71.04 | +[default7]: iteration 1015/ 3814 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 5.45 | learning rate: 1.553E-04 | global batch size: 512 | lm loss: 5.436093E+00 | loss scale: 16384.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 1016/ 3814 | consumed samples: 520192 | consumed tokens: 1065353216 | elapsed time per iteration (s): 5.43 | learning rate: 1.552E-04 | global batch size: 512 | lm loss: 5.440533E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 1017/ 3814 | consumed samples: 520704 | consumed tokens: 1066401792 | elapsed time per iteration (s): 5.45 | learning rate: 1.552E-04 | global batch size: 512 | lm loss: 5.421947E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.934 | TFLOPs: 70.95 | +[default7]: iteration 1018/ 3814 | consumed samples: 521216 | consumed tokens: 1067450368 | elapsed time per iteration (s): 5.45 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 5.445710E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.909 | TFLOPs: 70.93 | +[default7]: iteration 1019/ 3814 | consumed samples: 521728 | consumed tokens: 1068498944 | elapsed time per iteration (s): 5.45 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 5.447145E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.945 | TFLOPs: 70.96 | +[default7]: iteration 1020/ 3814 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 5.46 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 5.461235E+00 | loss scale: 16384.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.726 | TFLOPs: 70.79 | +[default7]: iteration 1021/ 3814 | consumed samples: 522752 | consumed tokens: 1070596096 | elapsed time per iteration (s): 5.45 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 5.436769E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.871 | TFLOPs: 70.90 | +[default7]: iteration 1022/ 3814 | consumed samples: 523264 | consumed tokens: 1071644672 | elapsed time per iteration (s): 5.43 | learning rate: 1.550E-04 | global batch size: 512 | lm loss: 5.422441E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.365 | TFLOPs: 71.28 | +[default7]: iteration 1023/ 3814 | consumed samples: 523776 | consumed tokens: 1072693248 | elapsed time per iteration (s): 5.44 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 5.427982E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.200 | TFLOPs: 71.15 | +[default7]: iteration 1024/ 3814 | consumed samples: 524288 | consumed tokens: 1073741824 | elapsed time per iteration (s): 5.44 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 5.431157E+00 | loss scale: 16384.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.173 | TFLOPs: 71.13 | +[default7]: iteration 1025/ 3814 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 5.43 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 5.430185E+00 | loss scale: 16384.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 1026/ 3814 | consumed samples: 525312 | consumed tokens: 1075838976 | elapsed time per iteration (s): 5.44 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 5.410079E+00 | loss scale: 16384.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.060 | TFLOPs: 71.04 | +[default7]: iteration 1027/ 3814 | consumed samples: 525824 | consumed tokens: 1076887552 | elapsed time per iteration (s): 5.44 | learning rate: 1.548E-04 | global batch size: 512 | lm loss: 5.420165E+00 | loss scale: 16384.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 1028/ 3814 | consumed samples: 526336 | consumed tokens: 1077936128 | elapsed time per iteration (s): 5.43 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 5.422575E+00 | loss scale: 16384.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.231 | TFLOPs: 71.17 | +[default7]: iteration 1029/ 3814 | consumed samples: 526848 | consumed tokens: 1078984704 | elapsed time per iteration (s): 5.45 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 5.420995E+00 | loss scale: 16384.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.026 | TFLOPs: 71.02 | +[default7]: iteration 1030/ 3814 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 5.42 | learning rate: 1.546E-04 | global batch size: 512 | lm loss: 5.396822E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.521 | TFLOPs: 71.39 | +[default7]: iteration 1031/ 3814 | consumed samples: 527872 | consumed tokens: 1081081856 | elapsed time per iteration (s): 5.43 | learning rate: 1.546E-04 | global batch size: 512 | lm loss: 5.451839E+00 | loss scale: 16384.0 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.349 | TFLOPs: 71.26 | +[default7]: iteration 1032/ 3814 | consumed samples: 528384 | consumed tokens: 1082130432 | elapsed time per iteration (s): 5.45 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 5.430338E+00 | loss scale: 16384.0 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.915 | TFLOPs: 70.94 | +[default7]: iteration 1033/ 3814 | consumed samples: 528896 | consumed tokens: 1083179008 | elapsed time per iteration (s): 5.42 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 5.400514E+00 | loss scale: 16384.0 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.442 | TFLOPs: 71.33 | +[default7]: iteration 1034/ 3814 | consumed samples: 529408 | consumed tokens: 1084227584 | elapsed time per iteration (s): 5.43 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 5.453453E+00 | loss scale: 16384.0 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.332 | TFLOPs: 71.25 | +[default7]: iteration 1035/ 3814 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 5.43 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 5.412549E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.344 | TFLOPs: 71.26 | +[default7]: iteration 1036/ 3814 | consumed samples: 530432 | consumed tokens: 1086324736 | elapsed time per iteration (s): 5.43 | learning rate: 1.544E-04 | global batch size: 512 | lm loss: 5.417541E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.328 | TFLOPs: 71.25 | +[default7]: iteration 1037/ 3814 | consumed samples: 530944 | consumed tokens: 1087373312 | elapsed time per iteration (s): 5.42 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 5.392589E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.527 | TFLOPs: 71.40 | +[default7]: iteration 1038/ 3814 | consumed samples: 531456 | consumed tokens: 1088421888 | elapsed time per iteration (s): 5.43 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 5.454652E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.309 | TFLOPs: 71.23 | +[default7]: iteration 1039/ 3814 | consumed samples: 531968 | consumed tokens: 1089470464 | elapsed time per iteration (s): 5.46 | learning rate: 1.542E-04 | global batch size: 512 | lm loss: 5.412694E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.756 | TFLOPs: 70.82 | +[default7]: iteration 1040/ 3814 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 5.43 | learning rate: 1.542E-04 | global batch size: 512 | lm loss: 5.400943E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.248 | TFLOPs: 71.19 | +[default7]: iteration 1041/ 3814 | consumed samples: 532992 | consumed tokens: 1091567616 | elapsed time per iteration (s): 5.43 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 5.379925E+00 | loss scale: 16384.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.343 | TFLOPs: 71.26 | +[default7]: iteration 1042/ 3814 | consumed samples: 533504 | consumed tokens: 1092616192 | elapsed time per iteration (s): 5.43 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 5.404013E+00 | loss scale: 16384.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.327 | TFLOPs: 71.25 | +[default7]: iteration 1043/ 3814 | consumed samples: 534016 | consumed tokens: 1093664768 | elapsed time per iteration (s): 5.42 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 5.393635E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.388 | TFLOPs: 71.29 | +[default7]: iteration 1044/ 3814 | consumed samples: 534528 | consumed tokens: 1094713344 | elapsed time per iteration (s): 5.42 | learning rate: 1.540E-04 | global batch size: 512 | lm loss: 5.393049E+00 | loss scale: 16384.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.511 | TFLOPs: 71.39 | +[default7]: iteration 1045/ 3814 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 5.44 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 5.398376E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.159 | TFLOPs: 71.12 | +[default7]: iteration 1046/ 3814 | consumed samples: 535552 | consumed tokens: 1096810496 | elapsed time per iteration (s): 5.42 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 5.378639E+00 | loss scale: 16384.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.460 | TFLOPs: 71.35 | +[default7]: iteration 1047/ 3814 | consumed samples: 536064 | consumed tokens: 1097859072 | elapsed time per iteration (s): 5.42 | learning rate: 1.539E-04 | global batch size: 512 | lm loss: 5.422069E+00 | loss scale: 16384.0 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.432 | TFLOPs: 71.33 | +[default7]: iteration 1048/ 3814 | consumed samples: 536576 | consumed tokens: 1098907648 | elapsed time per iteration (s): 5.43 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 5.409276E+00 | loss scale: 16384.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.314 | TFLOPs: 71.24 | +[default7]: iteration 1049/ 3814 | consumed samples: 537088 | consumed tokens: 1099956224 | elapsed time per iteration (s): 5.45 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 5.399435E+00 | loss scale: 16384.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.000 | TFLOPs: 71.00 | +[default7]: iteration 1050/ 3814 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 5.44 | learning rate: 1.537E-04 | global batch size: 512 | lm loss: 5.405032E+00 | loss scale: 16384.0 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.191 | TFLOPs: 71.14 | +[default7]: iteration 1051/ 3814 | consumed samples: 538112 | consumed tokens: 1102053376 | elapsed time per iteration (s): 5.43 | learning rate: 1.537E-04 | global batch size: 512 | lm loss: 5.387852E+00 | loss scale: 16384.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.207 | TFLOPs: 71.16 | +[default7]: iteration 1052/ 3814 | consumed samples: 538624 | consumed tokens: 1103101952 | elapsed time per iteration (s): 5.43 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 5.408178E+00 | loss scale: 16384.0 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.349 | TFLOPs: 71.26 | +[default7]: iteration 1053/ 3814 | consumed samples: 539136 | consumed tokens: 1104150528 | elapsed time per iteration (s): 5.42 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 5.376324E+00 | loss scale: 16384.0 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.388 | TFLOPs: 71.29 | +[default7]: iteration 1054/ 3814 | consumed samples: 539648 | consumed tokens: 1105199104 | elapsed time per iteration (s): 5.42 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 5.397903E+00 | loss scale: 16384.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 1055/ 3814 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 5.43 | learning rate: 1.535E-04 | global batch size: 512 | lm loss: 5.396619E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.366 | TFLOPs: 71.28 | +[default7]: iteration 1056/ 3814 | consumed samples: 540672 | consumed tokens: 1107296256 | elapsed time per iteration (s): 5.42 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 5.392530E+00 | loss scale: 16384.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.378 | TFLOPs: 71.28 | +[default7]: iteration 1057/ 3814 | consumed samples: 541184 | consumed tokens: 1108344832 | elapsed time per iteration (s): 5.44 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 5.429376E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.068 | TFLOPs: 71.05 | +[default7]: iteration 1058/ 3814 | consumed samples: 541696 | consumed tokens: 1109393408 | elapsed time per iteration (s): 5.41 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 5.377751E+00 | loss scale: 16384.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.645 | TFLOPs: 71.49 | +[default7]: iteration 1059/ 3814 | consumed samples: 542208 | consumed tokens: 1110441984 | elapsed time per iteration (s): 5.43 | learning rate: 1.533E-04 | global batch size: 512 | lm loss: 5.385395E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.376 | TFLOPs: 71.28 | +[default7]: iteration 1060/ 3814 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 5.45 | learning rate: 1.533E-04 | global batch size: 512 | lm loss: 5.387801E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.952 | TFLOPs: 70.96 | +[default7]: iteration 1061/ 3814 | consumed samples: 543232 | consumed tokens: 1112539136 | elapsed time per iteration (s): 5.44 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 5.393437E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.118 | TFLOPs: 71.09 | +[default7]: iteration 1062/ 3814 | consumed samples: 543744 | consumed tokens: 1113587712 | elapsed time per iteration (s): 5.47 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 5.360970E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.583 | TFLOPs: 70.68 | +[default7]: iteration 1063/ 3814 | consumed samples: 544256 | consumed tokens: 1114636288 | elapsed time per iteration (s): 5.46 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 5.370694E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.771 | TFLOPs: 70.83 | +[default7]: iteration 1064/ 3814 | consumed samples: 544768 | consumed tokens: 1115684864 | elapsed time per iteration (s): 5.43 | learning rate: 1.531E-04 | global batch size: 512 | lm loss: 5.377073E+00 | loss scale: 16384.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.207 | TFLOPs: 71.16 | +[default7]: iteration 1065/ 3814 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 5.44 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 5.382195E+00 | loss scale: 16384.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.156 | TFLOPs: 71.12 | +[default7]: iteration 1066/ 3814 | consumed samples: 545792 | consumed tokens: 1117782016 | elapsed time per iteration (s): 5.46 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 5.394624E+00 | loss scale: 16384.0 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.779 | TFLOPs: 70.83 | +[default7]: iteration 1067/ 3814 | consumed samples: 546304 | consumed tokens: 1118830592 | elapsed time per iteration (s): 5.46 | learning rate: 1.529E-04 | global batch size: 512 | lm loss: 5.379169E+00 | loss scale: 16384.0 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.809 | TFLOPs: 70.86 | +[default7]: iteration 1068/ 3814 | consumed samples: 546816 | consumed tokens: 1119879168 | elapsed time per iteration (s): 5.42 | learning rate: 1.529E-04 | global batch size: 512 | lm loss: 5.359638E+00 | loss scale: 16384.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 1069/ 3814 | consumed samples: 547328 | consumed tokens: 1120927744 | elapsed time per iteration (s): 5.44 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 5.363249E+00 | loss scale: 16384.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.086 | TFLOPs: 71.06 | +[default7]: iteration 1070/ 3814 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 5.44 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 5.364285E+00 | loss scale: 16384.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.153 | TFLOPs: 71.12 | +[default7]: iteration 1071/ 3814 | consumed samples: 548352 | consumed tokens: 1123024896 | elapsed time per iteration (s): 5.43 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 5.349941E+00 | loss scale: 16384.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.242 | TFLOPs: 71.18 | +[default7]: iteration 1072/ 3814 | consumed samples: 548864 | consumed tokens: 1124073472 | elapsed time per iteration (s): 5.43 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 5.354922E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.276 | TFLOPs: 71.21 | +[default7]: iteration 1073/ 3814 | consumed samples: 549376 | consumed tokens: 1125122048 | elapsed time per iteration (s): 5.46 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 5.365296E+00 | loss scale: 16384.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.808 | TFLOPs: 70.85 | +[default7]: iteration 1074/ 3814 | consumed samples: 549888 | consumed tokens: 1126170624 | elapsed time per iteration (s): 5.43 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 5.334453E+00 | loss scale: 16384.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 1075/ 3814 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 5.43 | learning rate: 1.526E-04 | global batch size: 512 | lm loss: 5.333918E+00 | loss scale: 16384.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.291 | TFLOPs: 71.22 | +[default7]: iteration 1076/ 3814 | consumed samples: 550912 | consumed tokens: 1128267776 | elapsed time per iteration (s): 5.44 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 5.374527E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.199 | TFLOPs: 71.15 | +[default7]: iteration 1077/ 3814 | consumed samples: 551424 | consumed tokens: 1129316352 | elapsed time per iteration (s): 5.44 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 5.345842E+00 | loss scale: 16384.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.147 | TFLOPs: 71.11 | +[default7]: iteration 1078/ 3814 | consumed samples: 551936 | consumed tokens: 1130364928 | elapsed time per iteration (s): 5.42 | learning rate: 1.524E-04 | global batch size: 512 | lm loss: 5.383214E+00 | loss scale: 16384.0 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.414 | TFLOPs: 71.31 | +[default7]: iteration 1079/ 3814 | consumed samples: 552448 | consumed tokens: 1131413504 | elapsed time per iteration (s): 5.46 | learning rate: 1.524E-04 | global batch size: 512 | lm loss: 5.350037E+00 | loss scale: 16384.0 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.740 | TFLOPs: 70.80 | +[default7]: iteration 1080/ 3814 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 5.45 | learning rate: 1.523E-04 | global batch size: 512 | lm loss: 5.362438E+00 | loss scale: 16384.0 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.993 | TFLOPs: 70.99 | +[default7]: iteration 1081/ 3814 | consumed samples: 553472 | consumed tokens: 1133510656 | elapsed time per iteration (s): 5.43 | learning rate: 1.523E-04 | global batch size: 512 | lm loss: 5.364499E+00 | loss scale: 16384.0 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.270 | TFLOPs: 71.20 | +[default7]: iteration 1082/ 3814 | consumed samples: 553984 | consumed tokens: 1134559232 | elapsed time per iteration (s): 5.43 | learning rate: 1.522E-04 | global batch size: 512 | lm loss: 5.367498E+00 | loss scale: 16384.0 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.293 | TFLOPs: 71.22 | +[default7]: iteration 1083/ 3814 | consumed samples: 554496 | consumed tokens: 1135607808 | elapsed time per iteration (s): 5.42 | learning rate: 1.522E-04 | global batch size: 512 | lm loss: 5.356866E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.453 | TFLOPs: 71.34 | +[default7]: iteration 1084/ 3814 | consumed samples: 555008 | consumed tokens: 1136656384 | elapsed time per iteration (s): 5.42 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 5.350283E+00 | loss scale: 16384.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.409 | TFLOPs: 71.31 | +[default7]: iteration 1085/ 3814 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 5.45 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 5.364989E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.961 | TFLOPs: 70.97 | +[default7]: iteration 1086/ 3814 | consumed samples: 556032 | consumed tokens: 1138753536 | elapsed time per iteration (s): 5.44 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 5.366769E+00 | loss scale: 16384.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.053 | TFLOPs: 71.04 | +[default7]: iteration 1087/ 3814 | consumed samples: 556544 | consumed tokens: 1139802112 | elapsed time per iteration (s): 5.44 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 5.323939E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.073 | TFLOPs: 71.05 | +[default7]: iteration 1088/ 3814 | consumed samples: 557056 | consumed tokens: 1140850688 | elapsed time per iteration (s): 5.46 | learning rate: 1.520E-04 | global batch size: 512 | lm loss: 5.316594E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.704 | TFLOPs: 70.78 | +[default7]: iteration 1089/ 3814 | consumed samples: 557568 | consumed tokens: 1141899264 | elapsed time per iteration (s): 5.46 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 5.335159E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.786 | TFLOPs: 70.84 | +[default7]: iteration 1090/ 3814 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 5.43 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 5.350087E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 1091/ 3814 | consumed samples: 558592 | consumed tokens: 1143996416 | elapsed time per iteration (s): 5.44 | learning rate: 1.518E-04 | global batch size: 512 | lm loss: 5.325935E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.040 | TFLOPs: 71.03 | +[default7]: iteration 1092/ 3814 | consumed samples: 559104 | consumed tokens: 1145044992 | elapsed time per iteration (s): 5.45 | learning rate: 1.518E-04 | global batch size: 512 | lm loss: 5.319045E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 1093/ 3814 | consumed samples: 559616 | consumed tokens: 1146093568 | elapsed time per iteration (s): 5.44 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 5.303990E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.121 | TFLOPs: 71.09 | +[default7]: iteration 1094/ 3814 | consumed samples: 560128 | consumed tokens: 1147142144 | elapsed time per iteration (s): 5.43 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 5.315853E+00 | loss scale: 16384.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.327 | TFLOPs: 71.25 | +[default7]: iteration 1095/ 3814 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 5.42 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 5.337535E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.496 | TFLOPs: 71.37 | +[default7]: iteration 1096/ 3814 | consumed samples: 561152 | consumed tokens: 1149239296 | elapsed time per iteration (s): 5.43 | learning rate: 1.516E-04 | global batch size: 512 | lm loss: 5.364296E+00 | loss scale: 16384.0 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.246 | TFLOPs: 71.18 | +[default7]: iteration 1097/ 3814 | consumed samples: 561664 | consumed tokens: 1150287872 | elapsed time per iteration (s): 5.43 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 5.331875E+00 | loss scale: 16384.0 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.226 | TFLOPs: 71.17 | +[default7]: iteration 1098/ 3814 | consumed samples: 562176 | consumed tokens: 1151336448 | elapsed time per iteration (s): 5.42 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 5.323597E+00 | loss scale: 16384.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.439 | TFLOPs: 71.33 | +[default7]: iteration 1099/ 3814 | consumed samples: 562688 | consumed tokens: 1152385024 | elapsed time per iteration (s): 5.41 | learning rate: 1.514E-04 | global batch size: 512 | lm loss: 5.311079E+00 | loss scale: 16384.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.619 | TFLOPs: 71.47 | +[default7]: iteration 1100/ 3814 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 5.43 | learning rate: 1.514E-04 | global batch size: 512 | lm loss: 5.347811E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.372 | TFLOPs: 71.28 | +[default7]: iteration 1101/ 3814 | consumed samples: 563712 | consumed tokens: 1154482176 | elapsed time per iteration (s): 5.45 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 5.340225E+00 | loss scale: 16384.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.017 | TFLOPs: 71.01 | +[default7]: iteration 1102/ 3814 | consumed samples: 564224 | consumed tokens: 1155530752 | elapsed time per iteration (s): 5.46 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 5.319752E+00 | loss scale: 16384.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.830 | TFLOPs: 70.87 | +[default7]: iteration 1103/ 3814 | consumed samples: 564736 | consumed tokens: 1156579328 | elapsed time per iteration (s): 5.43 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 5.314681E+00 | loss scale: 16384.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.328 | TFLOPs: 71.25 | +[default7]: iteration 1104/ 3814 | consumed samples: 565248 | consumed tokens: 1157627904 | elapsed time per iteration (s): 5.43 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 5.322250E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.297 | TFLOPs: 71.22 | +[default7]: iteration 1105/ 3814 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 5.43 | learning rate: 1.511E-04 | global batch size: 512 | lm loss: 5.335112E+00 | loss scale: 16384.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.318 | TFLOPs: 71.24 | +[default7]: iteration 1106/ 3814 | consumed samples: 566272 | consumed tokens: 1159725056 | elapsed time per iteration (s): 5.44 | learning rate: 1.511E-04 | global batch size: 512 | lm loss: 5.311186E+00 | loss scale: 16384.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.062 | TFLOPs: 71.05 | +[default7]: iteration 1107/ 3814 | consumed samples: 566784 | consumed tokens: 1160773632 | elapsed time per iteration (s): 5.43 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 5.320579E+00 | loss scale: 16384.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.290 | TFLOPs: 71.22 | +[default7]: iteration 1108/ 3814 | consumed samples: 567296 | consumed tokens: 1161822208 | elapsed time per iteration (s): 5.43 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 5.329211E+00 | loss scale: 16384.0 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.243 | TFLOPs: 71.18 | +[default7]: iteration 1109/ 3814 | consumed samples: 567808 | consumed tokens: 1162870784 | elapsed time per iteration (s): 5.42 | learning rate: 1.509E-04 | global batch size: 512 | lm loss: 5.315492E+00 | loss scale: 16384.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.474 | TFLOPs: 71.36 | +[default7]: iteration 1110/ 3814 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 5.42 | learning rate: 1.509E-04 | global batch size: 512 | lm loss: 5.329438E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.441 | TFLOPs: 71.33 | +[default7]: iteration 1111/ 3814 | consumed samples: 568832 | consumed tokens: 1164967936 | elapsed time per iteration (s): 5.43 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 5.321434E+00 | loss scale: 16384.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.332 | TFLOPs: 71.25 | +[default7]: iteration 1112/ 3814 | consumed samples: 569344 | consumed tokens: 1166016512 | elapsed time per iteration (s): 5.42 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 5.304989E+00 | loss scale: 16384.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 1113/ 3814 | consumed samples: 569856 | consumed tokens: 1167065088 | elapsed time per iteration (s): 5.42 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 5.317149E+00 | loss scale: 16384.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.482 | TFLOPs: 71.36 | +[default7]: iteration 1114/ 3814 | consumed samples: 570368 | consumed tokens: 1168113664 | elapsed time per iteration (s): 5.43 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 5.290395E+00 | loss scale: 16384.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.213 | TFLOPs: 71.16 | +[default7]: iteration 1115/ 3814 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 5.46 | learning rate: 1.507E-04 | global batch size: 512 | lm loss: 5.291988E+00 | loss scale: 16384.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.778 | TFLOPs: 70.83 | +[default7]: iteration 1116/ 3814 | consumed samples: 571392 | consumed tokens: 1170210816 | elapsed time per iteration (s): 5.45 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 5.304251E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.992 | TFLOPs: 70.99 | +[default7]: iteration 1117/ 3814 | consumed samples: 571904 | consumed tokens: 1171259392 | elapsed time per iteration (s): 5.45 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 5.309916E+00 | loss scale: 16384.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.934 | TFLOPs: 70.95 | +[default7]: iteration 1118/ 3814 | consumed samples: 572416 | consumed tokens: 1172307968 | elapsed time per iteration (s): 5.45 | learning rate: 1.505E-04 | global batch size: 512 | lm loss: 5.312446E+00 | loss scale: 16384.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.914 | TFLOPs: 70.93 | +[default7]: iteration 1119/ 3814 | consumed samples: 572928 | consumed tokens: 1173356544 | elapsed time per iteration (s): 5.45 | learning rate: 1.505E-04 | global batch size: 512 | lm loss: 5.318774E+00 | loss scale: 16384.0 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.961 | TFLOPs: 70.97 | +[default7]: iteration 1120/ 3814 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 5.46 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 5.312321E+00 | loss scale: 16384.0 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.773 | TFLOPs: 70.83 | +[default7]: iteration 1121/ 3814 | consumed samples: 573952 | consumed tokens: 1175453696 | elapsed time per iteration (s): 5.47 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 5.307924E+00 | loss scale: 16384.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.568 | TFLOPs: 70.67 | +[default7]: iteration 1122/ 3814 | consumed samples: 574464 | consumed tokens: 1176502272 | elapsed time per iteration (s): 5.43 | learning rate: 1.503E-04 | global batch size: 512 | lm loss: 5.313918E+00 | loss scale: 16384.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.367 | TFLOPs: 71.28 | +[default7]: iteration 1123/ 3814 | consumed samples: 574976 | consumed tokens: 1177550848 | elapsed time per iteration (s): 5.45 | learning rate: 1.503E-04 | global batch size: 512 | lm loss: 5.286463E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.931 | TFLOPs: 70.95 | +[default7]: iteration 1124/ 3814 | consumed samples: 575488 | consumed tokens: 1178599424 | elapsed time per iteration (s): 5.45 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 5.296447E+00 | loss scale: 16384.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.890 | TFLOPs: 70.92 | +[default7]: iteration 1125/ 3814 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 5.45 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 5.273618E+00 | loss scale: 16384.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default7]: iteration 1126/ 3814 | consumed samples: 576512 | consumed tokens: 1180696576 | elapsed time per iteration (s): 5.46 | learning rate: 1.501E-04 | global batch size: 512 | lm loss: 5.303296E+00 | loss scale: 16384.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.821 | TFLOPs: 70.86 | +[default7]: iteration 1127/ 3814 | consumed samples: 577024 | consumed tokens: 1181745152 | elapsed time per iteration (s): 5.46 | learning rate: 1.501E-04 | global batch size: 512 | lm loss: 5.281589E+00 | loss scale: 16384.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.814 | TFLOPs: 70.86 | +[default7]: iteration 1128/ 3814 | consumed samples: 577536 | consumed tokens: 1182793728 | elapsed time per iteration (s): 5.45 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 5.279524E+00 | loss scale: 16384.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.017 | TFLOPs: 71.01 | +[default7]: iteration 1129/ 3814 | consumed samples: 578048 | consumed tokens: 1183842304 | elapsed time per iteration (s): 5.46 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 5.288982E+00 | loss scale: 16384.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.754 | TFLOPs: 70.81 | +[default7]: iteration 1130/ 3814 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 5.45 | learning rate: 1.499E-04 | global batch size: 512 | lm loss: 5.283530E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.888 | TFLOPs: 70.91 | +[default7]: iteration 1131/ 3814 | consumed samples: 579072 | consumed tokens: 1185939456 | elapsed time per iteration (s): 5.45 | learning rate: 1.499E-04 | global batch size: 512 | lm loss: 5.297367E+00 | loss scale: 16384.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.938 | TFLOPs: 70.95 | +[default7]: iteration 1132/ 3814 | consumed samples: 579584 | consumed tokens: 1186988032 | elapsed time per iteration (s): 5.44 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 5.293746E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.093 | TFLOPs: 71.07 | +[default7]: iteration 1133/ 3814 | consumed samples: 580096 | consumed tokens: 1188036608 | elapsed time per iteration (s): 5.44 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 5.300657E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 1134/ 3814 | consumed samples: 580608 | consumed tokens: 1189085184 | elapsed time per iteration (s): 5.44 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 5.294102E+00 | loss scale: 16384.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.033 | TFLOPs: 71.02 | +[default7]: iteration 1135/ 3814 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 5.44 | learning rate: 1.497E-04 | global batch size: 512 | lm loss: 5.259327E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.087 | TFLOPs: 71.06 | +[default7]: iteration 1136/ 3814 | consumed samples: 581632 | consumed tokens: 1191182336 | elapsed time per iteration (s): 5.42 | learning rate: 1.496E-04 | global batch size: 512 | lm loss: 5.243752E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.431 | TFLOPs: 71.32 | +[default7]: iteration 1137/ 3814 | consumed samples: 582144 | consumed tokens: 1192230912 | elapsed time per iteration (s): 5.42 | learning rate: 1.496E-04 | global batch size: 512 | lm loss: 5.268977E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.542 | TFLOPs: 71.41 | +[default7]: iteration 1138/ 3814 | consumed samples: 582656 | consumed tokens: 1193279488 | elapsed time per iteration (s): 5.41 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 5.272984E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.655 | TFLOPs: 71.49 | +[default7]: iteration 1139/ 3814 | consumed samples: 583168 | consumed tokens: 1194328064 | elapsed time per iteration (s): 5.41 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 5.283629E+00 | loss scale: 16384.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.640 | TFLOPs: 71.48 | +[default7]: iteration 1140/ 3814 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 5.42 | learning rate: 1.494E-04 | global batch size: 512 | lm loss: 5.264614E+00 | loss scale: 16384.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.412 | TFLOPs: 71.31 | +[default7]: iteration 1141/ 3814 | consumed samples: 584192 | consumed tokens: 1196425216 | elapsed time per iteration (s): 5.44 | learning rate: 1.494E-04 | global batch size: 512 | lm loss: 5.296008E+00 | loss scale: 16384.0 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.191 | TFLOPs: 71.14 | +[default7]: iteration 1142/ 3814 | consumed samples: 584704 | consumed tokens: 1197473792 | elapsed time per iteration (s): 5.42 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 5.262261E+00 | loss scale: 16384.0 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.393 | TFLOPs: 71.30 | +[default7]: iteration 1143/ 3814 | consumed samples: 585216 | consumed tokens: 1198522368 | elapsed time per iteration (s): 5.42 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 5.273597E+00 | loss scale: 16384.0 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.435 | TFLOPs: 71.33 | +[default7]: iteration 1144/ 3814 | consumed samples: 585728 | consumed tokens: 1199570944 | elapsed time per iteration (s): 5.42 | learning rate: 1.492E-04 | global batch size: 512 | lm loss: 5.248518E+00 | loss scale: 16384.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.412 | TFLOPs: 71.31 | +[default7]: iteration 1145/ 3814 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 5.43 | learning rate: 1.492E-04 | global batch size: 512 | lm loss: 5.260197E+00 | loss scale: 16384.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.276 | TFLOPs: 71.21 | +[default7]: iteration 1146/ 3814 | consumed samples: 586752 | consumed tokens: 1201668096 | elapsed time per iteration (s): 5.43 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 5.294655E+00 | loss scale: 16384.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.242 | TFLOPs: 71.18 | +[default7]: iteration 1147/ 3814 | consumed samples: 587264 | consumed tokens: 1202716672 | elapsed time per iteration (s): 5.43 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 5.251454E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.250 | TFLOPs: 71.19 | +[default7]: iteration 1148/ 3814 | consumed samples: 587776 | consumed tokens: 1203765248 | elapsed time per iteration (s): 5.43 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 5.251591E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 1149/ 3814 | consumed samples: 588288 | consumed tokens: 1204813824 | elapsed time per iteration (s): 5.43 | learning rate: 1.490E-04 | global batch size: 512 | lm loss: 5.263389E+00 | loss scale: 16384.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.322 | TFLOPs: 71.24 | +[default7]: iteration 1150/ 3814 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 5.43 | learning rate: 1.489E-04 | global batch size: 512 | lm loss: 5.257193E+00 | loss scale: 16384.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.265 | TFLOPs: 71.20 | +[default7]: iteration 1151/ 3814 | consumed samples: 589312 | consumed tokens: 1206910976 | elapsed time per iteration (s): 5.42 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 5.249403E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.485 | TFLOPs: 71.37 | +[default7]: iteration 1152/ 3814 | consumed samples: 589824 | consumed tokens: 1207959552 | elapsed time per iteration (s): 5.43 | learning rate: 1.488E-04 | global batch size: 512 | lm loss: 5.289869E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.221 | TFLOPs: 71.17 | +[default7]: iteration 1153/ 3814 | consumed samples: 590336 | consumed tokens: 1209008128 | elapsed time per iteration (s): 5.45 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 5.250827E+00 | loss scale: 16384.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.029 | TFLOPs: 71.02 | +[default7]: iteration 1154/ 3814 | consumed samples: 590848 | consumed tokens: 1210056704 | elapsed time per iteration (s): 5.43 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 5.251514E+00 | loss scale: 16384.0 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 1155/ 3814 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 5.45 | learning rate: 1.486E-04 | global batch size: 512 | lm loss: 5.284188E+00 | loss scale: 16384.0 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 1156/ 3814 | consumed samples: 591872 | consumed tokens: 1212153856 | elapsed time per iteration (s): 5.45 | learning rate: 1.486E-04 | global batch size: 512 | lm loss: 5.289280E+00 | loss scale: 16384.0 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.027 | TFLOPs: 71.02 | +[default7]: iteration 1157/ 3814 | consumed samples: 592384 | consumed tokens: 1213202432 | elapsed time per iteration (s): 5.43 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 5.291037E+00 | loss scale: 16384.0 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.251 | TFLOPs: 71.19 | +[default7]: iteration 1158/ 3814 | consumed samples: 592896 | consumed tokens: 1214251008 | elapsed time per iteration (s): 5.45 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 5.241114E+00 | loss scale: 16384.0 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.019 | TFLOPs: 71.01 | +[default7]: iteration 1159/ 3814 | consumed samples: 593408 | consumed tokens: 1215299584 | elapsed time per iteration (s): 5.42 | learning rate: 1.484E-04 | global batch size: 512 | lm loss: 5.267516E+00 | loss scale: 16384.0 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.398 | TFLOPs: 71.30 | +[default7]: iteration 1160/ 3814 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 5.44 | learning rate: 1.484E-04 | global batch size: 512 | lm loss: 5.250406E+00 | loss scale: 16384.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.184 | TFLOPs: 71.14 | +[default7]: iteration 1161/ 3814 | consumed samples: 594432 | consumed tokens: 1217396736 | elapsed time per iteration (s): 5.47 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 5.281292E+00 | loss scale: 16384.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.642 | TFLOPs: 70.73 | +[default7]: iteration 1162/ 3814 | consumed samples: 594944 | consumed tokens: 1218445312 | elapsed time per iteration (s): 5.43 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 5.256574E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.287 | TFLOPs: 71.22 | +[default7]: iteration 1163/ 3814 | consumed samples: 595456 | consumed tokens: 1219493888 | elapsed time per iteration (s): 5.44 | learning rate: 1.482E-04 | global batch size: 512 | lm loss: 5.279604E+00 | loss scale: 16384.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.167 | TFLOPs: 71.13 | +[default7]: iteration 1164/ 3814 | consumed samples: 595968 | consumed tokens: 1220542464 | elapsed time per iteration (s): 5.44 | learning rate: 1.482E-04 | global batch size: 512 | lm loss: 5.250254E+00 | loss scale: 16384.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.153 | TFLOPs: 71.11 | +[default7]: iteration 1165/ 3814 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 5.44 | learning rate: 1.481E-04 | global batch size: 512 | lm loss: 5.229702E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.071 | TFLOPs: 71.05 | +[default7]: iteration 1166/ 3814 | consumed samples: 596992 | consumed tokens: 1222639616 | elapsed time per iteration (s): 5.45 | learning rate: 1.481E-04 | global batch size: 512 | lm loss: 5.226123E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.920 | TFLOPs: 70.94 | +[default7]: iteration 1167/ 3814 | consumed samples: 597504 | consumed tokens: 1223688192 | elapsed time per iteration (s): 5.41 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 5.264893E+00 | loss scale: 16384.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.571 | TFLOPs: 71.43 | +[default7]: iteration 1168/ 3814 | consumed samples: 598016 | consumed tokens: 1224736768 | elapsed time per iteration (s): 5.43 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 5.245628E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.291 | TFLOPs: 71.22 | +[default7]: iteration 1169/ 3814 | consumed samples: 598528 | consumed tokens: 1225785344 | elapsed time per iteration (s): 5.44 | learning rate: 1.479E-04 | global batch size: 512 | lm loss: 5.232374E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.170 | TFLOPs: 71.13 | +[default7]: iteration 1170/ 3814 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 5.41 | learning rate: 1.479E-04 | global batch size: 512 | lm loss: 5.233772E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.586 | TFLOPs: 71.44 | +[default7]: iteration 1171/ 3814 | consumed samples: 599552 | consumed tokens: 1227882496 | elapsed time per iteration (s): 5.43 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 5.250229E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.366 | TFLOPs: 71.28 | +[default7]: iteration 1172/ 3814 | consumed samples: 600064 | consumed tokens: 1228931072 | elapsed time per iteration (s): 5.44 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 5.235855E+00 | loss scale: 16384.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.194 | TFLOPs: 71.15 | +[default7]: iteration 1173/ 3814 | consumed samples: 600576 | consumed tokens: 1229979648 | elapsed time per iteration (s): 5.45 | learning rate: 1.477E-04 | global batch size: 512 | lm loss: 5.260773E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 1174/ 3814 | consumed samples: 601088 | consumed tokens: 1231028224 | elapsed time per iteration (s): 5.46 | learning rate: 1.477E-04 | global batch size: 512 | lm loss: 5.228446E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.825 | TFLOPs: 70.87 | +[default7]: iteration 1175/ 3814 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 5.43 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 5.221279E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.229 | TFLOPs: 71.17 | +[default7]: iteration 1176/ 3814 | consumed samples: 602112 | consumed tokens: 1233125376 | elapsed time per iteration (s): 5.45 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 5.195339E+00 | loss scale: 16384.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.940 | TFLOPs: 70.95 | +[default7]: iteration 1177/ 3814 | consumed samples: 602624 | consumed tokens: 1234173952 | elapsed time per iteration (s): 5.44 | learning rate: 1.475E-04 | global batch size: 512 | lm loss: 5.241716E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 1178/ 3814 | consumed samples: 603136 | consumed tokens: 1235222528 | elapsed time per iteration (s): 5.46 | learning rate: 1.475E-04 | global batch size: 512 | lm loss: 5.207477E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.707 | TFLOPs: 70.78 | +[default7]: iteration 1179/ 3814 | consumed samples: 603648 | consumed tokens: 1236271104 | elapsed time per iteration (s): 5.43 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 5.239269E+00 | loss scale: 16384.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.217 | TFLOPs: 71.16 | +[default7]: iteration 1180/ 3814 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 5.46 | learning rate: 1.473E-04 | global batch size: 512 | lm loss: 5.227386E+00 | loss scale: 16384.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.748 | TFLOPs: 70.81 | +[default7]: iteration 1181/ 3814 | consumed samples: 604672 | consumed tokens: 1238368256 | elapsed time per iteration (s): 5.46 | learning rate: 1.473E-04 | global batch size: 512 | lm loss: 5.213384E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.817 | TFLOPs: 70.86 | +[default7]: iteration 1182/ 3814 | consumed samples: 605184 | consumed tokens: 1239416832 | elapsed time per iteration (s): 5.45 | learning rate: 1.472E-04 | global batch size: 512 | lm loss: 5.227392E+00 | loss scale: 16384.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.005 | TFLOPs: 71.00 | +[default7]: iteration 1183/ 3814 | consumed samples: 605696 | consumed tokens: 1240465408 | elapsed time per iteration (s): 5.45 | learning rate: 1.472E-04 | global batch size: 512 | lm loss: 5.204405E+00 | loss scale: 16384.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.019 | TFLOPs: 71.01 | +[default7]: iteration 1184/ 3814 | consumed samples: 606208 | consumed tokens: 1241513984 | elapsed time per iteration (s): 5.45 | learning rate: 1.471E-04 | global batch size: 512 | lm loss: 5.226123E+00 | loss scale: 16384.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.883 | TFLOPs: 70.91 | +[default7]: iteration 1185/ 3814 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 5.45 | learning rate: 1.471E-04 | global batch size: 512 | lm loss: 5.191891E+00 | loss scale: 16384.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.953 | TFLOPs: 70.96 | +[default7]: iteration 1186/ 3814 | consumed samples: 607232 | consumed tokens: 1243611136 | elapsed time per iteration (s): 5.46 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 5.243190E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.714 | TFLOPs: 70.78 | +[default7]: iteration 1187/ 3814 | consumed samples: 607744 | consumed tokens: 1244659712 | elapsed time per iteration (s): 5.45 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 5.221232E+00 | loss scale: 16384.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.017 | TFLOPs: 71.01 | +[default7]: iteration 1188/ 3814 | consumed samples: 608256 | consumed tokens: 1245708288 | elapsed time per iteration (s): 5.45 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 5.229585E+00 | loss scale: 16384.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.956 | TFLOPs: 70.97 | +[default7]: iteration 1189/ 3814 | consumed samples: 608768 | consumed tokens: 1246756864 | elapsed time per iteration (s): 5.45 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 5.232666E+00 | loss scale: 16384.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.931 | TFLOPs: 70.95 | +[default7]: iteration 1190/ 3814 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 5.44 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 5.243953E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.168 | TFLOPs: 71.13 | +[default7]: iteration 1191/ 3814 | consumed samples: 609792 | consumed tokens: 1248854016 | elapsed time per iteration (s): 5.44 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 5.234194E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.127 | TFLOPs: 71.09 | +[default7]: iteration 1192/ 3814 | consumed samples: 610304 | consumed tokens: 1249902592 | elapsed time per iteration (s): 5.44 | learning rate: 1.467E-04 | global batch size: 512 | lm loss: 5.205329E+00 | loss scale: 16384.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 1193/ 3814 | consumed samples: 610816 | consumed tokens: 1250951168 | elapsed time per iteration (s): 5.43 | learning rate: 1.467E-04 | global batch size: 512 | lm loss: 5.232162E+00 | loss scale: 16384.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.295 | TFLOPs: 71.22 | +[default7]: iteration 1194/ 3814 | consumed samples: 611328 | consumed tokens: 1251999744 | elapsed time per iteration (s): 5.45 | learning rate: 1.466E-04 | global batch size: 512 | lm loss: 5.211723E+00 | loss scale: 16384.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.008 | TFLOPs: 71.01 | +[default7]: iteration 1195/ 3814 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 5.44 | learning rate: 1.466E-04 | global batch size: 512 | lm loss: 5.199079E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 1196/ 3814 | consumed samples: 612352 | consumed tokens: 1254096896 | elapsed time per iteration (s): 5.45 | learning rate: 1.465E-04 | global batch size: 512 | lm loss: 5.189308E+00 | loss scale: 16384.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 1197/ 3814 | consumed samples: 612864 | consumed tokens: 1255145472 | elapsed time per iteration (s): 5.44 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 5.189880E+00 | loss scale: 16384.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.081 | TFLOPs: 71.06 | +[default7]: iteration 1198/ 3814 | consumed samples: 613376 | consumed tokens: 1256194048 | elapsed time per iteration (s): 5.45 | learning rate: 1.464E-04 | global batch size: 512 | lm loss: 5.242367E+00 | loss scale: 16384.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1199/ 3814 | consumed samples: 613888 | consumed tokens: 1257242624 | elapsed time per iteration (s): 5.45 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 5.186174E+00 | loss scale: 16384.0 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 1200/ 3814 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 5.43 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 5.204652E+00 | loss scale: 16384.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.208 | TFLOPs: 71.16 | +[default7]: iteration 1201/ 3814 | consumed samples: 614912 | consumed tokens: 1259339776 | elapsed time per iteration (s): 5.44 | learning rate: 1.462E-04 | global batch size: 512 | lm loss: 5.190827E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 1202/ 3814 | consumed samples: 615424 | consumed tokens: 1260388352 | elapsed time per iteration (s): 5.44 | learning rate: 1.462E-04 | global batch size: 512 | lm loss: 5.202442E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 1203/ 3814 | consumed samples: 615936 | consumed tokens: 1261436928 | elapsed time per iteration (s): 5.45 | learning rate: 1.461E-04 | global batch size: 512 | lm loss: 5.208144E+00 | loss scale: 16384.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.020 | TFLOPs: 71.01 | +[default7]: iteration 1204/ 3814 | consumed samples: 616448 | consumed tokens: 1262485504 | elapsed time per iteration (s): 5.43 | learning rate: 1.461E-04 | global batch size: 512 | lm loss: 5.212023E+00 | loss scale: 16384.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.299 | TFLOPs: 71.22 | +[default7]: iteration 1205/ 3814 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 5.46 | learning rate: 1.460E-04 | global batch size: 512 | lm loss: 5.178919E+00 | loss scale: 16384.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.711 | TFLOPs: 70.78 | +[default7]: iteration 1206/ 3814 | consumed samples: 617472 | consumed tokens: 1264582656 | elapsed time per iteration (s): 5.47 | learning rate: 1.460E-04 | global batch size: 512 | lm loss: 5.220608E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.589 | TFLOPs: 70.69 | +[default7]: iteration 1207/ 3814 | consumed samples: 617984 | consumed tokens: 1265631232 | elapsed time per iteration (s): 5.45 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 5.193197E+00 | loss scale: 16384.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.938 | TFLOPs: 70.95 | +[default7]: iteration 1208/ 3814 | consumed samples: 618496 | consumed tokens: 1266679808 | elapsed time per iteration (s): 5.45 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 5.191469E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.964 | TFLOPs: 70.97 | +[default7]: iteration 1209/ 3814 | consumed samples: 619008 | consumed tokens: 1267728384 | elapsed time per iteration (s): 5.44 | learning rate: 1.458E-04 | global batch size: 512 | lm loss: 5.191110E+00 | loss scale: 16384.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.086 | TFLOPs: 71.06 | +[default7]: iteration 1210/ 3814 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 5.44 | learning rate: 1.458E-04 | global batch size: 512 | lm loss: 5.190342E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.178 | TFLOPs: 71.13 | +[default7]: iteration 1211/ 3814 | consumed samples: 620032 | consumed tokens: 1269825536 | elapsed time per iteration (s): 5.46 | learning rate: 1.457E-04 | global batch size: 512 | lm loss: 5.166881E+00 | loss scale: 16384.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.852 | TFLOPs: 70.89 | +[default7]: iteration 1212/ 3814 | consumed samples: 620544 | consumed tokens: 1270874112 | elapsed time per iteration (s): 5.45 | learning rate: 1.456E-04 | global batch size: 512 | lm loss: 5.177671E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.973 | TFLOPs: 70.98 | +[default7]: iteration 1213/ 3814 | consumed samples: 621056 | consumed tokens: 1271922688 | elapsed time per iteration (s): 5.46 | learning rate: 1.456E-04 | global batch size: 512 | lm loss: 5.181979E+00 | loss scale: 16384.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.815 | TFLOPs: 70.86 | +[default7]: iteration 1214/ 3814 | consumed samples: 621568 | consumed tokens: 1272971264 | elapsed time per iteration (s): 5.45 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 5.163381E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 1215/ 3814 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 5.46 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 5.179031E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.791 | TFLOPs: 70.84 | +[default7]: iteration 1216/ 3814 | consumed samples: 622592 | consumed tokens: 1275068416 | elapsed time per iteration (s): 5.47 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 5.200696E+00 | loss scale: 16384.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.642 | TFLOPs: 70.73 | +[default7]: iteration 1217/ 3814 | consumed samples: 623104 | consumed tokens: 1276116992 | elapsed time per iteration (s): 5.44 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 5.163561E+00 | loss scale: 16384.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.176 | TFLOPs: 71.13 | +[default7]: iteration 1218/ 3814 | consumed samples: 623616 | consumed tokens: 1277165568 | elapsed time per iteration (s): 5.43 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 5.188644E+00 | loss scale: 16384.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.217 | TFLOPs: 71.16 | +[default7]: iteration 1219/ 3814 | consumed samples: 624128 | consumed tokens: 1278214144 | elapsed time per iteration (s): 5.44 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 5.184196E+00 | loss scale: 16384.0 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.046 | TFLOPs: 71.03 | +[default7]: iteration 1220/ 3814 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 5.43 | learning rate: 1.452E-04 | global batch size: 512 | lm loss: 5.190087E+00 | loss scale: 16384.0 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.235 | TFLOPs: 71.18 | +[default7]: iteration 1221/ 3814 | consumed samples: 625152 | consumed tokens: 1280311296 | elapsed time per iteration (s): 5.45 | learning rate: 1.452E-04 | global batch size: 512 | lm loss: 5.211778E+00 | loss scale: 16384.0 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.89 | +[default7]: iteration 1222/ 3814 | consumed samples: 625664 | consumed tokens: 1281359872 | elapsed time per iteration (s): 5.45 | learning rate: 1.451E-04 | global batch size: 512 | lm loss: 5.168024E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 1223/ 3814 | consumed samples: 626176 | consumed tokens: 1282408448 | elapsed time per iteration (s): 5.47 | learning rate: 1.450E-04 | global batch size: 512 | lm loss: 5.194174E+00 | loss scale: 16384.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.681 | TFLOPs: 70.76 | +[default7]: iteration 1224/ 3814 | consumed samples: 626688 | consumed tokens: 1283457024 | elapsed time per iteration (s): 5.46 | learning rate: 1.450E-04 | global batch size: 512 | lm loss: 5.204954E+00 | loss scale: 16384.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.825 | TFLOPs: 70.87 | +[default7]: iteration 1225/ 3814 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 5.45 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 5.172234E+00 | loss scale: 16384.0 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.904 | TFLOPs: 70.93 | +[default7]: iteration 1226/ 3814 | consumed samples: 627712 | consumed tokens: 1285554176 | elapsed time per iteration (s): 5.45 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 5.158056E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.887 | TFLOPs: 70.91 | +[default7]: iteration 1227/ 3814 | consumed samples: 628224 | consumed tokens: 1286602752 | elapsed time per iteration (s): 5.44 | learning rate: 1.448E-04 | global batch size: 512 | lm loss: 5.160283E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.05 | +[default7]: iteration 1228/ 3814 | consumed samples: 628736 | consumed tokens: 1287651328 | elapsed time per iteration (s): 5.45 | learning rate: 1.448E-04 | global batch size: 512 | lm loss: 5.165005E+00 | loss scale: 16384.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.880 | TFLOPs: 70.91 | +[default7]: iteration 1229/ 3814 | consumed samples: 629248 | consumed tokens: 1288699904 | elapsed time per iteration (s): 5.46 | learning rate: 1.447E-04 | global batch size: 512 | lm loss: 5.177287E+00 | loss scale: 16384.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.705 | TFLOPs: 70.78 | +[default7]: iteration 1230/ 3814 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 5.45 | learning rate: 1.447E-04 | global batch size: 512 | lm loss: 5.176581E+00 | loss scale: 16384.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default7]: iteration 1231/ 3814 | consumed samples: 630272 | consumed tokens: 1290797056 | elapsed time per iteration (s): 5.44 | learning rate: 1.446E-04 | global batch size: 512 | lm loss: 5.155458E+00 | loss scale: 16384.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.080 | TFLOPs: 71.06 | +[default7]: iteration 1232/ 3814 | consumed samples: 630784 | consumed tokens: 1291845632 | elapsed time per iteration (s): 5.47 | learning rate: 1.445E-04 | global batch size: 512 | lm loss: 5.156312E+00 | loss scale: 16384.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.680 | TFLOPs: 70.76 | +[default7]: iteration 1233/ 3814 | consumed samples: 631296 | consumed tokens: 1292894208 | elapsed time per iteration (s): 5.45 | learning rate: 1.445E-04 | global batch size: 512 | lm loss: 5.171694E+00 | loss scale: 16384.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.894 | TFLOPs: 70.92 | +[default7]: iteration 1234/ 3814 | consumed samples: 631808 | consumed tokens: 1293942784 | elapsed time per iteration (s): 5.45 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 5.142469E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.864 | TFLOPs: 70.90 | +[default7]: iteration 1235/ 3814 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 5.46 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 5.177038E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.831 | TFLOPs: 70.87 | +[default7]: iteration 1236/ 3814 | consumed samples: 632832 | consumed tokens: 1296039936 | elapsed time per iteration (s): 5.46 | learning rate: 1.443E-04 | global batch size: 512 | lm loss: 5.163796E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.824 | TFLOPs: 70.87 | +[default7]: iteration 1237/ 3814 | consumed samples: 633344 | consumed tokens: 1297088512 | elapsed time per iteration (s): 5.46 | learning rate: 1.443E-04 | global batch size: 512 | lm loss: 5.155391E+00 | loss scale: 16384.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.693 | TFLOPs: 70.77 | +[default7]: iteration 1238/ 3814 | consumed samples: 633856 | consumed tokens: 1298137088 | elapsed time per iteration (s): 5.45 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 5.155089E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.888 | TFLOPs: 70.91 | +[default7]: iteration 1239/ 3814 | consumed samples: 634368 | consumed tokens: 1299185664 | elapsed time per iteration (s): 5.45 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 5.147970E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.863 | TFLOPs: 70.90 | +[default7]: iteration 1240/ 3814 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 5.45 | learning rate: 1.441E-04 | global batch size: 512 | lm loss: 5.171821E+00 | loss scale: 16384.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.870 | TFLOPs: 70.90 | +[default7]: iteration 1241/ 3814 | consumed samples: 635392 | consumed tokens: 1301282816 | elapsed time per iteration (s): 5.46 | learning rate: 1.441E-04 | global batch size: 512 | lm loss: 5.129807E+00 | loss scale: 16384.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.779 | TFLOPs: 70.83 | +[default7]: iteration 1242/ 3814 | consumed samples: 635904 | consumed tokens: 1302331392 | elapsed time per iteration (s): 5.46 | learning rate: 1.440E-04 | global batch size: 512 | lm loss: 5.173749E+00 | loss scale: 16384.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.781 | TFLOPs: 70.83 | +[default7]: iteration 1243/ 3814 | consumed samples: 636416 | consumed tokens: 1303379968 | elapsed time per iteration (s): 5.43 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 5.166831E+00 | loss scale: 16384.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.229 | TFLOPs: 71.17 | +[default7]: iteration 1244/ 3814 | consumed samples: 636928 | consumed tokens: 1304428544 | elapsed time per iteration (s): 5.44 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 5.165309E+00 | loss scale: 16384.0 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.059 | TFLOPs: 71.04 | +[default7]: iteration 1245/ 3814 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 5.43 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 5.176841E+00 | loss scale: 16384.0 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.220 | TFLOPs: 71.17 | +[default7]: iteration 1246/ 3814 | consumed samples: 637952 | consumed tokens: 1306525696 | elapsed time per iteration (s): 5.45 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 5.200169E+00 | loss scale: 16384.0 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.996 | TFLOPs: 71.00 | +[default7]: iteration 1247/ 3814 | consumed samples: 638464 | consumed tokens: 1307574272 | elapsed time per iteration (s): 5.44 | learning rate: 1.437E-04 | global batch size: 512 | lm loss: 5.144171E+00 | loss scale: 16384.0 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.112 | TFLOPs: 71.08 | +[default7]: iteration 1248/ 3814 | consumed samples: 638976 | consumed tokens: 1308622848 | elapsed time per iteration (s): 5.44 | learning rate: 1.437E-04 | global batch size: 512 | lm loss: 5.168515E+00 | loss scale: 16384.0 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.076 | TFLOPs: 71.06 | +[default7]: iteration 1249/ 3814 | consumed samples: 639488 | consumed tokens: 1309671424 | elapsed time per iteration (s): 5.45 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 5.176775E+00 | loss scale: 16384.0 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.981 | TFLOPs: 70.98 | +[default0]:saving checkpoint at iteration 1250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 13:13:06,476] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1250 is begin to save! +[default0]:[2023-02-16 13:13:06,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_00-model_states.pt... +[default7]: iteration 1250/ 3814 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 5.43 | learning rate: 1.435E-04 | global batch size: 512 | lm loss: 5.138266E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.372 | TFLOPs: 71.28 | +[default1]:[2023-02-16 13:13:06,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:06,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,640] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:06,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:06,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,697] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:06,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:06,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,756] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:06,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,817] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:06,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:06,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:06,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:06,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:06,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:06,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:06,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:06,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:06,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,075] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,107] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,129] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,427] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_00-model_states.pt. +[default1]:[2023-02-16 13:13:07,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,532] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,489] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,603] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,719] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:07,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:07,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,922] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:07,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:07,983] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:07,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:07,981] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:08,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,036] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:08,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:08,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:08,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:08,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,203] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:08,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,204] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:08,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,270] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:08,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,264] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,328] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:08,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:08,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,376] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 13:13:08,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,437] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 13:13:08,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 13:13:08,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 13:13:08,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_01-model_states.pt. +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:13:08,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:08,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,550] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 13:13:08,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 13:13:08,552] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt +[default0]:[2023-02-16 13:13:08,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 13:13:08,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:13:08,550] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 13:13:08,550] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 13:13:08,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:13:08,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:13:09,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,065] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,082] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,079] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,079] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,144] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,104] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,163] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,111] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,201] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,182] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,156] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,224] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,204] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,191] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,207] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,238] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,198] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,195] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,262] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,243] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,259] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,184] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,217] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,212] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,231] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,244] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,232] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,253] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,230] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,280] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,263] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,293] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,271] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,253] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,265] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,251] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,224] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,241] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,244] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,255] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,264] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,283] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,309] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,342] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,295] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,290] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,320] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,332] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,303] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 13:13:09,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:13:09,294] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:13:09,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 13:13:09,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:13:09,355] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:13:09,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,292] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,347] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,294] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,375] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,375] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,355] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 13:13:09,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,350] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,389] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 13:13:09,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:13:09,362] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:13:09,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 13:13:09,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:13:09,450] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:13:09,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,368] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 13:13:09,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:13:09,402] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:13:09,402] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 13:13:09,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:13:09,472] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:13:09,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 13:13:09,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:13:09,750] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:13:09,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]: successfully saved checkpoint at iteration 1250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 3294.01 +[default4]:[2023-02-16 13:13:09,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:13:09,760] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:13:09,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]: iteration 1251/ 3814 | consumed samples: 640512 | consumed tokens: 1311768576 | elapsed time per iteration (s): 8.76 | learning rate: 1.435E-04 | global batch size: 512 | lm loss: 5.154901E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 58.470 | TFLOPs: 44.16 | +[default7]: iteration 1252/ 3814 | consumed samples: 641024 | consumed tokens: 1312817152 | elapsed time per iteration (s): 5.45 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 5.148184E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.000 | TFLOPs: 71.00 | +[default7]: iteration 1253/ 3814 | consumed samples: 641536 | consumed tokens: 1313865728 | elapsed time per iteration (s): 5.46 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 5.158904E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.846 | TFLOPs: 70.88 | +[default7]: iteration 1254/ 3814 | consumed samples: 642048 | consumed tokens: 1314914304 | elapsed time per iteration (s): 5.44 | learning rate: 1.433E-04 | global batch size: 512 | lm loss: 5.185637E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.137 | TFLOPs: 71.10 | +[default7]: iteration 1255/ 3814 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 5.43 | learning rate: 1.433E-04 | global batch size: 512 | lm loss: 5.135108E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.288 | TFLOPs: 71.22 | +[default7]: iteration 1256/ 3814 | consumed samples: 643072 | consumed tokens: 1317011456 | elapsed time per iteration (s): 5.44 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 5.119180E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 1257/ 3814 | consumed samples: 643584 | consumed tokens: 1318060032 | elapsed time per iteration (s): 5.44 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 5.159031E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.06 | +[default7]: iteration 1258/ 3814 | consumed samples: 644096 | consumed tokens: 1319108608 | elapsed time per iteration (s): 5.46 | learning rate: 1.431E-04 | global batch size: 512 | lm loss: 5.137304E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.846 | TFLOPs: 70.88 | +[default7]: iteration 1259/ 3814 | consumed samples: 644608 | consumed tokens: 1320157184 | elapsed time per iteration (s): 5.45 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 5.144072E+00 | loss scale: 16384.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.975 | TFLOPs: 70.98 | +[default7]: iteration 1260/ 3814 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 5.44 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 5.110245E+00 | loss scale: 16384.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.042 | TFLOPs: 71.03 | +[default7]: iteration 1261/ 3814 | consumed samples: 645632 | consumed tokens: 1322254336 | elapsed time per iteration (s): 5.44 | learning rate: 1.429E-04 | global batch size: 512 | lm loss: 5.148909E+00 | loss scale: 16384.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.089 | TFLOPs: 71.07 | +[default7]: iteration 1262/ 3814 | consumed samples: 646144 | consumed tokens: 1323302912 | elapsed time per iteration (s): 5.44 | learning rate: 1.429E-04 | global batch size: 512 | lm loss: 5.115244E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.086 | TFLOPs: 71.06 | +[default7]: iteration 1263/ 3814 | consumed samples: 646656 | consumed tokens: 1324351488 | elapsed time per iteration (s): 5.45 | learning rate: 1.428E-04 | global batch size: 512 | lm loss: 5.134251E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.976 | TFLOPs: 70.98 | +[default7]: iteration 1264/ 3814 | consumed samples: 647168 | consumed tokens: 1325400064 | elapsed time per iteration (s): 5.44 | learning rate: 1.428E-04 | global batch size: 512 | lm loss: 5.138765E+00 | loss scale: 16384.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.163 | TFLOPs: 71.12 | +[default7]: iteration 1265/ 3814 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 5.44 | learning rate: 1.427E-04 | global batch size: 512 | lm loss: 5.149476E+00 | loss scale: 16384.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.173 | TFLOPs: 71.13 | +[default7]: iteration 1266/ 3814 | consumed samples: 648192 | consumed tokens: 1327497216 | elapsed time per iteration (s): 5.44 | learning rate: 1.426E-04 | global batch size: 512 | lm loss: 5.118943E+00 | loss scale: 16384.0 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.187 | TFLOPs: 71.14 | +[default7]: iteration 1267/ 3814 | consumed samples: 648704 | consumed tokens: 1328545792 | elapsed time per iteration (s): 5.44 | learning rate: 1.426E-04 | global batch size: 512 | lm loss: 5.130376E+00 | loss scale: 16384.0 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.200 | TFLOPs: 71.15 | +[default7]: iteration 1268/ 3814 | consumed samples: 649216 | consumed tokens: 1329594368 | elapsed time per iteration (s): 5.44 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 5.125608E+00 | loss scale: 16384.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.117 | TFLOPs: 71.09 | +[default7]: iteration 1269/ 3814 | consumed samples: 649728 | consumed tokens: 1330642944 | elapsed time per iteration (s): 5.44 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 5.135394E+00 | loss scale: 16384.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.059 | TFLOPs: 71.04 | +[default7]: iteration 1270/ 3814 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 5.45 | learning rate: 1.424E-04 | global batch size: 512 | lm loss: 5.125323E+00 | loss scale: 16384.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.960 | TFLOPs: 70.97 | +[default7]: iteration 1271/ 3814 | consumed samples: 650752 | consumed tokens: 1332740096 | elapsed time per iteration (s): 5.45 | learning rate: 1.424E-04 | global batch size: 512 | lm loss: 5.115061E+00 | loss scale: 16384.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.012 | TFLOPs: 71.01 | +[default7]: iteration 1272/ 3814 | consumed samples: 651264 | consumed tokens: 1333788672 | elapsed time per iteration (s): 5.44 | learning rate: 1.423E-04 | global batch size: 512 | lm loss: 5.143329E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.139 | TFLOPs: 71.10 | +[default7]: iteration 1273/ 3814 | consumed samples: 651776 | consumed tokens: 1334837248 | elapsed time per iteration (s): 5.44 | learning rate: 1.422E-04 | global batch size: 512 | lm loss: 5.123467E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.159 | TFLOPs: 71.12 | +[default7]: iteration 1274/ 3814 | consumed samples: 652288 | consumed tokens: 1335885824 | elapsed time per iteration (s): 5.42 | learning rate: 1.422E-04 | global batch size: 512 | lm loss: 5.123509E+00 | loss scale: 16384.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.382 | TFLOPs: 71.29 | +[default7]: iteration 1275/ 3814 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 5.41 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 5.120094E+00 | loss scale: 16384.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.566 | TFLOPs: 71.43 | +[default7]: iteration 1276/ 3814 | consumed samples: 653312 | consumed tokens: 1337982976 | elapsed time per iteration (s): 5.43 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 5.151131E+00 | loss scale: 16384.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.372 | TFLOPs: 71.28 | +[default7]: iteration 1277/ 3814 | consumed samples: 653824 | consumed tokens: 1339031552 | elapsed time per iteration (s): 5.44 | learning rate: 1.420E-04 | global batch size: 512 | lm loss: 5.116943E+00 | loss scale: 16384.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.096 | TFLOPs: 71.07 | +[default7]: iteration 1278/ 3814 | consumed samples: 654336 | consumed tokens: 1340080128 | elapsed time per iteration (s): 5.45 | learning rate: 1.420E-04 | global batch size: 512 | lm loss: 5.109638E+00 | loss scale: 16384.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1279/ 3814 | consumed samples: 654848 | consumed tokens: 1341128704 | elapsed time per iteration (s): 5.43 | learning rate: 1.419E-04 | global batch size: 512 | lm loss: 5.115725E+00 | loss scale: 16384.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.274 | TFLOPs: 71.21 | +[default7]: iteration 1280/ 3814 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 5.44 | learning rate: 1.418E-04 | global batch size: 512 | lm loss: 5.115769E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.050 | TFLOPs: 71.04 | +[default7]: iteration 1281/ 3814 | consumed samples: 655872 | consumed tokens: 1343225856 | elapsed time per iteration (s): 5.44 | learning rate: 1.418E-04 | global batch size: 512 | lm loss: 5.143086E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.129 | TFLOPs: 71.10 | +[default7]: iteration 1282/ 3814 | consumed samples: 656384 | consumed tokens: 1344274432 | elapsed time per iteration (s): 5.44 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 5.151713E+00 | loss scale: 16384.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 1283/ 3814 | consumed samples: 656896 | consumed tokens: 1345323008 | elapsed time per iteration (s): 5.44 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 5.102894E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.193 | TFLOPs: 71.15 | +[default7]: iteration 1284/ 3814 | consumed samples: 657408 | consumed tokens: 1346371584 | elapsed time per iteration (s): 5.44 | learning rate: 1.416E-04 | global batch size: 512 | lm loss: 5.131774E+00 | loss scale: 16384.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.040 | TFLOPs: 71.03 | +[default7]: iteration 1285/ 3814 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 5.46 | learning rate: 1.416E-04 | global batch size: 512 | lm loss: 5.117553E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.850 | TFLOPs: 70.89 | +[default7]: iteration 1286/ 3814 | consumed samples: 658432 | consumed tokens: 1348468736 | elapsed time per iteration (s): 5.44 | learning rate: 1.415E-04 | global batch size: 512 | lm loss: 5.113382E+00 | loss scale: 16384.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.146 | TFLOPs: 71.11 | +[default7]: iteration 1287/ 3814 | consumed samples: 658944 | consumed tokens: 1349517312 | elapsed time per iteration (s): 5.47 | learning rate: 1.414E-04 | global batch size: 512 | lm loss: 5.098380E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.601 | TFLOPs: 70.70 | +[default7]: iteration 1288/ 3814 | consumed samples: 659456 | consumed tokens: 1350565888 | elapsed time per iteration (s): 5.43 | learning rate: 1.414E-04 | global batch size: 512 | lm loss: 5.081942E+00 | loss scale: 16384.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.255 | TFLOPs: 71.19 | +[default7]: iteration 1289/ 3814 | consumed samples: 659968 | consumed tokens: 1351614464 | elapsed time per iteration (s): 5.44 | learning rate: 1.413E-04 | global batch size: 512 | lm loss: 5.102902E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.179 | TFLOPs: 71.13 | +[default7]: iteration 1290/ 3814 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 5.44 | learning rate: 1.413E-04 | global batch size: 512 | lm loss: 5.087665E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.190 | TFLOPs: 71.14 | +[default7]: iteration 1291/ 3814 | consumed samples: 660992 | consumed tokens: 1353711616 | elapsed time per iteration (s): 5.45 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 5.077647E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.028 | TFLOPs: 71.02 | +[default7]: iteration 1292/ 3814 | consumed samples: 661504 | consumed tokens: 1354760192 | elapsed time per iteration (s): 5.44 | learning rate: 1.412E-04 | global batch size: 512 | lm loss: 5.095447E+00 | loss scale: 16384.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.066 | TFLOPs: 71.05 | +[default7]: iteration 1293/ 3814 | consumed samples: 662016 | consumed tokens: 1355808768 | elapsed time per iteration (s): 5.45 | learning rate: 1.411E-04 | global batch size: 512 | lm loss: 5.067540E+00 | loss scale: 16384.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.001 | TFLOPs: 71.00 | +[default7]: iteration 1294/ 3814 | consumed samples: 662528 | consumed tokens: 1356857344 | elapsed time per iteration (s): 5.45 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 5.080739E+00 | loss scale: 16384.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.975 | TFLOPs: 70.98 | +[default7]: iteration 1295/ 3814 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 5.46 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 5.098659E+00 | loss scale: 16384.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.780 | TFLOPs: 70.83 | +[default7]: iteration 1296/ 3814 | consumed samples: 663552 | consumed tokens: 1358954496 | elapsed time per iteration (s): 5.45 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 5.072164E+00 | loss scale: 16384.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 1297/ 3814 | consumed samples: 664064 | consumed tokens: 1360003072 | elapsed time per iteration (s): 5.46 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 5.078065E+00 | loss scale: 16384.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.801 | TFLOPs: 70.85 | +[default7]: iteration 1298/ 3814 | consumed samples: 664576 | consumed tokens: 1361051648 | elapsed time per iteration (s): 5.45 | learning rate: 1.408E-04 | global batch size: 512 | lm loss: 5.123230E+00 | loss scale: 16384.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.881 | TFLOPs: 70.91 | +[default7]: iteration 1299/ 3814 | consumed samples: 665088 | consumed tokens: 1362100224 | elapsed time per iteration (s): 5.43 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 5.119570E+00 | loss scale: 16384.0 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.295 | TFLOPs: 71.22 | +[default7]: iteration 1300/ 3814 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 5.44 | learning rate: 1.407E-04 | global batch size: 512 | lm loss: 5.060582E+00 | loss scale: 16384.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 1301/ 3814 | consumed samples: 666112 | consumed tokens: 1364197376 | elapsed time per iteration (s): 5.42 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 5.087492E+00 | loss scale: 16384.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.383 | TFLOPs: 71.29 | +[default7]: iteration 1302/ 3814 | consumed samples: 666624 | consumed tokens: 1365245952 | elapsed time per iteration (s): 5.43 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 5.064444E+00 | loss scale: 16384.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 1303/ 3814 | consumed samples: 667136 | consumed tokens: 1366294528 | elapsed time per iteration (s): 5.46 | learning rate: 1.405E-04 | global batch size: 512 | lm loss: 5.104701E+00 | loss scale: 16384.0 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.759 | TFLOPs: 70.82 | +[default7]: iteration 1304/ 3814 | consumed samples: 667648 | consumed tokens: 1367343104 | elapsed time per iteration (s): 5.45 | learning rate: 1.405E-04 | global batch size: 512 | lm loss: 5.094936E+00 | loss scale: 16384.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.951 | TFLOPs: 70.96 | +[default7]: iteration 1305/ 3814 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 5.43 | learning rate: 1.404E-04 | global batch size: 512 | lm loss: 5.080698E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.324 | TFLOPs: 71.24 | +[default7]: iteration 1306/ 3814 | consumed samples: 668672 | consumed tokens: 1369440256 | elapsed time per iteration (s): 5.45 | learning rate: 1.403E-04 | global batch size: 512 | lm loss: 5.074222E+00 | loss scale: 16384.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.904 | TFLOPs: 70.93 | +[default7]: iteration 1307/ 3814 | consumed samples: 669184 | consumed tokens: 1370488832 | elapsed time per iteration (s): 5.44 | learning rate: 1.403E-04 | global batch size: 512 | lm loss: 5.063168E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.081 | TFLOPs: 71.06 | +[default7]: iteration 1308/ 3814 | consumed samples: 669696 | consumed tokens: 1371537408 | elapsed time per iteration (s): 5.44 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 5.071122E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.137 | TFLOPs: 71.10 | +[default7]: iteration 1309/ 3814 | consumed samples: 670208 | consumed tokens: 1372585984 | elapsed time per iteration (s): 5.45 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 5.069313E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 1310/ 3814 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 5.44 | learning rate: 1.401E-04 | global batch size: 512 | lm loss: 5.096435E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.101 | TFLOPs: 71.08 | +[default7]: iteration 1311/ 3814 | consumed samples: 671232 | consumed tokens: 1374683136 | elapsed time per iteration (s): 5.45 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 5.064478E+00 | loss scale: 16384.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.927 | TFLOPs: 70.94 | +[default7]: iteration 1312/ 3814 | consumed samples: 671744 | consumed tokens: 1375731712 | elapsed time per iteration (s): 5.45 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 5.060952E+00 | loss scale: 16384.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.966 | TFLOPs: 70.97 | +[default7]: iteration 1313/ 3814 | consumed samples: 672256 | consumed tokens: 1376780288 | elapsed time per iteration (s): 5.45 | learning rate: 1.399E-04 | global batch size: 512 | lm loss: 5.084276E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.984 | TFLOPs: 70.99 | +[default7]: iteration 1314/ 3814 | consumed samples: 672768 | consumed tokens: 1377828864 | elapsed time per iteration (s): 5.44 | learning rate: 1.399E-04 | global batch size: 512 | lm loss: 5.085886E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.077 | TFLOPs: 71.06 | +[default7]: iteration 1315/ 3814 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 5.45 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 5.065051E+00 | loss scale: 16384.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.008 | TFLOPs: 71.01 | +[default7]: iteration 1316/ 3814 | consumed samples: 673792 | consumed tokens: 1379926016 | elapsed time per iteration (s): 5.45 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 5.063940E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.914 | TFLOPs: 70.93 | +[default7]: iteration 1317/ 3814 | consumed samples: 674304 | consumed tokens: 1380974592 | elapsed time per iteration (s): 5.44 | learning rate: 1.397E-04 | global batch size: 512 | lm loss: 5.064588E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.193 | TFLOPs: 71.14 | +[default7]: iteration 1318/ 3814 | consumed samples: 674816 | consumed tokens: 1382023168 | elapsed time per iteration (s): 5.45 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 5.090208E+00 | loss scale: 16384.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.031 | TFLOPs: 71.02 | +[default7]: iteration 1319/ 3814 | consumed samples: 675328 | consumed tokens: 1383071744 | elapsed time per iteration (s): 5.45 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 5.070374E+00 | loss scale: 16384.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.990 | TFLOPs: 70.99 | +[default7]: iteration 1320/ 3814 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 5.45 | learning rate: 1.395E-04 | global batch size: 512 | lm loss: 5.069537E+00 | loss scale: 16384.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.968 | TFLOPs: 70.97 | +[default7]: iteration 1321/ 3814 | consumed samples: 676352 | consumed tokens: 1385168896 | elapsed time per iteration (s): 5.46 | learning rate: 1.395E-04 | global batch size: 512 | lm loss: 5.062721E+00 | loss scale: 16384.0 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.694 | TFLOPs: 70.77 | +[default7]: iteration 1322/ 3814 | consumed samples: 676864 | consumed tokens: 1386217472 | elapsed time per iteration (s): 5.43 | learning rate: 1.394E-04 | global batch size: 512 | lm loss: 5.055037E+00 | loss scale: 16384.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.256 | TFLOPs: 71.19 | +[default7]: iteration 1323/ 3814 | consumed samples: 677376 | consumed tokens: 1387266048 | elapsed time per iteration (s): 5.46 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 5.044589E+00 | loss scale: 16384.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.841 | TFLOPs: 70.88 | +[default7]: iteration 1324/ 3814 | consumed samples: 677888 | consumed tokens: 1388314624 | elapsed time per iteration (s): 5.42 | learning rate: 1.393E-04 | global batch size: 512 | lm loss: 5.070241E+00 | loss scale: 16384.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.382 | TFLOPs: 71.29 | +[default7]: iteration 1325/ 3814 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 5.45 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 5.061565E+00 | loss scale: 16384.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.928 | TFLOPs: 70.95 | +[default7]: iteration 1326/ 3814 | consumed samples: 678912 | consumed tokens: 1390411776 | elapsed time per iteration (s): 5.46 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 5.080166E+00 | loss scale: 16384.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.816 | TFLOPs: 70.86 | +[default7]: iteration 1327/ 3814 | consumed samples: 679424 | consumed tokens: 1391460352 | elapsed time per iteration (s): 5.43 | learning rate: 1.391E-04 | global batch size: 512 | lm loss: 5.042128E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.261 | TFLOPs: 71.20 | +[default7]: iteration 1328/ 3814 | consumed samples: 679936 | consumed tokens: 1392508928 | elapsed time per iteration (s): 5.45 | learning rate: 1.390E-04 | global batch size: 512 | lm loss: 5.060116E+00 | loss scale: 16384.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.949 | TFLOPs: 70.96 | +[default7]: iteration 1329/ 3814 | consumed samples: 680448 | consumed tokens: 1393557504 | elapsed time per iteration (s): 5.46 | learning rate: 1.390E-04 | global batch size: 512 | lm loss: 5.082335E+00 | loss scale: 16384.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.852 | TFLOPs: 70.89 | +[default7]: iteration 1330/ 3814 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 5.45 | learning rate: 1.389E-04 | global batch size: 512 | lm loss: 5.070811E+00 | loss scale: 16384.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.874 | TFLOPs: 70.90 | +[default7]: iteration 1331/ 3814 | consumed samples: 681472 | consumed tokens: 1395654656 | elapsed time per iteration (s): 5.45 | learning rate: 1.389E-04 | global batch size: 512 | lm loss: 5.055291E+00 | loss scale: 16384.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.948 | TFLOPs: 70.96 | +[default7]: iteration 1332/ 3814 | consumed samples: 681984 | consumed tokens: 1396703232 | elapsed time per iteration (s): 5.44 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 5.094744E+00 | loss scale: 16384.0 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.077 | TFLOPs: 71.06 | +[default7]: iteration 1333/ 3814 | consumed samples: 682496 | consumed tokens: 1397751808 | elapsed time per iteration (s): 5.46 | learning rate: 1.387E-04 | global batch size: 512 | lm loss: 5.041579E+00 | loss scale: 16384.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.700 | TFLOPs: 70.77 | +[default7]: iteration 1334/ 3814 | consumed samples: 683008 | consumed tokens: 1398800384 | elapsed time per iteration (s): 5.46 | learning rate: 1.387E-04 | global batch size: 512 | lm loss: 5.046810E+00 | loss scale: 16384.0 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.731 | TFLOPs: 70.80 | +[default7]: iteration 1335/ 3814 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 5.45 | learning rate: 1.386E-04 | global batch size: 512 | lm loss: 5.060074E+00 | loss scale: 16384.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.891 | TFLOPs: 70.92 | +[default7]: iteration 1336/ 3814 | consumed samples: 684032 | consumed tokens: 1400897536 | elapsed time per iteration (s): 5.46 | learning rate: 1.386E-04 | global batch size: 512 | lm loss: 5.053610E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.763 | TFLOPs: 70.82 | +[default7]: iteration 1337/ 3814 | consumed samples: 684544 | consumed tokens: 1401946112 | elapsed time per iteration (s): 5.45 | learning rate: 1.385E-04 | global batch size: 512 | lm loss: 5.042096E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.989 | TFLOPs: 70.99 | +[default7]: iteration 1338/ 3814 | consumed samples: 685056 | consumed tokens: 1402994688 | elapsed time per iteration (s): 5.45 | learning rate: 1.384E-04 | global batch size: 512 | lm loss: 5.026457E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.864 | TFLOPs: 70.90 | +[default7]: iteration 1339/ 3814 | consumed samples: 685568 | consumed tokens: 1404043264 | elapsed time per iteration (s): 5.47 | learning rate: 1.384E-04 | global batch size: 512 | lm loss: 5.047799E+00 | loss scale: 16384.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.669 | TFLOPs: 70.75 | +[default7]: iteration 1340/ 3814 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 5.45 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 5.075535E+00 | loss scale: 16384.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.994 | TFLOPs: 70.99 | +[default7]: iteration 1341/ 3814 | consumed samples: 686592 | consumed tokens: 1406140416 | elapsed time per iteration (s): 5.47 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 5.057650E+00 | loss scale: 16384.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.575 | TFLOPs: 70.68 | +[default7]: iteration 1342/ 3814 | consumed samples: 687104 | consumed tokens: 1407188992 | elapsed time per iteration (s): 5.45 | learning rate: 1.382E-04 | global batch size: 512 | lm loss: 5.039515E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.993 | TFLOPs: 70.99 | +[default7]: iteration 1343/ 3814 | consumed samples: 687616 | consumed tokens: 1408237568 | elapsed time per iteration (s): 5.48 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 5.047081E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.402 | TFLOPs: 70.55 | +[default7]: iteration 1344/ 3814 | consumed samples: 688128 | consumed tokens: 1409286144 | elapsed time per iteration (s): 5.47 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 5.036287E+00 | loss scale: 16384.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.636 | TFLOPs: 70.72 | +[default7]: iteration 1345/ 3814 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 5.45 | learning rate: 1.380E-04 | global batch size: 512 | lm loss: 5.052748E+00 | loss scale: 16384.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.973 | TFLOPs: 70.98 | +[default7]: iteration 1346/ 3814 | consumed samples: 689152 | consumed tokens: 1411383296 | elapsed time per iteration (s): 5.46 | learning rate: 1.380E-04 | global batch size: 512 | lm loss: 5.052015E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.751 | TFLOPs: 70.81 | +[default7]: iteration 1347/ 3814 | consumed samples: 689664 | consumed tokens: 1412431872 | elapsed time per iteration (s): 5.46 | learning rate: 1.379E-04 | global batch size: 512 | lm loss: 5.028776E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.775 | TFLOPs: 70.83 | +[default7]: iteration 1348/ 3814 | consumed samples: 690176 | consumed tokens: 1413480448 | elapsed time per iteration (s): 5.46 | learning rate: 1.378E-04 | global batch size: 512 | lm loss: 5.050018E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.762 | TFLOPs: 70.82 | +[default7]: iteration 1349/ 3814 | consumed samples: 690688 | consumed tokens: 1414529024 | elapsed time per iteration (s): 5.46 | learning rate: 1.378E-04 | global batch size: 512 | lm loss: 5.040091E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.801 | TFLOPs: 70.85 | +[default7]: iteration 1350/ 3814 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 5.45 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 5.036930E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.958 | TFLOPs: 70.97 | +[default7]: iteration 1351/ 3814 | consumed samples: 691712 | consumed tokens: 1416626176 | elapsed time per iteration (s): 5.45 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 5.057902E+00 | loss scale: 16384.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1352/ 3814 | consumed samples: 692224 | consumed tokens: 1417674752 | elapsed time per iteration (s): 5.49 | learning rate: 1.376E-04 | global batch size: 512 | lm loss: 5.035889E+00 | loss scale: 16384.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.341 | TFLOPs: 70.50 | +[default7]: iteration 1353/ 3814 | consumed samples: 692736 | consumed tokens: 1418723328 | elapsed time per iteration (s): 5.47 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 5.056127E+00 | loss scale: 16384.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.604 | TFLOPs: 70.70 | +[default7]: iteration 1354/ 3814 | consumed samples: 693248 | consumed tokens: 1419771904 | elapsed time per iteration (s): 5.43 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 5.025781E+00 | loss scale: 16384.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.213 | TFLOPs: 71.16 | +[default7]: iteration 1355/ 3814 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 5.43 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 5.036726E+00 | loss scale: 16384.0 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 1356/ 3814 | consumed samples: 694272 | consumed tokens: 1421869056 | elapsed time per iteration (s): 5.44 | learning rate: 1.374E-04 | global batch size: 512 | lm loss: 5.038908E+00 | loss scale: 16384.0 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 1357/ 3814 | consumed samples: 694784 | consumed tokens: 1422917632 | elapsed time per iteration (s): 5.45 | learning rate: 1.373E-04 | global batch size: 512 | lm loss: 5.035671E+00 | loss scale: 16384.0 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.917 | TFLOPs: 70.94 | +[default7]: iteration 1358/ 3814 | consumed samples: 695296 | consumed tokens: 1423966208 | elapsed time per iteration (s): 5.46 | learning rate: 1.372E-04 | global batch size: 512 | lm loss: 5.017986E+00 | loss scale: 16384.0 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.766 | TFLOPs: 70.82 | +[default7]: iteration 1359/ 3814 | consumed samples: 695808 | consumed tokens: 1425014784 | elapsed time per iteration (s): 5.45 | learning rate: 1.372E-04 | global batch size: 512 | lm loss: 5.048785E+00 | loss scale: 16384.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.985 | TFLOPs: 70.99 | +[default7]: iteration 1360/ 3814 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 5.47 | learning rate: 1.371E-04 | global batch size: 512 | lm loss: 5.035563E+00 | loss scale: 16384.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.523 | TFLOPs: 70.64 | +[default7]: iteration 1361/ 3814 | consumed samples: 696832 | consumed tokens: 1427111936 | elapsed time per iteration (s): 5.46 | learning rate: 1.370E-04 | global batch size: 512 | lm loss: 5.034790E+00 | loss scale: 16384.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.755 | TFLOPs: 70.81 | +[default7]: iteration 1362/ 3814 | consumed samples: 697344 | consumed tokens: 1428160512 | elapsed time per iteration (s): 5.45 | learning rate: 1.370E-04 | global batch size: 512 | lm loss: 5.026639E+00 | loss scale: 16384.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.865 | TFLOPs: 70.90 | +[default7]: iteration 1363/ 3814 | consumed samples: 697856 | consumed tokens: 1429209088 | elapsed time per iteration (s): 5.46 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 5.025844E+00 | loss scale: 16384.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.794 | TFLOPs: 70.84 | +[default7]: iteration 1364/ 3814 | consumed samples: 698368 | consumed tokens: 1430257664 | elapsed time per iteration (s): 5.45 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 5.029222E+00 | loss scale: 16384.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.941 | TFLOPs: 70.95 | +[default7]: iteration 1365/ 3814 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 5.46 | learning rate: 1.368E-04 | global batch size: 512 | lm loss: 5.029740E+00 | loss scale: 16384.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.688 | TFLOPs: 70.76 | +[default7]: iteration 1366/ 3814 | consumed samples: 699392 | consumed tokens: 1432354816 | elapsed time per iteration (s): 5.45 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 5.014485E+00 | loss scale: 16384.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.890 | TFLOPs: 70.92 | +[default7]: iteration 1367/ 3814 | consumed samples: 699904 | consumed tokens: 1433403392 | elapsed time per iteration (s): 5.47 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 5.024036E+00 | loss scale: 16384.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.545 | TFLOPs: 70.66 | +[default7]: iteration 1368/ 3814 | consumed samples: 700416 | consumed tokens: 1434451968 | elapsed time per iteration (s): 5.45 | learning rate: 1.366E-04 | global batch size: 512 | lm loss: 5.031988E+00 | loss scale: 16384.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 1369/ 3814 | consumed samples: 700928 | consumed tokens: 1435500544 | elapsed time per iteration (s): 5.46 | learning rate: 1.366E-04 | global batch size: 512 | lm loss: 5.038310E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.729 | TFLOPs: 70.79 | +[default7]: iteration 1370/ 3814 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 5.46 | learning rate: 1.365E-04 | global batch size: 512 | lm loss: 5.009251E+00 | loss scale: 16384.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.835 | TFLOPs: 70.87 | +[default7]: iteration 1371/ 3814 | consumed samples: 701952 | consumed tokens: 1437597696 | elapsed time per iteration (s): 5.45 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 5.005630E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.878 | TFLOPs: 70.91 | +[default7]: iteration 1372/ 3814 | consumed samples: 702464 | consumed tokens: 1438646272 | elapsed time per iteration (s): 5.44 | learning rate: 1.364E-04 | global batch size: 512 | lm loss: 5.008706E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.034 | TFLOPs: 71.03 | +[default7]: iteration 1373/ 3814 | consumed samples: 702976 | consumed tokens: 1439694848 | elapsed time per iteration (s): 5.46 | learning rate: 1.363E-04 | global batch size: 512 | lm loss: 5.017007E+00 | loss scale: 16384.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.802 | TFLOPs: 70.85 | +[default7]: iteration 1374/ 3814 | consumed samples: 703488 | consumed tokens: 1440743424 | elapsed time per iteration (s): 5.45 | learning rate: 1.362E-04 | global batch size: 512 | lm loss: 4.981347E+00 | loss scale: 16384.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.970 | TFLOPs: 70.98 | +[default7]: iteration 1375/ 3814 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 5.44 | learning rate: 1.362E-04 | global batch size: 512 | lm loss: 5.023861E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.033 | TFLOPs: 71.02 | +[default7]: iteration 1376/ 3814 | consumed samples: 704512 | consumed tokens: 1442840576 | elapsed time per iteration (s): 5.46 | learning rate: 1.361E-04 | global batch size: 512 | lm loss: 5.016499E+00 | loss scale: 16384.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.740 | TFLOPs: 70.80 | +[default7]: iteration 1377/ 3814 | consumed samples: 705024 | consumed tokens: 1443889152 | elapsed time per iteration (s): 5.47 | learning rate: 1.361E-04 | global batch size: 512 | lm loss: 5.019938E+00 | loss scale: 16384.0 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.683 | TFLOPs: 70.76 | +[default7]: iteration 1378/ 3814 | consumed samples: 705536 | consumed tokens: 1444937728 | elapsed time per iteration (s): 5.46 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 4.997125E+00 | loss scale: 16384.0 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.769 | TFLOPs: 70.82 | +[default7]: iteration 1379/ 3814 | consumed samples: 706048 | consumed tokens: 1445986304 | elapsed time per iteration (s): 5.45 | learning rate: 1.359E-04 | global batch size: 512 | lm loss: 5.035275E+00 | loss scale: 16384.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.866 | TFLOPs: 70.90 | +[default7]: iteration 1380/ 3814 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 5.46 | learning rate: 1.359E-04 | global batch size: 512 | lm loss: 5.008200E+00 | loss scale: 16384.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.830 | TFLOPs: 70.87 | +[default7]: iteration 1381/ 3814 | consumed samples: 707072 | consumed tokens: 1448083456 | elapsed time per iteration (s): 5.43 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 4.997216E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 1382/ 3814 | consumed samples: 707584 | consumed tokens: 1449132032 | elapsed time per iteration (s): 5.45 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 4.990297E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.952 | TFLOPs: 70.96 | +[default7]: iteration 1383/ 3814 | consumed samples: 708096 | consumed tokens: 1450180608 | elapsed time per iteration (s): 5.43 | learning rate: 1.357E-04 | global batch size: 512 | lm loss: 5.005351E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.319 | TFLOPs: 71.24 | +[default7]: iteration 1384/ 3814 | consumed samples: 708608 | consumed tokens: 1451229184 | elapsed time per iteration (s): 5.44 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 5.003928E+00 | loss scale: 16384.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.163 | TFLOPs: 71.12 | +[default7]: iteration 1385/ 3814 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 5.44 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 5.000386E+00 | loss scale: 16384.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.189 | TFLOPs: 71.14 | +[default7]: iteration 1386/ 3814 | consumed samples: 709632 | consumed tokens: 1453326336 | elapsed time per iteration (s): 5.45 | learning rate: 1.355E-04 | global batch size: 512 | lm loss: 4.999830E+00 | loss scale: 16384.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 1387/ 3814 | consumed samples: 710144 | consumed tokens: 1454374912 | elapsed time per iteration (s): 5.44 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 5.031245E+00 | loss scale: 16384.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.092 | TFLOPs: 71.07 | +[default7]: iteration 1388/ 3814 | consumed samples: 710656 | consumed tokens: 1455423488 | elapsed time per iteration (s): 5.45 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 4.988494E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.937 | TFLOPs: 70.95 | +[default7]: iteration 1389/ 3814 | consumed samples: 711168 | consumed tokens: 1456472064 | elapsed time per iteration (s): 5.46 | learning rate: 1.353E-04 | global batch size: 512 | lm loss: 4.987690E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.743 | TFLOPs: 70.81 | +[default7]: iteration 1390/ 3814 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 5.44 | learning rate: 1.353E-04 | global batch size: 512 | lm loss: 5.007291E+00 | loss scale: 16384.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 1391/ 3814 | consumed samples: 712192 | consumed tokens: 1458569216 | elapsed time per iteration (s): 5.44 | learning rate: 1.352E-04 | global batch size: 512 | lm loss: 4.990690E+00 | loss scale: 16384.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.044 | TFLOPs: 71.03 | +[default7]: iteration 1392/ 3814 | consumed samples: 712704 | consumed tokens: 1459617792 | elapsed time per iteration (s): 5.44 | learning rate: 1.351E-04 | global batch size: 512 | lm loss: 4.982445E+00 | loss scale: 16384.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.164 | TFLOPs: 71.12 | +[default7]: iteration 1393/ 3814 | consumed samples: 713216 | consumed tokens: 1460666368 | elapsed time per iteration (s): 5.43 | learning rate: 1.351E-04 | global batch size: 512 | lm loss: 5.006562E+00 | loss scale: 16384.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 1394/ 3814 | consumed samples: 713728 | consumed tokens: 1461714944 | elapsed time per iteration (s): 5.41 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 5.000691E+00 | loss scale: 16384.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.589 | TFLOPs: 71.44 | +[default7]: iteration 1395/ 3814 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 5.45 | learning rate: 1.349E-04 | global batch size: 512 | lm loss: 5.002737E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.950 | TFLOPs: 70.96 | +[default7]: iteration 1396/ 3814 | consumed samples: 714752 | consumed tokens: 1463812096 | elapsed time per iteration (s): 5.43 | learning rate: 1.349E-04 | global batch size: 512 | lm loss: 4.970407E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.272 | TFLOPs: 71.20 | +[default7]: iteration 1397/ 3814 | consumed samples: 715264 | consumed tokens: 1464860672 | elapsed time per iteration (s): 5.43 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 4.996696E+00 | loss scale: 16384.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.313 | TFLOPs: 71.24 | +[default7]: iteration 1398/ 3814 | consumed samples: 715776 | consumed tokens: 1465909248 | elapsed time per iteration (s): 5.44 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 4.988531E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.129 | TFLOPs: 71.10 | +[default7]: iteration 1399/ 3814 | consumed samples: 716288 | consumed tokens: 1466957824 | elapsed time per iteration (s): 5.42 | learning rate: 1.347E-04 | global batch size: 512 | lm loss: 4.953794E+00 | loss scale: 16384.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.410 | TFLOPs: 71.31 | +[default7]: iteration 1400/ 3814 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 5.42 | learning rate: 1.346E-04 | global batch size: 512 | lm loss: 4.981184E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.459 | TFLOPs: 71.35 | +[default7]: iteration 1401/ 3814 | consumed samples: 717312 | consumed tokens: 1469054976 | elapsed time per iteration (s): 5.44 | learning rate: 1.346E-04 | global batch size: 512 | lm loss: 4.994518E+00 | loss scale: 16384.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.173 | TFLOPs: 71.13 | +[default7]: iteration 1402/ 3814 | consumed samples: 717824 | consumed tokens: 1470103552 | elapsed time per iteration (s): 5.43 | learning rate: 1.345E-04 | global batch size: 512 | lm loss: 4.981790E+00 | loss scale: 16384.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.306 | TFLOPs: 71.23 | +[default7]: iteration 1403/ 3814 | consumed samples: 718336 | consumed tokens: 1471152128 | elapsed time per iteration (s): 5.46 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 4.979847E+00 | loss scale: 16384.0 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.857 | TFLOPs: 70.89 | +[default7]: iteration 1404/ 3814 | consumed samples: 718848 | consumed tokens: 1472200704 | elapsed time per iteration (s): 5.42 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 5.006809E+00 | loss scale: 16384.0 | grad norm: 0.400 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.383 | TFLOPs: 71.29 | +[default7]: iteration 1405/ 3814 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 5.44 | learning rate: 1.343E-04 | global batch size: 512 | lm loss: 4.995025E+00 | loss scale: 16384.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.092 | TFLOPs: 71.07 | +[default7]: iteration 1406/ 3814 | consumed samples: 719872 | consumed tokens: 1474297856 | elapsed time per iteration (s): 5.43 | learning rate: 1.343E-04 | global batch size: 512 | lm loss: 4.996290E+00 | loss scale: 16384.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.268 | TFLOPs: 71.20 | +[default7]: iteration 1407/ 3814 | consumed samples: 720384 | consumed tokens: 1475346432 | elapsed time per iteration (s): 5.42 | learning rate: 1.342E-04 | global batch size: 512 | lm loss: 4.970366E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.477 | TFLOPs: 71.36 | +[default7]: iteration 1408/ 3814 | consumed samples: 720896 | consumed tokens: 1476395008 | elapsed time per iteration (s): 5.43 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 5.002337E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.284 | TFLOPs: 71.21 | +[default7]: iteration 1409/ 3814 | consumed samples: 721408 | consumed tokens: 1477443584 | elapsed time per iteration (s): 5.43 | learning rate: 1.341E-04 | global batch size: 512 | lm loss: 4.977826E+00 | loss scale: 16384.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.253 | TFLOPs: 71.19 | +[default7]: iteration 1410/ 3814 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 5.43 | learning rate: 1.340E-04 | global batch size: 512 | lm loss: 4.962524E+00 | loss scale: 16384.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.308 | TFLOPs: 71.23 | +[default7]: iteration 1411/ 3814 | consumed samples: 722432 | consumed tokens: 1479540736 | elapsed time per iteration (s): 5.44 | learning rate: 1.339E-04 | global batch size: 512 | lm loss: 4.992051E+00 | loss scale: 16384.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.177 | TFLOPs: 71.13 | +[default7]: iteration 1412/ 3814 | consumed samples: 722944 | consumed tokens: 1480589312 | elapsed time per iteration (s): 5.45 | learning rate: 1.339E-04 | global batch size: 512 | lm loss: 4.992157E+00 | loss scale: 16384.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.870 | TFLOPs: 70.90 | +[default7]: iteration 1413/ 3814 | consumed samples: 723456 | consumed tokens: 1481637888 | elapsed time per iteration (s): 5.43 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 4.995600E+00 | loss scale: 16384.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.226 | TFLOPs: 71.17 | +[default7]: iteration 1414/ 3814 | consumed samples: 723968 | consumed tokens: 1482686464 | elapsed time per iteration (s): 5.44 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 4.991720E+00 | loss scale: 16384.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.157 | TFLOPs: 71.12 | +[default7]: iteration 1415/ 3814 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 5.46 | learning rate: 1.337E-04 | global batch size: 512 | lm loss: 4.973564E+00 | loss scale: 16384.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.824 | TFLOPs: 70.87 | +[default7]: iteration 1416/ 3814 | consumed samples: 724992 | consumed tokens: 1484783616 | elapsed time per iteration (s): 5.44 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 4.948478E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.061 | TFLOPs: 71.05 | +[default7]: iteration 1417/ 3814 | consumed samples: 725504 | consumed tokens: 1485832192 | elapsed time per iteration (s): 5.46 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 4.959438E+00 | loss scale: 16384.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.822 | TFLOPs: 70.86 | +[default7]: iteration 1418/ 3814 | consumed samples: 726016 | consumed tokens: 1486880768 | elapsed time per iteration (s): 5.43 | learning rate: 1.335E-04 | global batch size: 512 | lm loss: 4.974172E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.312 | TFLOPs: 71.23 | +[default7]: iteration 1419/ 3814 | consumed samples: 726528 | consumed tokens: 1487929344 | elapsed time per iteration (s): 5.45 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 4.945878E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.985 | TFLOPs: 70.99 | +[default7]: iteration 1420/ 3814 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 5.44 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 4.968878E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.165 | TFLOPs: 71.12 | +[default7]: iteration 1421/ 3814 | consumed samples: 727552 | consumed tokens: 1490026496 | elapsed time per iteration (s): 5.46 | learning rate: 1.333E-04 | global batch size: 512 | lm loss: 4.972792E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.798 | TFLOPs: 70.85 | +[default7]: iteration 1422/ 3814 | consumed samples: 728064 | consumed tokens: 1491075072 | elapsed time per iteration (s): 5.45 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 4.948810E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 1423/ 3814 | consumed samples: 728576 | consumed tokens: 1492123648 | elapsed time per iteration (s): 5.45 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 4.943388E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.938 | TFLOPs: 70.95 | +[default7]: iteration 1424/ 3814 | consumed samples: 729088 | consumed tokens: 1493172224 | elapsed time per iteration (s): 5.44 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 4.946882E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.104 | TFLOPs: 71.08 | +[default7]: iteration 1425/ 3814 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 5.44 | learning rate: 1.331E-04 | global batch size: 512 | lm loss: 4.960549E+00 | loss scale: 16384.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.085 | TFLOPs: 71.06 | +[default7]: iteration 1426/ 3814 | consumed samples: 730112 | consumed tokens: 1495269376 | elapsed time per iteration (s): 5.43 | learning rate: 1.330E-04 | global batch size: 512 | lm loss: 4.930009E+00 | loss scale: 16384.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.281 | TFLOPs: 71.21 | +[default7]: iteration 1427/ 3814 | consumed samples: 730624 | consumed tokens: 1496317952 | elapsed time per iteration (s): 5.44 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 4.939790E+00 | loss scale: 16384.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.115 | TFLOPs: 71.09 | +[default7]: iteration 1428/ 3814 | consumed samples: 731136 | consumed tokens: 1497366528 | elapsed time per iteration (s): 5.44 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 4.966747E+00 | loss scale: 16384.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.083 | TFLOPs: 71.06 | +[default7]: iteration 1429/ 3814 | consumed samples: 731648 | consumed tokens: 1498415104 | elapsed time per iteration (s): 5.43 | learning rate: 1.328E-04 | global batch size: 512 | lm loss: 4.949887E+00 | loss scale: 16384.0 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.327 | TFLOPs: 71.25 | +[default7]: iteration 1430/ 3814 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 5.49 | learning rate: 1.327E-04 | global batch size: 512 | lm loss: 4.946176E+00 | loss scale: 16384.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.253 | TFLOPs: 70.44 | +[default7]: iteration 1431/ 3814 | consumed samples: 732672 | consumed tokens: 1500512256 | elapsed time per iteration (s): 5.44 | learning rate: 1.327E-04 | global batch size: 512 | lm loss: 4.972342E+00 | loss scale: 16384.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.137 | TFLOPs: 71.10 | +[default7]: iteration 1432/ 3814 | consumed samples: 733184 | consumed tokens: 1501560832 | elapsed time per iteration (s): 5.43 | learning rate: 1.326E-04 | global batch size: 512 | lm loss: 4.931181E+00 | loss scale: 16384.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.212 | TFLOPs: 71.16 | +[default7]: iteration 1433/ 3814 | consumed samples: 733696 | consumed tokens: 1502609408 | elapsed time per iteration (s): 5.44 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 4.947366E+00 | loss scale: 16384.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.041 | TFLOPs: 71.03 | +[default7]: iteration 1434/ 3814 | consumed samples: 734208 | consumed tokens: 1503657984 | elapsed time per iteration (s): 5.45 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 4.962494E+00 | loss scale: 16384.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 1435/ 3814 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 5.42 | learning rate: 1.324E-04 | global batch size: 512 | lm loss: 4.975207E+00 | loss scale: 16384.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.449 | TFLOPs: 71.34 | +[default7]: iteration 1436/ 3814 | consumed samples: 735232 | consumed tokens: 1505755136 | elapsed time per iteration (s): 5.43 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 4.957309E+00 | loss scale: 16384.0 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.289 | TFLOPs: 71.22 | +[default7]: iteration 1437/ 3814 | consumed samples: 735744 | consumed tokens: 1506803712 | elapsed time per iteration (s): 5.43 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 4.985128E+00 | loss scale: 16384.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.357 | TFLOPs: 71.27 | +[default7]: iteration 1438/ 3814 | consumed samples: 736256 | consumed tokens: 1507852288 | elapsed time per iteration (s): 5.42 | learning rate: 1.322E-04 | global batch size: 512 | lm loss: 4.974141E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.458 | TFLOPs: 71.35 | +[default7]: iteration 1439/ 3814 | consumed samples: 736768 | consumed tokens: 1508900864 | elapsed time per iteration (s): 5.43 | learning rate: 1.322E-04 | global batch size: 512 | lm loss: 4.925560E+00 | loss scale: 16384.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.299 | TFLOPs: 71.23 | +[default7]: iteration 1440/ 3814 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 5.42 | learning rate: 1.321E-04 | global batch size: 512 | lm loss: 4.939626E+00 | loss scale: 16384.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.538 | TFLOPs: 71.41 | +[default7]: iteration 1441/ 3814 | consumed samples: 737792 | consumed tokens: 1510998016 | elapsed time per iteration (s): 5.43 | learning rate: 1.320E-04 | global batch size: 512 | lm loss: 4.961249E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.347 | TFLOPs: 71.26 | +[default7]: iteration 1442/ 3814 | consumed samples: 738304 | consumed tokens: 1512046592 | elapsed time per iteration (s): 5.42 | learning rate: 1.320E-04 | global batch size: 512 | lm loss: 4.969199E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.451 | TFLOPs: 71.34 | +[default7]: iteration 1443/ 3814 | consumed samples: 738816 | consumed tokens: 1513095168 | elapsed time per iteration (s): 5.42 | learning rate: 1.319E-04 | global batch size: 512 | lm loss: 4.928735E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.483 | TFLOPs: 71.36 | +[default7]: iteration 1444/ 3814 | consumed samples: 739328 | consumed tokens: 1514143744 | elapsed time per iteration (s): 5.41 | learning rate: 1.318E-04 | global batch size: 512 | lm loss: 4.942211E+00 | loss scale: 16384.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.584 | TFLOPs: 71.44 | +[default7]: iteration 1445/ 3814 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 5.42 | learning rate: 1.318E-04 | global batch size: 512 | lm loss: 4.935173E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.410 | TFLOPs: 71.31 | +[default7]: iteration 1446/ 3814 | consumed samples: 740352 | consumed tokens: 1516240896 | elapsed time per iteration (s): 5.42 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 4.935842E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.419 | TFLOPs: 71.32 | +[default7]: iteration 1447/ 3814 | consumed samples: 740864 | consumed tokens: 1517289472 | elapsed time per iteration (s): 5.44 | learning rate: 1.316E-04 | global batch size: 512 | lm loss: 4.956658E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.127 | TFLOPs: 71.10 | +[default7]: iteration 1448/ 3814 | consumed samples: 741376 | consumed tokens: 1518338048 | elapsed time per iteration (s): 5.40 | learning rate: 1.316E-04 | global batch size: 512 | lm loss: 4.930202E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.779 | TFLOPs: 71.59 | +[default7]: iteration 1449/ 3814 | consumed samples: 741888 | consumed tokens: 1519386624 | elapsed time per iteration (s): 5.41 | learning rate: 1.315E-04 | global batch size: 512 | lm loss: 4.938687E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.611 | TFLOPs: 71.46 | +[default7]: iteration 1450/ 3814 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 5.43 | learning rate: 1.314E-04 | global batch size: 512 | lm loss: 4.928933E+00 | loss scale: 16384.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.323 | TFLOPs: 71.24 | +[default7]: iteration 1451/ 3814 | consumed samples: 742912 | consumed tokens: 1521483776 | elapsed time per iteration (s): 5.43 | learning rate: 1.314E-04 | global batch size: 512 | lm loss: 4.942674E+00 | loss scale: 16384.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.357 | TFLOPs: 71.27 | +[default7]: iteration 1452/ 3814 | consumed samples: 743424 | consumed tokens: 1522532352 | elapsed time per iteration (s): 5.43 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 4.942924E+00 | loss scale: 16384.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.376 | TFLOPs: 71.28 | +[default7]: iteration 1453/ 3814 | consumed samples: 743936 | consumed tokens: 1523580928 | elapsed time per iteration (s): 5.42 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 4.916873E+00 | loss scale: 16384.0 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.422 | TFLOPs: 71.32 | +[default7]: iteration 1454/ 3814 | consumed samples: 744448 | consumed tokens: 1524629504 | elapsed time per iteration (s): 5.41 | learning rate: 1.312E-04 | global batch size: 512 | lm loss: 4.979842E+00 | loss scale: 16384.0 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.716 | TFLOPs: 71.54 | +[default7]: iteration 1455/ 3814 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 5.43 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 4.955596E+00 | loss scale: 16384.0 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.329 | TFLOPs: 71.25 | +[default7]: iteration 1456/ 3814 | consumed samples: 745472 | consumed tokens: 1526726656 | elapsed time per iteration (s): 5.42 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 4.923427E+00 | loss scale: 16384.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.417 | TFLOPs: 71.31 | +[default7]: iteration 1457/ 3814 | consumed samples: 745984 | consumed tokens: 1527775232 | elapsed time per iteration (s): 5.42 | learning rate: 1.310E-04 | global batch size: 512 | lm loss: 4.933739E+00 | loss scale: 16384.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.507 | TFLOPs: 71.38 | +[default7]: iteration 1458/ 3814 | consumed samples: 746496 | consumed tokens: 1528823808 | elapsed time per iteration (s): 5.42 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 4.942509E+00 | loss scale: 16384.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.503 | TFLOPs: 71.38 | +[default7]: iteration 1459/ 3814 | consumed samples: 747008 | consumed tokens: 1529872384 | elapsed time per iteration (s): 5.43 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 4.949287E+00 | loss scale: 16384.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.330 | TFLOPs: 71.25 | +[default7]: iteration 1460/ 3814 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 5.42 | learning rate: 1.308E-04 | global batch size: 512 | lm loss: 4.953399E+00 | loss scale: 16384.0 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.380 | TFLOPs: 71.29 | +[default7]: iteration 1461/ 3814 | consumed samples: 748032 | consumed tokens: 1531969536 | elapsed time per iteration (s): 5.41 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 4.938637E+00 | loss scale: 16384.0 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.610 | TFLOPs: 71.46 | +[default7]: iteration 1462/ 3814 | consumed samples: 748544 | consumed tokens: 1533018112 | elapsed time per iteration (s): 5.42 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 4.936167E+00 | loss scale: 16384.0 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.509 | TFLOPs: 71.38 | +[default7]: iteration 1463/ 3814 | consumed samples: 749056 | consumed tokens: 1534066688 | elapsed time per iteration (s): 5.43 | learning rate: 1.306E-04 | global batch size: 512 | lm loss: 4.930665E+00 | loss scale: 16384.0 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.306 | TFLOPs: 71.23 | +[default7]: iteration 1464/ 3814 | consumed samples: 749568 | consumed tokens: 1535115264 | elapsed time per iteration (s): 5.43 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 4.919998E+00 | loss scale: 16384.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.307 | TFLOPs: 71.23 | +[default7]: iteration 1465/ 3814 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 5.44 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 4.923041E+00 | loss scale: 16384.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 1466/ 3814 | consumed samples: 750592 | consumed tokens: 1537212416 | elapsed time per iteration (s): 5.43 | learning rate: 1.304E-04 | global batch size: 512 | lm loss: 4.902606E+00 | loss scale: 16384.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.348 | TFLOPs: 71.26 | +[default7]: iteration 1467/ 3814 | consumed samples: 751104 | consumed tokens: 1538260992 | elapsed time per iteration (s): 5.44 | learning rate: 1.303E-04 | global batch size: 512 | lm loss: 4.929320E+00 | loss scale: 16384.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.188 | TFLOPs: 71.14 | +[default7]: iteration 1468/ 3814 | consumed samples: 751616 | consumed tokens: 1539309568 | elapsed time per iteration (s): 5.43 | learning rate: 1.303E-04 | global batch size: 512 | lm loss: 4.914128E+00 | loss scale: 16384.0 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.277 | TFLOPs: 71.21 | +[default7]: iteration 1469/ 3814 | consumed samples: 752128 | consumed tokens: 1540358144 | elapsed time per iteration (s): 5.42 | learning rate: 1.302E-04 | global batch size: 512 | lm loss: 4.926806E+00 | loss scale: 16384.0 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.382 | TFLOPs: 71.29 | +[default7]: iteration 1470/ 3814 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 5.42 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 4.929492E+00 | loss scale: 16384.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.455 | TFLOPs: 71.34 | +[default7]: iteration 1471/ 3814 | consumed samples: 753152 | consumed tokens: 1542455296 | elapsed time per iteration (s): 5.44 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 4.919583E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.199 | TFLOPs: 71.15 | +[default7]: iteration 1472/ 3814 | consumed samples: 753664 | consumed tokens: 1543503872 | elapsed time per iteration (s): 5.43 | learning rate: 1.300E-04 | global batch size: 512 | lm loss: 4.925826E+00 | loss scale: 16384.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.246 | TFLOPs: 71.19 | +[default7]: iteration 1473/ 3814 | consumed samples: 754176 | consumed tokens: 1544552448 | elapsed time per iteration (s): 5.45 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 4.907773E+00 | loss scale: 16384.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.992 | TFLOPs: 70.99 | +[default7]: iteration 1474/ 3814 | consumed samples: 754688 | consumed tokens: 1545601024 | elapsed time per iteration (s): 5.45 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 4.915535E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.992 | TFLOPs: 70.99 | +[default7]: iteration 1475/ 3814 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 5.45 | learning rate: 1.298E-04 | global batch size: 512 | lm loss: 4.918961E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.892 | TFLOPs: 70.92 | +[default7]: iteration 1476/ 3814 | consumed samples: 755712 | consumed tokens: 1547698176 | elapsed time per iteration (s): 5.43 | learning rate: 1.298E-04 | global batch size: 512 | lm loss: 4.914817E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.242 | TFLOPs: 71.18 | +[default7]: iteration 1477/ 3814 | consumed samples: 756224 | consumed tokens: 1548746752 | elapsed time per iteration (s): 5.44 | learning rate: 1.297E-04 | global batch size: 512 | lm loss: 4.922327E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.041 | TFLOPs: 71.03 | +[default7]: iteration 1478/ 3814 | consumed samples: 756736 | consumed tokens: 1549795328 | elapsed time per iteration (s): 5.44 | learning rate: 1.296E-04 | global batch size: 512 | lm loss: 4.917348E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.158 | TFLOPs: 71.12 | +[default7]: iteration 1479/ 3814 | consumed samples: 757248 | consumed tokens: 1550843904 | elapsed time per iteration (s): 5.45 | learning rate: 1.296E-04 | global batch size: 512 | lm loss: 4.919472E+00 | loss scale: 16384.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.936 | TFLOPs: 70.95 | +[default7]: iteration 1480/ 3814 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 5.43 | learning rate: 1.295E-04 | global batch size: 512 | lm loss: 4.920630E+00 | loss scale: 16384.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.233 | TFLOPs: 71.18 | +[default7]: iteration 1481/ 3814 | consumed samples: 758272 | consumed tokens: 1552941056 | elapsed time per iteration (s): 5.44 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 4.892658E+00 | loss scale: 16384.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 1482/ 3814 | consumed samples: 758784 | consumed tokens: 1553989632 | elapsed time per iteration (s): 5.44 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 4.916562E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 1483/ 3814 | consumed samples: 759296 | consumed tokens: 1555038208 | elapsed time per iteration (s): 5.45 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 4.906325E+00 | loss scale: 16384.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.910 | TFLOPs: 70.93 | +[default7]: iteration 1484/ 3814 | consumed samples: 759808 | consumed tokens: 1556086784 | elapsed time per iteration (s): 5.46 | learning rate: 1.292E-04 | global batch size: 512 | lm loss: 4.896272E+00 | loss scale: 16384.0 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.829 | TFLOPs: 70.87 | +[default7]: iteration 1485/ 3814 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 5.47 | learning rate: 1.292E-04 | global batch size: 512 | lm loss: 4.926611E+00 | loss scale: 16384.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.650 | TFLOPs: 70.73 | +[default7]: iteration 1486/ 3814 | consumed samples: 760832 | consumed tokens: 1558183936 | elapsed time per iteration (s): 5.44 | learning rate: 1.291E-04 | global batch size: 512 | lm loss: 4.921335E+00 | loss scale: 16384.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.084 | TFLOPs: 71.06 | +[default7]: iteration 1487/ 3814 | consumed samples: 761344 | consumed tokens: 1559232512 | elapsed time per iteration (s): 5.45 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 4.894507E+00 | loss scale: 16384.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.005 | TFLOPs: 71.00 | +[default7]: iteration 1488/ 3814 | consumed samples: 761856 | consumed tokens: 1560281088 | elapsed time per iteration (s): 5.45 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 4.904143E+00 | loss scale: 16384.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.889 | TFLOPs: 70.92 | +[default7]: iteration 1489/ 3814 | consumed samples: 762368 | consumed tokens: 1561329664 | elapsed time per iteration (s): 5.45 | learning rate: 1.289E-04 | global batch size: 512 | lm loss: 4.907069E+00 | loss scale: 16384.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.868 | TFLOPs: 70.90 | +[default7]: iteration 1490/ 3814 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 5.46 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 4.895726E+00 | loss scale: 16384.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.781 | TFLOPs: 70.83 | +[default7]: iteration 1491/ 3814 | consumed samples: 763392 | consumed tokens: 1563426816 | elapsed time per iteration (s): 5.44 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 4.912001E+00 | loss scale: 16384.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.106 | TFLOPs: 71.08 | +[default7]: iteration 1492/ 3814 | consumed samples: 763904 | consumed tokens: 1564475392 | elapsed time per iteration (s): 5.45 | learning rate: 1.287E-04 | global batch size: 512 | lm loss: 4.899485E+00 | loss scale: 16384.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.030 | TFLOPs: 71.02 | +[default7]: iteration 1493/ 3814 | consumed samples: 764416 | consumed tokens: 1565523968 | elapsed time per iteration (s): 5.46 | learning rate: 1.286E-04 | global batch size: 512 | lm loss: 4.909983E+00 | loss scale: 16384.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.833 | TFLOPs: 70.87 | +[default7]: iteration 1494/ 3814 | consumed samples: 764928 | consumed tokens: 1566572544 | elapsed time per iteration (s): 5.47 | learning rate: 1.286E-04 | global batch size: 512 | lm loss: 4.908542E+00 | loss scale: 16384.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.539 | TFLOPs: 70.65 | +[default7]: iteration 1495/ 3814 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 5.45 | learning rate: 1.285E-04 | global batch size: 512 | lm loss: 4.898492E+00 | loss scale: 16384.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.89 | +[default7]: iteration 1496/ 3814 | consumed samples: 765952 | consumed tokens: 1568669696 | elapsed time per iteration (s): 5.47 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 4.900252E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.578 | TFLOPs: 70.68 | +[default7]: iteration 1497/ 3814 | consumed samples: 766464 | consumed tokens: 1569718272 | elapsed time per iteration (s): 5.45 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 4.929102E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.020 | TFLOPs: 71.01 | +[default7]: iteration 1498/ 3814 | consumed samples: 766976 | consumed tokens: 1570766848 | elapsed time per iteration (s): 5.43 | learning rate: 1.283E-04 | global batch size: 512 | lm loss: 4.933774E+00 | loss scale: 16384.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.232 | TFLOPs: 71.17 | +[default7]: iteration 1499/ 3814 | consumed samples: 767488 | consumed tokens: 1571815424 | elapsed time per iteration (s): 5.45 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 4.894595E+00 | loss scale: 16384.0 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default1]:[2023-02-16 13:35:50,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 1500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 13:35:50,544] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1500 is begin to save! +[default0]:[2023-02-16 13:35:50,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_00-model_states.pt... +[default7]: iteration 1500/ 3814 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 5.45 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 4.920814E+00 | loss scale: 32768.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.013 | TFLOPs: 71.01 | +[default0]:[2023-02-16 13:35:50,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:50,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:50,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:50,707] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:50,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:50,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:50,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:50,838] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:50,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:50,838] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:50,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:50,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:50,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:50,902] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:50,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:50,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,016] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:50,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:50,957] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,013] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,075] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,125] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,180] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,233] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,238] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,296] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,447] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,456] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_00-model_states.pt. +[default1]:[2023-02-16 13:35:51,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,556] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,835] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,841] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:51,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,887] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:51,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:51,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:51,949] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,004] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:51,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:51,994] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:52,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,048] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:52,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:52,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,101] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:52,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:52,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:52,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:52,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,298] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:52,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,276] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:52,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:52,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,352] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 13:35:52,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:52,439] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 13:35:52,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,459] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 13:35:52,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 13:35:52,512] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 13:35:52,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 13:35:52,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt. +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:35:52,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 13:35:52,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 13:35:52,495] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 13:35:52,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 13:35:52,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:35:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:35:53,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,050] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,073] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,073] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,081] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,081] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,030] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,108] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,028] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,094] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,071] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,073] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,073] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,107] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,117] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,072] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,072] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,133] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,104] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,139] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,121] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,178] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,133] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,165] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,142] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,167] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,187] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,195] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,123] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,131] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,214] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,145] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,167] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,160] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,220] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,160] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,226] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,203] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,197] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,187] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,188] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,184] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,184] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,262] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,270] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,295] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,263] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,229] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,213] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,234] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,290] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,271] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,310] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,263] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 13:35:53,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:35:53,235] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:35:53,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,230] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,256] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,242] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 13:35:53,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:35:53,328] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:35:53,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 13:35:53,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:35:53,356] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:35:53,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 13:35:53,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,330] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,281] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,359] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,310] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 13:35:53,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:35:53,385] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:35:53,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 13:35:53,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:35:53,425] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:35:53,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 13:35:53,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:35:53,475] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:35:53,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 13:35:53,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:35:53,434] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:35:53,435] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]: successfully saved checkpoint at iteration 1500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 2947.42 +[default4]:[2023-02-16 13:35:53,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:35:53,490] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:35:53,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]: iteration 1501/ 3814 | consumed samples: 768512 | consumed tokens: 1573912576 | elapsed time per iteration (s): 8.40 | learning rate: 1.281E-04 | global batch size: 512 | lm loss: 4.886263E+00 | loss scale: 32768.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 60.938 | TFLOPs: 46.03 | +[default7]: iteration 1502/ 3814 | consumed samples: 769024 | consumed tokens: 1574961152 | elapsed time per iteration (s): 5.44 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 4.931126E+00 | loss scale: 32768.0 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.053 | TFLOPs: 71.04 | +[default7]: iteration 1503/ 3814 | consumed samples: 769536 | consumed tokens: 1576009728 | elapsed time per iteration (s): 5.44 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 4.916968E+00 | loss scale: 32768.0 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.150 | TFLOPs: 71.11 | +[default7]: iteration 1504/ 3814 | consumed samples: 770048 | consumed tokens: 1577058304 | elapsed time per iteration (s): 5.47 | learning rate: 1.279E-04 | global batch size: 512 | lm loss: 4.897582E+00 | loss scale: 32768.0 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.678 | TFLOPs: 70.76 | +[default7]: iteration 1505/ 3814 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 5.45 | learning rate: 1.278E-04 | global batch size: 512 | lm loss: 4.913399E+00 | loss scale: 32768.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.945 | TFLOPs: 70.96 | +[default7]: iteration 1506/ 3814 | consumed samples: 771072 | consumed tokens: 1579155456 | elapsed time per iteration (s): 5.46 | learning rate: 1.278E-04 | global batch size: 512 | lm loss: 4.868303E+00 | loss scale: 32768.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.838 | TFLOPs: 70.88 | +[default7]: iteration 1507/ 3814 | consumed samples: 771584 | consumed tokens: 1580204032 | elapsed time per iteration (s): 5.46 | learning rate: 1.277E-04 | global batch size: 512 | lm loss: 4.909307E+00 | loss scale: 32768.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.781 | TFLOPs: 70.83 | +[default7]: iteration 1508/ 3814 | consumed samples: 772096 | consumed tokens: 1581252608 | elapsed time per iteration (s): 5.46 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 4.885291E+00 | loss scale: 32768.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.827 | TFLOPs: 70.87 | +[default7]: iteration 1509/ 3814 | consumed samples: 772608 | consumed tokens: 1582301184 | elapsed time per iteration (s): 5.45 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 4.905433E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.999 | TFLOPs: 71.00 | +[default7]: iteration 1510/ 3814 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 5.45 | learning rate: 1.275E-04 | global batch size: 512 | lm loss: 4.871664E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.949 | TFLOPs: 70.96 | +[default7]: iteration 1511/ 3814 | consumed samples: 773632 | consumed tokens: 1584398336 | elapsed time per iteration (s): 5.48 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 4.910434E+00 | loss scale: 32768.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.502 | TFLOPs: 70.62 | +[default7]: iteration 1512/ 3814 | consumed samples: 774144 | consumed tokens: 1585446912 | elapsed time per iteration (s): 5.46 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 4.897252E+00 | loss scale: 32768.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.830 | TFLOPs: 70.87 | +[default7]: iteration 1513/ 3814 | consumed samples: 774656 | consumed tokens: 1586495488 | elapsed time per iteration (s): 5.44 | learning rate: 1.273E-04 | global batch size: 512 | lm loss: 4.860651E+00 | loss scale: 32768.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.083 | TFLOPs: 71.06 | +[default7]: iteration 1514/ 3814 | consumed samples: 775168 | consumed tokens: 1587544064 | elapsed time per iteration (s): 5.47 | learning rate: 1.272E-04 | global batch size: 512 | lm loss: 4.876097E+00 | loss scale: 32768.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.648 | TFLOPs: 70.73 | +[default7]: iteration 1515/ 3814 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 5.46 | learning rate: 1.272E-04 | global batch size: 512 | lm loss: 4.861862E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.810 | TFLOPs: 70.86 | +[default7]: iteration 1516/ 3814 | consumed samples: 776192 | consumed tokens: 1589641216 | elapsed time per iteration (s): 5.44 | learning rate: 1.271E-04 | global batch size: 512 | lm loss: 4.876996E+00 | loss scale: 32768.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 1517/ 3814 | consumed samples: 776704 | consumed tokens: 1590689792 | elapsed time per iteration (s): 5.41 | learning rate: 1.270E-04 | global batch size: 512 | lm loss: 4.875900E+00 | loss scale: 32768.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.670 | TFLOPs: 71.51 | +[default7]: iteration 1518/ 3814 | consumed samples: 777216 | consumed tokens: 1591738368 | elapsed time per iteration (s): 5.42 | learning rate: 1.270E-04 | global batch size: 512 | lm loss: 4.884651E+00 | loss scale: 32768.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.433 | TFLOPs: 71.33 | +[default7]: iteration 1519/ 3814 | consumed samples: 777728 | consumed tokens: 1592786944 | elapsed time per iteration (s): 5.44 | learning rate: 1.269E-04 | global batch size: 512 | lm loss: 4.890078E+00 | loss scale: 32768.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.098 | TFLOPs: 71.07 | +[default7]: iteration 1520/ 3814 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 5.44 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 4.877196E+00 | loss scale: 32768.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.177 | TFLOPs: 71.13 | +[default7]: iteration 1521/ 3814 | consumed samples: 778752 | consumed tokens: 1594884096 | elapsed time per iteration (s): 5.43 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 4.898930E+00 | loss scale: 32768.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.250 | TFLOPs: 71.19 | +[default7]: iteration 1522/ 3814 | consumed samples: 779264 | consumed tokens: 1595932672 | elapsed time per iteration (s): 5.44 | learning rate: 1.267E-04 | global batch size: 512 | lm loss: 4.887196E+00 | loss scale: 32768.0 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 1523/ 3814 | consumed samples: 779776 | consumed tokens: 1596981248 | elapsed time per iteration (s): 5.45 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 4.871004E+00 | loss scale: 32768.0 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.914 | TFLOPs: 70.93 | +[default7]: iteration 1524/ 3814 | consumed samples: 780288 | consumed tokens: 1598029824 | elapsed time per iteration (s): 5.45 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 4.878393E+00 | loss scale: 32768.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.954 | TFLOPs: 70.96 | +[default7]: iteration 1525/ 3814 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 5.46 | learning rate: 1.265E-04 | global batch size: 512 | lm loss: 4.851731E+00 | loss scale: 32768.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.848 | TFLOPs: 70.88 | +[default7]: iteration 1526/ 3814 | consumed samples: 781312 | consumed tokens: 1600126976 | elapsed time per iteration (s): 5.43 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 4.888324E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.296 | TFLOPs: 71.22 | +[default7]: iteration 1527/ 3814 | consumed samples: 781824 | consumed tokens: 1601175552 | elapsed time per iteration (s): 5.44 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 4.875235E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.177 | TFLOPs: 71.13 | +[default7]: iteration 1528/ 3814 | consumed samples: 782336 | consumed tokens: 1602224128 | elapsed time per iteration (s): 5.44 | learning rate: 1.263E-04 | global batch size: 512 | lm loss: 4.867376E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 1529/ 3814 | consumed samples: 782848 | consumed tokens: 1603272704 | elapsed time per iteration (s): 5.45 | learning rate: 1.262E-04 | global batch size: 512 | lm loss: 4.864870E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.942 | TFLOPs: 70.96 | +[default7]: iteration 1530/ 3814 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 5.46 | learning rate: 1.262E-04 | global batch size: 512 | lm loss: 4.867959E+00 | loss scale: 32768.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.744 | TFLOPs: 70.81 | +[default7]: iteration 1531/ 3814 | consumed samples: 783872 | consumed tokens: 1605369856 | elapsed time per iteration (s): 5.46 | learning rate: 1.261E-04 | global batch size: 512 | lm loss: 4.857160E+00 | loss scale: 32768.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.763 | TFLOPs: 70.82 | +[default7]: iteration 1532/ 3814 | consumed samples: 784384 | consumed tokens: 1606418432 | elapsed time per iteration (s): 5.45 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 4.838391E+00 | loss scale: 32768.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.860 | TFLOPs: 70.89 | +[default7]: iteration 1533/ 3814 | consumed samples: 784896 | consumed tokens: 1607467008 | elapsed time per iteration (s): 5.45 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 4.870492E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.961 | TFLOPs: 70.97 | +[default7]: iteration 1534/ 3814 | consumed samples: 785408 | consumed tokens: 1608515584 | elapsed time per iteration (s): 5.45 | learning rate: 1.259E-04 | global batch size: 512 | lm loss: 4.885389E+00 | loss scale: 32768.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.937 | TFLOPs: 70.95 | +[default7]: iteration 1535/ 3814 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 5.43 | learning rate: 1.258E-04 | global batch size: 512 | lm loss: 4.862638E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.355 | TFLOPs: 71.27 | +[default7]: iteration 1536/ 3814 | consumed samples: 786432 | consumed tokens: 1610612736 | elapsed time per iteration (s): 5.45 | learning rate: 1.257E-04 | global batch size: 512 | lm loss: 4.873517E+00 | loss scale: 32768.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 1537/ 3814 | consumed samples: 786944 | consumed tokens: 1611661312 | elapsed time per iteration (s): 5.46 | learning rate: 1.257E-04 | global batch size: 512 | lm loss: 4.875331E+00 | loss scale: 32768.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.774 | TFLOPs: 70.83 | +[default7]: iteration 1538/ 3814 | consumed samples: 787456 | consumed tokens: 1612709888 | elapsed time per iteration (s): 5.45 | learning rate: 1.256E-04 | global batch size: 512 | lm loss: 4.873044E+00 | loss scale: 32768.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 1539/ 3814 | consumed samples: 787968 | consumed tokens: 1613758464 | elapsed time per iteration (s): 5.44 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 4.862597E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.037 | TFLOPs: 71.03 | +[default7]: iteration 1540/ 3814 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 5.45 | learning rate: 1.255E-04 | global batch size: 512 | lm loss: 4.860133E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.859 | TFLOPs: 70.89 | +[default7]: iteration 1541/ 3814 | consumed samples: 788992 | consumed tokens: 1615855616 | elapsed time per iteration (s): 5.46 | learning rate: 1.254E-04 | global batch size: 512 | lm loss: 4.858520E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 1542/ 3814 | consumed samples: 789504 | consumed tokens: 1616904192 | elapsed time per iteration (s): 5.43 | learning rate: 1.253E-04 | global batch size: 512 | lm loss: 4.871119E+00 | loss scale: 32768.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.343 | TFLOPs: 71.26 | +[default7]: iteration 1543/ 3814 | consumed samples: 790016 | consumed tokens: 1617952768 | elapsed time per iteration (s): 5.45 | learning rate: 1.253E-04 | global batch size: 512 | lm loss: 4.846611E+00 | loss scale: 32768.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.013 | TFLOPs: 71.01 | +[default7]: iteration 1544/ 3814 | consumed samples: 790528 | consumed tokens: 1619001344 | elapsed time per iteration (s): 5.45 | learning rate: 1.252E-04 | global batch size: 512 | lm loss: 4.853168E+00 | loss scale: 32768.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.981 | TFLOPs: 70.98 | +[default7]: iteration 1545/ 3814 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 5.44 | learning rate: 1.251E-04 | global batch size: 512 | lm loss: 4.874287E+00 | loss scale: 32768.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.059 | TFLOPs: 71.04 | +[default7]: iteration 1546/ 3814 | consumed samples: 791552 | consumed tokens: 1621098496 | elapsed time per iteration (s): 5.44 | learning rate: 1.251E-04 | global batch size: 512 | lm loss: 4.857842E+00 | loss scale: 32768.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.044 | TFLOPs: 71.03 | +[default7]: iteration 1547/ 3814 | consumed samples: 792064 | consumed tokens: 1622147072 | elapsed time per iteration (s): 5.46 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 4.837382E+00 | loss scale: 32768.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.748 | TFLOPs: 70.81 | +[default7]: iteration 1548/ 3814 | consumed samples: 792576 | consumed tokens: 1623195648 | elapsed time per iteration (s): 5.46 | learning rate: 1.249E-04 | global batch size: 512 | lm loss: 4.860186E+00 | loss scale: 32768.0 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.771 | TFLOPs: 70.83 | +[default7]: iteration 1549/ 3814 | consumed samples: 793088 | consumed tokens: 1624244224 | elapsed time per iteration (s): 5.47 | learning rate: 1.249E-04 | global batch size: 512 | lm loss: 4.856913E+00 | loss scale: 32768.0 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.665 | TFLOPs: 70.75 | +[default7]: iteration 1550/ 3814 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 5.46 | learning rate: 1.248E-04 | global batch size: 512 | lm loss: 4.877946E+00 | loss scale: 32768.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.772 | TFLOPs: 70.83 | +[default7]: iteration 1551/ 3814 | consumed samples: 794112 | consumed tokens: 1626341376 | elapsed time per iteration (s): 5.44 | learning rate: 1.247E-04 | global batch size: 512 | lm loss: 4.847996E+00 | loss scale: 32768.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.109 | TFLOPs: 71.08 | +[default7]: iteration 1552/ 3814 | consumed samples: 794624 | consumed tokens: 1627389952 | elapsed time per iteration (s): 5.49 | learning rate: 1.247E-04 | global batch size: 512 | lm loss: 4.856580E+00 | loss scale: 32768.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.301 | TFLOPs: 70.47 | +[default7]: iteration 1553/ 3814 | consumed samples: 795136 | consumed tokens: 1628438528 | elapsed time per iteration (s): 5.44 | learning rate: 1.246E-04 | global batch size: 512 | lm loss: 4.822358E+00 | loss scale: 32768.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.168 | TFLOPs: 71.13 | +[default7]: iteration 1554/ 3814 | consumed samples: 795648 | consumed tokens: 1629487104 | elapsed time per iteration (s): 5.44 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 4.866512E+00 | loss scale: 32768.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 1555/ 3814 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 5.44 | learning rate: 1.245E-04 | global batch size: 512 | lm loss: 4.820873E+00 | loss scale: 32768.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.180 | TFLOPs: 71.13 | +[default7]: iteration 1556/ 3814 | consumed samples: 796672 | consumed tokens: 1631584256 | elapsed time per iteration (s): 5.44 | learning rate: 1.244E-04 | global batch size: 512 | lm loss: 4.853977E+00 | loss scale: 32768.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.054 | TFLOPs: 71.04 | +[default7]: iteration 1557/ 3814 | consumed samples: 797184 | consumed tokens: 1632632832 | elapsed time per iteration (s): 5.44 | learning rate: 1.243E-04 | global batch size: 512 | lm loss: 4.859667E+00 | loss scale: 32768.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.080 | TFLOPs: 71.06 | +[default7]: iteration 1558/ 3814 | consumed samples: 797696 | consumed tokens: 1633681408 | elapsed time per iteration (s): 5.45 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 4.837687E+00 | loss scale: 32768.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 1559/ 3814 | consumed samples: 798208 | consumed tokens: 1634729984 | elapsed time per iteration (s): 5.45 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 4.844392E+00 | loss scale: 32768.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.025 | TFLOPs: 71.02 | +[default7]: iteration 1560/ 3814 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 5.43 | learning rate: 1.241E-04 | global batch size: 512 | lm loss: 4.864088E+00 | loss scale: 32768.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.310 | TFLOPs: 71.23 | +[default7]: iteration 1561/ 3814 | consumed samples: 799232 | consumed tokens: 1636827136 | elapsed time per iteration (s): 5.42 | learning rate: 1.240E-04 | global batch size: 512 | lm loss: 4.850512E+00 | loss scale: 32768.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.420 | TFLOPs: 71.32 | +[default7]: iteration 1562/ 3814 | consumed samples: 799744 | consumed tokens: 1637875712 | elapsed time per iteration (s): 5.43 | learning rate: 1.240E-04 | global batch size: 512 | lm loss: 4.846664E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.365 | TFLOPs: 71.28 | +[default7]: iteration 1563/ 3814 | consumed samples: 800256 | consumed tokens: 1638924288 | elapsed time per iteration (s): 5.42 | learning rate: 1.239E-04 | global batch size: 512 | lm loss: 4.836257E+00 | loss scale: 32768.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.493 | TFLOPs: 71.37 | +[default7]: iteration 1564/ 3814 | consumed samples: 800768 | consumed tokens: 1639972864 | elapsed time per iteration (s): 5.43 | learning rate: 1.238E-04 | global batch size: 512 | lm loss: 4.854570E+00 | loss scale: 32768.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.354 | TFLOPs: 71.27 | +[default7]: iteration 1565/ 3814 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 5.43 | learning rate: 1.238E-04 | global batch size: 512 | lm loss: 4.848556E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.252 | TFLOPs: 71.19 | +[default7]: iteration 1566/ 3814 | consumed samples: 801792 | consumed tokens: 1642070016 | elapsed time per iteration (s): 5.43 | learning rate: 1.237E-04 | global batch size: 512 | lm loss: 4.841938E+00 | loss scale: 32768.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.207 | TFLOPs: 71.16 | +[default7]: iteration 1567/ 3814 | consumed samples: 802304 | consumed tokens: 1643118592 | elapsed time per iteration (s): 5.44 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 4.853008E+00 | loss scale: 32768.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.117 | TFLOPs: 71.09 | +[default7]: iteration 1568/ 3814 | consumed samples: 802816 | consumed tokens: 1644167168 | elapsed time per iteration (s): 5.44 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 4.833632E+00 | loss scale: 32768.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.099 | TFLOPs: 71.07 | +[default7]: iteration 1569/ 3814 | consumed samples: 803328 | consumed tokens: 1645215744 | elapsed time per iteration (s): 5.42 | learning rate: 1.235E-04 | global batch size: 512 | lm loss: 4.842671E+00 | loss scale: 32768.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.458 | TFLOPs: 71.35 | +[default7]: iteration 1570/ 3814 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 5.46 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 4.848048E+00 | loss scale: 32768.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.853 | TFLOPs: 70.89 | +[default7]: iteration 1571/ 3814 | consumed samples: 804352 | consumed tokens: 1647312896 | elapsed time per iteration (s): 5.45 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 4.817886E+00 | loss scale: 32768.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.947 | TFLOPs: 70.96 | +[default7]: iteration 1572/ 3814 | consumed samples: 804864 | consumed tokens: 1648361472 | elapsed time per iteration (s): 5.43 | learning rate: 1.233E-04 | global batch size: 512 | lm loss: 4.832926E+00 | loss scale: 32768.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.301 | TFLOPs: 71.23 | +[default7]: iteration 1573/ 3814 | consumed samples: 805376 | consumed tokens: 1649410048 | elapsed time per iteration (s): 5.43 | learning rate: 1.232E-04 | global batch size: 512 | lm loss: 4.829874E+00 | loss scale: 32768.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.271 | TFLOPs: 71.20 | +[default7]: iteration 1574/ 3814 | consumed samples: 805888 | consumed tokens: 1650458624 | elapsed time per iteration (s): 5.44 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 4.869355E+00 | loss scale: 32768.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.058 | TFLOPs: 71.04 | +[default7]: iteration 1575/ 3814 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 5.43 | learning rate: 1.231E-04 | global batch size: 512 | lm loss: 4.850996E+00 | loss scale: 32768.0 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.212 | TFLOPs: 71.16 | +[default7]: iteration 1576/ 3814 | consumed samples: 806912 | consumed tokens: 1652555776 | elapsed time per iteration (s): 5.43 | learning rate: 1.230E-04 | global batch size: 512 | lm loss: 4.848263E+00 | loss scale: 32768.0 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.345 | TFLOPs: 71.26 | +[default7]: iteration 1577/ 3814 | consumed samples: 807424 | consumed tokens: 1653604352 | elapsed time per iteration (s): 5.44 | learning rate: 1.229E-04 | global batch size: 512 | lm loss: 4.835384E+00 | loss scale: 32768.0 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.06 | +[default7]: iteration 1578/ 3814 | consumed samples: 807936 | consumed tokens: 1654652928 | elapsed time per iteration (s): 5.43 | learning rate: 1.229E-04 | global batch size: 512 | lm loss: 4.817863E+00 | loss scale: 32768.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.354 | TFLOPs: 71.27 | +[default7]: iteration 1579/ 3814 | consumed samples: 808448 | consumed tokens: 1655701504 | elapsed time per iteration (s): 5.43 | learning rate: 1.228E-04 | global batch size: 512 | lm loss: 4.817936E+00 | loss scale: 32768.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.253 | TFLOPs: 71.19 | +[default7]: iteration 1580/ 3814 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 5.43 | learning rate: 1.227E-04 | global batch size: 512 | lm loss: 4.839749E+00 | loss scale: 32768.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.304 | TFLOPs: 71.23 | +[default7]: iteration 1581/ 3814 | consumed samples: 809472 | consumed tokens: 1657798656 | elapsed time per iteration (s): 5.45 | learning rate: 1.227E-04 | global batch size: 512 | lm loss: 4.840464E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.941 | TFLOPs: 70.95 | +[default7]: iteration 1582/ 3814 | consumed samples: 809984 | consumed tokens: 1658847232 | elapsed time per iteration (s): 5.44 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 4.840619E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.082 | TFLOPs: 71.06 | +[default7]: iteration 1583/ 3814 | consumed samples: 810496 | consumed tokens: 1659895808 | elapsed time per iteration (s): 5.47 | learning rate: 1.225E-04 | global batch size: 512 | lm loss: 4.816002E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.533 | TFLOPs: 70.65 | +[default7]: iteration 1584/ 3814 | consumed samples: 811008 | consumed tokens: 1660944384 | elapsed time per iteration (s): 5.43 | learning rate: 1.225E-04 | global batch size: 512 | lm loss: 4.828362E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.283 | TFLOPs: 71.21 | +[default7]: iteration 1585/ 3814 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 5.42 | learning rate: 1.224E-04 | global batch size: 512 | lm loss: 4.827500E+00 | loss scale: 32768.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.448 | TFLOPs: 71.34 | +[default7]: iteration 1586/ 3814 | consumed samples: 812032 | consumed tokens: 1663041536 | elapsed time per iteration (s): 5.44 | learning rate: 1.223E-04 | global batch size: 512 | lm loss: 4.791329E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.202 | TFLOPs: 71.15 | +[default7]: iteration 1587/ 3814 | consumed samples: 812544 | consumed tokens: 1664090112 | elapsed time per iteration (s): 5.42 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 4.823175E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.414 | TFLOPs: 71.31 | +[default7]: iteration 1588/ 3814 | consumed samples: 813056 | consumed tokens: 1665138688 | elapsed time per iteration (s): 5.43 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 4.805178E+00 | loss scale: 32768.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 1589/ 3814 | consumed samples: 813568 | consumed tokens: 1666187264 | elapsed time per iteration (s): 5.43 | learning rate: 1.221E-04 | global batch size: 512 | lm loss: 4.807180E+00 | loss scale: 32768.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.258 | TFLOPs: 71.19 | +[default7]: iteration 1590/ 3814 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 5.45 | learning rate: 1.220E-04 | global batch size: 512 | lm loss: 4.808271E+00 | loss scale: 32768.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.023 | TFLOPs: 71.02 | +[default7]: iteration 1591/ 3814 | consumed samples: 814592 | consumed tokens: 1668284416 | elapsed time per iteration (s): 5.43 | learning rate: 1.220E-04 | global batch size: 512 | lm loss: 4.842120E+00 | loss scale: 32768.0 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.223 | TFLOPs: 71.17 | +[default7]: iteration 1592/ 3814 | consumed samples: 815104 | consumed tokens: 1669332992 | elapsed time per iteration (s): 5.46 | learning rate: 1.219E-04 | global batch size: 512 | lm loss: 4.824869E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.855 | TFLOPs: 70.89 | +[default7]: iteration 1593/ 3814 | consumed samples: 815616 | consumed tokens: 1670381568 | elapsed time per iteration (s): 5.47 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 4.807119E+00 | loss scale: 32768.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.671 | TFLOPs: 70.75 | +[default7]: iteration 1594/ 3814 | consumed samples: 816128 | consumed tokens: 1671430144 | elapsed time per iteration (s): 5.45 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 4.788735E+00 | loss scale: 32768.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.003 | TFLOPs: 71.00 | +[default7]: iteration 1595/ 3814 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 5.45 | learning rate: 1.217E-04 | global batch size: 512 | lm loss: 4.827894E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 1596/ 3814 | consumed samples: 817152 | consumed tokens: 1673527296 | elapsed time per iteration (s): 5.44 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 4.818104E+00 | loss scale: 32768.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.095 | TFLOPs: 71.07 | +[default7]: iteration 1597/ 3814 | consumed samples: 817664 | consumed tokens: 1674575872 | elapsed time per iteration (s): 5.45 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 4.806440E+00 | loss scale: 32768.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.005 | TFLOPs: 71.00 | +[default7]: iteration 1598/ 3814 | consumed samples: 818176 | consumed tokens: 1675624448 | elapsed time per iteration (s): 5.47 | learning rate: 1.215E-04 | global batch size: 512 | lm loss: 4.847874E+00 | loss scale: 32768.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.674 | TFLOPs: 70.75 | +[default7]: iteration 1599/ 3814 | consumed samples: 818688 | consumed tokens: 1676673024 | elapsed time per iteration (s): 5.45 | learning rate: 1.214E-04 | global batch size: 512 | lm loss: 4.803685E+00 | loss scale: 32768.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.924 | TFLOPs: 70.94 | +[default7]: iteration 1600/ 3814 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 5.44 | learning rate: 1.213E-04 | global batch size: 512 | lm loss: 4.834006E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.06 | +[default7]: iteration 1601/ 3814 | consumed samples: 819712 | consumed tokens: 1678770176 | elapsed time per iteration (s): 5.45 | learning rate: 1.213E-04 | global batch size: 512 | lm loss: 4.793831E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.991 | TFLOPs: 70.99 | +[default7]: iteration 1602/ 3814 | consumed samples: 820224 | consumed tokens: 1679818752 | elapsed time per iteration (s): 5.46 | learning rate: 1.212E-04 | global batch size: 512 | lm loss: 4.796828E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.723 | TFLOPs: 70.79 | +[default7]: iteration 1603/ 3814 | consumed samples: 820736 | consumed tokens: 1680867328 | elapsed time per iteration (s): 5.45 | learning rate: 1.211E-04 | global batch size: 512 | lm loss: 4.815596E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.906 | TFLOPs: 70.93 | +[default7]: iteration 1604/ 3814 | consumed samples: 821248 | consumed tokens: 1681915904 | elapsed time per iteration (s): 5.46 | learning rate: 1.211E-04 | global batch size: 512 | lm loss: 4.804015E+00 | loss scale: 32768.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.774 | TFLOPs: 70.83 | +[default7]: iteration 1605/ 3814 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 5.44 | learning rate: 1.210E-04 | global batch size: 512 | lm loss: 4.797508E+00 | loss scale: 32768.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.067 | TFLOPs: 71.05 | +[default7]: iteration 1606/ 3814 | consumed samples: 822272 | consumed tokens: 1684013056 | elapsed time per iteration (s): 5.48 | learning rate: 1.209E-04 | global batch size: 512 | lm loss: 4.828899E+00 | loss scale: 32768.0 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.469 | TFLOPs: 70.60 | +[default7]: iteration 1607/ 3814 | consumed samples: 822784 | consumed tokens: 1685061632 | elapsed time per iteration (s): 5.49 | learning rate: 1.209E-04 | global batch size: 512 | lm loss: 4.850905E+00 | loss scale: 32768.0 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.237 | TFLOPs: 70.42 | +[default7]: iteration 1608/ 3814 | consumed samples: 823296 | consumed tokens: 1686110208 | elapsed time per iteration (s): 5.48 | learning rate: 1.208E-04 | global batch size: 512 | lm loss: 4.811207E+00 | loss scale: 32768.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.510 | TFLOPs: 70.63 | +[default7]: iteration 1609/ 3814 | consumed samples: 823808 | consumed tokens: 1687158784 | elapsed time per iteration (s): 5.44 | learning rate: 1.207E-04 | global batch size: 512 | lm loss: 4.808430E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.080 | TFLOPs: 71.06 | +[default7]: iteration 1610/ 3814 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 5.46 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 4.823644E+00 | loss scale: 32768.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.778 | TFLOPs: 70.83 | +[default7]: iteration 1611/ 3814 | consumed samples: 824832 | consumed tokens: 1689255936 | elapsed time per iteration (s): 5.48 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 4.786570E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.462 | TFLOPs: 70.59 | +[default7]: iteration 1612/ 3814 | consumed samples: 825344 | consumed tokens: 1690304512 | elapsed time per iteration (s): 5.44 | learning rate: 1.205E-04 | global batch size: 512 | lm loss: 4.815243E+00 | loss scale: 32768.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.060 | TFLOPs: 71.04 | +[default7]: iteration 1613/ 3814 | consumed samples: 825856 | consumed tokens: 1691353088 | elapsed time per iteration (s): 5.47 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 4.808760E+00 | loss scale: 32768.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.651 | TFLOPs: 70.74 | +[default7]: iteration 1614/ 3814 | consumed samples: 826368 | consumed tokens: 1692401664 | elapsed time per iteration (s): 5.48 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 4.801000E+00 | loss scale: 32768.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.405 | TFLOPs: 70.55 | +[default7]: iteration 1615/ 3814 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 5.46 | learning rate: 1.203E-04 | global batch size: 512 | lm loss: 4.809398E+00 | loss scale: 32768.0 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.710 | TFLOPs: 70.78 | +[default7]: iteration 1616/ 3814 | consumed samples: 827392 | consumed tokens: 1694498816 | elapsed time per iteration (s): 5.46 | learning rate: 1.202E-04 | global batch size: 512 | lm loss: 4.818034E+00 | loss scale: 32768.0 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.858 | TFLOPs: 70.89 | +[default7]: iteration 1617/ 3814 | consumed samples: 827904 | consumed tokens: 1695547392 | elapsed time per iteration (s): 5.45 | learning rate: 1.202E-04 | global batch size: 512 | lm loss: 4.786759E+00 | loss scale: 32768.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.867 | TFLOPs: 70.90 | +[default7]: iteration 1618/ 3814 | consumed samples: 828416 | consumed tokens: 1696595968 | elapsed time per iteration (s): 5.46 | learning rate: 1.201E-04 | global batch size: 512 | lm loss: 4.801199E+00 | loss scale: 32768.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.790 | TFLOPs: 70.84 | +[default7]: iteration 1619/ 3814 | consumed samples: 828928 | consumed tokens: 1697644544 | elapsed time per iteration (s): 5.46 | learning rate: 1.200E-04 | global batch size: 512 | lm loss: 4.805231E+00 | loss scale: 32768.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.706 | TFLOPs: 70.78 | +[default7]: iteration 1620/ 3814 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 5.46 | learning rate: 1.199E-04 | global batch size: 512 | lm loss: 4.789824E+00 | loss scale: 32768.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.803 | TFLOPs: 70.85 | +[default7]: iteration 1621/ 3814 | consumed samples: 829952 | consumed tokens: 1699741696 | elapsed time per iteration (s): 5.45 | learning rate: 1.199E-04 | global batch size: 512 | lm loss: 4.788225E+00 | loss scale: 32768.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.984 | TFLOPs: 70.99 | +[default7]: iteration 1622/ 3814 | consumed samples: 830464 | consumed tokens: 1700790272 | elapsed time per iteration (s): 5.44 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 4.787263E+00 | loss scale: 32768.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.072 | TFLOPs: 71.05 | +[default7]: iteration 1623/ 3814 | consumed samples: 830976 | consumed tokens: 1701838848 | elapsed time per iteration (s): 5.44 | learning rate: 1.197E-04 | global batch size: 512 | lm loss: 4.798990E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.146 | TFLOPs: 71.11 | +[default7]: iteration 1624/ 3814 | consumed samples: 831488 | consumed tokens: 1702887424 | elapsed time per iteration (s): 5.45 | learning rate: 1.197E-04 | global batch size: 512 | lm loss: 4.812810E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.963 | TFLOPs: 70.97 | +[default7]: iteration 1625/ 3814 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 5.41 | learning rate: 1.196E-04 | global batch size: 512 | lm loss: 4.782617E+00 | loss scale: 32768.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.609 | TFLOPs: 71.46 | +[default7]: iteration 1626/ 3814 | consumed samples: 832512 | consumed tokens: 1704984576 | elapsed time per iteration (s): 5.41 | learning rate: 1.195E-04 | global batch size: 512 | lm loss: 4.799381E+00 | loss scale: 32768.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.577 | TFLOPs: 71.44 | +[default7]: iteration 1627/ 3814 | consumed samples: 833024 | consumed tokens: 1706033152 | elapsed time per iteration (s): 5.42 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 4.782598E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.447 | TFLOPs: 71.34 | +[default7]: iteration 1628/ 3814 | consumed samples: 833536 | consumed tokens: 1707081728 | elapsed time per iteration (s): 5.43 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 4.803413E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.369 | TFLOPs: 71.28 | +[default7]: iteration 1629/ 3814 | consumed samples: 834048 | consumed tokens: 1708130304 | elapsed time per iteration (s): 5.43 | learning rate: 1.193E-04 | global batch size: 512 | lm loss: 4.805623E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.283 | TFLOPs: 71.21 | +[default7]: iteration 1630/ 3814 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 5.43 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 4.767031E+00 | loss scale: 32768.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.375 | TFLOPs: 71.28 | +[default7]: iteration 1631/ 3814 | consumed samples: 835072 | consumed tokens: 1710227456 | elapsed time per iteration (s): 5.44 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 4.787264E+00 | loss scale: 32768.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.172 | TFLOPs: 71.13 | +[default7]: iteration 1632/ 3814 | consumed samples: 835584 | consumed tokens: 1711276032 | elapsed time per iteration (s): 5.44 | learning rate: 1.191E-04 | global batch size: 512 | lm loss: 4.783996E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.135 | TFLOPs: 71.10 | +[default7]: iteration 1633/ 3814 | consumed samples: 836096 | consumed tokens: 1712324608 | elapsed time per iteration (s): 5.43 | learning rate: 1.190E-04 | global batch size: 512 | lm loss: 4.759157E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.275 | TFLOPs: 71.21 | +[default7]: iteration 1634/ 3814 | consumed samples: 836608 | consumed tokens: 1713373184 | elapsed time per iteration (s): 5.45 | learning rate: 1.190E-04 | global batch size: 512 | lm loss: 4.754026E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.971 | TFLOPs: 70.98 | +[default7]: iteration 1635/ 3814 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 5.43 | learning rate: 1.189E-04 | global batch size: 512 | lm loss: 4.786922E+00 | loss scale: 32768.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 1636/ 3814 | consumed samples: 837632 | consumed tokens: 1715470336 | elapsed time per iteration (s): 5.45 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 4.794480E+00 | loss scale: 32768.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.916 | TFLOPs: 70.94 | +[default7]: iteration 1637/ 3814 | consumed samples: 838144 | consumed tokens: 1716518912 | elapsed time per iteration (s): 5.44 | learning rate: 1.187E-04 | global batch size: 512 | lm loss: 4.783312E+00 | loss scale: 32768.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.076 | TFLOPs: 71.06 | +[default7]: iteration 1638/ 3814 | consumed samples: 838656 | consumed tokens: 1717567488 | elapsed time per iteration (s): 5.45 | learning rate: 1.187E-04 | global batch size: 512 | lm loss: 4.785994E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.997 | TFLOPs: 71.00 | +[default7]: iteration 1639/ 3814 | consumed samples: 839168 | consumed tokens: 1718616064 | elapsed time per iteration (s): 5.43 | learning rate: 1.186E-04 | global batch size: 512 | lm loss: 4.782520E+00 | loss scale: 32768.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.220 | TFLOPs: 71.17 | +[default7]: iteration 1640/ 3814 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 5.45 | learning rate: 1.185E-04 | global batch size: 512 | lm loss: 4.797473E+00 | loss scale: 32768.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.928 | TFLOPs: 70.95 | +[default7]: iteration 1641/ 3814 | consumed samples: 840192 | consumed tokens: 1720713216 | elapsed time per iteration (s): 5.44 | learning rate: 1.185E-04 | global batch size: 512 | lm loss: 4.782953E+00 | loss scale: 32768.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.179 | TFLOPs: 71.13 | +[default7]: iteration 1642/ 3814 | consumed samples: 840704 | consumed tokens: 1721761792 | elapsed time per iteration (s): 5.46 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 4.744569E+00 | loss scale: 32768.0 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.833 | TFLOPs: 70.87 | +[default7]: iteration 1643/ 3814 | consumed samples: 841216 | consumed tokens: 1722810368 | elapsed time per iteration (s): 5.44 | learning rate: 1.183E-04 | global batch size: 512 | lm loss: 4.785697E+00 | loss scale: 32768.0 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.055 | TFLOPs: 71.04 | +[default7]: iteration 1644/ 3814 | consumed samples: 841728 | consumed tokens: 1723858944 | elapsed time per iteration (s): 5.46 | learning rate: 1.182E-04 | global batch size: 512 | lm loss: 4.788050E+00 | loss scale: 32768.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.809 | TFLOPs: 70.85 | +[default7]: iteration 1645/ 3814 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 5.46 | learning rate: 1.182E-04 | global batch size: 512 | lm loss: 4.769583E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.856 | TFLOPs: 70.89 | +[default7]: iteration 1646/ 3814 | consumed samples: 842752 | consumed tokens: 1725956096 | elapsed time per iteration (s): 5.45 | learning rate: 1.181E-04 | global batch size: 512 | lm loss: 4.770851E+00 | loss scale: 32768.0 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.955 | TFLOPs: 70.97 | +[default7]: iteration 1647/ 3814 | consumed samples: 843264 | consumed tokens: 1727004672 | elapsed time per iteration (s): 5.46 | learning rate: 1.180E-04 | global batch size: 512 | lm loss: 4.767031E+00 | loss scale: 32768.0 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.844 | TFLOPs: 70.88 | +[default7]: iteration 1648/ 3814 | consumed samples: 843776 | consumed tokens: 1728053248 | elapsed time per iteration (s): 5.47 | learning rate: 1.180E-04 | global batch size: 512 | lm loss: 4.764016E+00 | loss scale: 32768.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.619 | TFLOPs: 70.71 | +[default7]: iteration 1649/ 3814 | consumed samples: 844288 | consumed tokens: 1729101824 | elapsed time per iteration (s): 5.44 | learning rate: 1.179E-04 | global batch size: 512 | lm loss: 4.795223E+00 | loss scale: 32768.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 1650/ 3814 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 5.44 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 4.766329E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.109 | TFLOPs: 71.08 | +[default7]: iteration 1651/ 3814 | consumed samples: 845312 | consumed tokens: 1731198976 | elapsed time per iteration (s): 5.46 | learning rate: 1.177E-04 | global batch size: 512 | lm loss: 4.764896E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.751 | TFLOPs: 70.81 | +[default7]: iteration 1652/ 3814 | consumed samples: 845824 | consumed tokens: 1732247552 | elapsed time per iteration (s): 5.45 | learning rate: 1.177E-04 | global batch size: 512 | lm loss: 4.765356E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.891 | TFLOPs: 70.92 | +[default7]: iteration 1653/ 3814 | consumed samples: 846336 | consumed tokens: 1733296128 | elapsed time per iteration (s): 5.45 | learning rate: 1.176E-04 | global batch size: 512 | lm loss: 4.790979E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.90 | +[default7]: iteration 1654/ 3814 | consumed samples: 846848 | consumed tokens: 1734344704 | elapsed time per iteration (s): 5.46 | learning rate: 1.175E-04 | global batch size: 512 | lm loss: 4.765110E+00 | loss scale: 32768.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.693 | TFLOPs: 70.77 | +[default7]: iteration 1655/ 3814 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 5.44 | learning rate: 1.175E-04 | global batch size: 512 | lm loss: 4.745649E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.038 | TFLOPs: 71.03 | +[default7]: iteration 1656/ 3814 | consumed samples: 847872 | consumed tokens: 1736441856 | elapsed time per iteration (s): 5.46 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 4.758584E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.698 | TFLOPs: 70.77 | +[default7]: iteration 1657/ 3814 | consumed samples: 848384 | consumed tokens: 1737490432 | elapsed time per iteration (s): 5.45 | learning rate: 1.173E-04 | global batch size: 512 | lm loss: 4.771522E+00 | loss scale: 32768.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.947 | TFLOPs: 70.96 | +[default7]: iteration 1658/ 3814 | consumed samples: 848896 | consumed tokens: 1738539008 | elapsed time per iteration (s): 5.48 | learning rate: 1.172E-04 | global batch size: 512 | lm loss: 4.772478E+00 | loss scale: 32768.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.462 | TFLOPs: 70.59 | +[default7]: iteration 1659/ 3814 | consumed samples: 849408 | consumed tokens: 1739587584 | elapsed time per iteration (s): 5.46 | learning rate: 1.172E-04 | global batch size: 512 | lm loss: 4.748184E+00 | loss scale: 32768.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.831 | TFLOPs: 70.87 | +[default7]: iteration 1660/ 3814 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 5.46 | learning rate: 1.171E-04 | global batch size: 512 | lm loss: 4.759898E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.721 | TFLOPs: 70.79 | +[default7]: iteration 1661/ 3814 | consumed samples: 850432 | consumed tokens: 1741684736 | elapsed time per iteration (s): 5.46 | learning rate: 1.170E-04 | global batch size: 512 | lm loss: 4.775535E+00 | loss scale: 32768.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.723 | TFLOPs: 70.79 | +[default7]: iteration 1662/ 3814 | consumed samples: 850944 | consumed tokens: 1742733312 | elapsed time per iteration (s): 5.46 | learning rate: 1.170E-04 | global batch size: 512 | lm loss: 4.768692E+00 | loss scale: 32768.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.848 | TFLOPs: 70.88 | +[default7]: iteration 1663/ 3814 | consumed samples: 851456 | consumed tokens: 1743781888 | elapsed time per iteration (s): 5.46 | learning rate: 1.169E-04 | global batch size: 512 | lm loss: 4.792974E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 1664/ 3814 | consumed samples: 851968 | consumed tokens: 1744830464 | elapsed time per iteration (s): 5.45 | learning rate: 1.168E-04 | global batch size: 512 | lm loss: 4.755178E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.893 | TFLOPs: 70.92 | +[default7]: iteration 1665/ 3814 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 5.46 | learning rate: 1.167E-04 | global batch size: 512 | lm loss: 4.744099E+00 | loss scale: 32768.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.732 | TFLOPs: 70.80 | +[default7]: iteration 1666/ 3814 | consumed samples: 852992 | consumed tokens: 1746927616 | elapsed time per iteration (s): 5.45 | learning rate: 1.167E-04 | global batch size: 512 | lm loss: 4.759628E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.881 | TFLOPs: 70.91 | +[default7]: iteration 1667/ 3814 | consumed samples: 853504 | consumed tokens: 1747976192 | elapsed time per iteration (s): 5.47 | learning rate: 1.166E-04 | global batch size: 512 | lm loss: 4.779835E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.599 | TFLOPs: 70.70 | +[default7]: iteration 1668/ 3814 | consumed samples: 854016 | consumed tokens: 1749024768 | elapsed time per iteration (s): 5.47 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 4.707099E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.670 | TFLOPs: 70.75 | +[default7]: iteration 1669/ 3814 | consumed samples: 854528 | consumed tokens: 1750073344 | elapsed time per iteration (s): 5.45 | learning rate: 1.165E-04 | global batch size: 512 | lm loss: 4.769068E+00 | loss scale: 32768.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.870 | TFLOPs: 70.90 | +[default7]: iteration 1670/ 3814 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 5.46 | learning rate: 1.164E-04 | global batch size: 512 | lm loss: 4.780560E+00 | loss scale: 32768.0 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.858 | TFLOPs: 70.89 | +[default7]: iteration 1671/ 3814 | consumed samples: 855552 | consumed tokens: 1752170496 | elapsed time per iteration (s): 5.48 | learning rate: 1.163E-04 | global batch size: 512 | lm loss: 4.738100E+00 | loss scale: 32768.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.500 | TFLOPs: 70.62 | +[default7]: iteration 1672/ 3814 | consumed samples: 856064 | consumed tokens: 1753219072 | elapsed time per iteration (s): 5.47 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 4.780312E+00 | loss scale: 32768.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.594 | TFLOPs: 70.69 | +[default7]: iteration 1673/ 3814 | consumed samples: 856576 | consumed tokens: 1754267648 | elapsed time per iteration (s): 5.48 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 4.736232E+00 | loss scale: 32768.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.359 | TFLOPs: 70.52 | +[default7]: iteration 1674/ 3814 | consumed samples: 857088 | consumed tokens: 1755316224 | elapsed time per iteration (s): 5.46 | learning rate: 1.161E-04 | global batch size: 512 | lm loss: 4.760742E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.858 | TFLOPs: 70.89 | +[default7]: iteration 1675/ 3814 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 5.46 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 4.769538E+00 | loss scale: 32768.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.807 | TFLOPs: 70.85 | +[default7]: iteration 1676/ 3814 | consumed samples: 858112 | consumed tokens: 1757413376 | elapsed time per iteration (s): 5.45 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 4.731789E+00 | loss scale: 32768.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.905 | TFLOPs: 70.93 | +[default7]: iteration 1677/ 3814 | consumed samples: 858624 | consumed tokens: 1758461952 | elapsed time per iteration (s): 5.47 | learning rate: 1.159E-04 | global batch size: 512 | lm loss: 4.760980E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.659 | TFLOPs: 70.74 | +[default7]: iteration 1678/ 3814 | consumed samples: 859136 | consumed tokens: 1759510528 | elapsed time per iteration (s): 5.45 | learning rate: 1.158E-04 | global batch size: 512 | lm loss: 4.746889E+00 | loss scale: 32768.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.917 | TFLOPs: 70.94 | +[default7]: iteration 1679/ 3814 | consumed samples: 859648 | consumed tokens: 1760559104 | elapsed time per iteration (s): 5.44 | learning rate: 1.157E-04 | global batch size: 512 | lm loss: 4.761226E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 1680/ 3814 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 5.44 | learning rate: 1.157E-04 | global batch size: 512 | lm loss: 4.732499E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.123 | TFLOPs: 71.09 | +[default7]: iteration 1681/ 3814 | consumed samples: 860672 | consumed tokens: 1762656256 | elapsed time per iteration (s): 5.45 | learning rate: 1.156E-04 | global batch size: 512 | lm loss: 4.763763E+00 | loss scale: 32768.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 1682/ 3814 | consumed samples: 861184 | consumed tokens: 1763704832 | elapsed time per iteration (s): 5.46 | learning rate: 1.155E-04 | global batch size: 512 | lm loss: 4.746994E+00 | loss scale: 32768.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.807 | TFLOPs: 70.85 | +[default7]: iteration 1683/ 3814 | consumed samples: 861696 | consumed tokens: 1764753408 | elapsed time per iteration (s): 5.47 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 4.766830E+00 | loss scale: 32768.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.564 | TFLOPs: 70.67 | +[default7]: iteration 1684/ 3814 | consumed samples: 862208 | consumed tokens: 1765801984 | elapsed time per iteration (s): 5.46 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 4.732801E+00 | loss scale: 32768.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.848 | TFLOPs: 70.88 | +[default7]: iteration 1685/ 3814 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 5.47 | learning rate: 1.153E-04 | global batch size: 512 | lm loss: 4.766997E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.602 | TFLOPs: 70.70 | +[default7]: iteration 1686/ 3814 | consumed samples: 863232 | consumed tokens: 1767899136 | elapsed time per iteration (s): 5.47 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 4.745280E+00 | loss scale: 32768.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.544 | TFLOPs: 70.65 | +[default7]: iteration 1687/ 3814 | consumed samples: 863744 | consumed tokens: 1768947712 | elapsed time per iteration (s): 5.45 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 4.766908E+00 | loss scale: 32768.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.016 | TFLOPs: 71.01 | +[default7]: iteration 1688/ 3814 | consumed samples: 864256 | consumed tokens: 1769996288 | elapsed time per iteration (s): 5.45 | learning rate: 1.151E-04 | global batch size: 512 | lm loss: 4.749379E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.942 | TFLOPs: 70.96 | +[default7]: iteration 1689/ 3814 | consumed samples: 864768 | consumed tokens: 1771044864 | elapsed time per iteration (s): 5.44 | learning rate: 1.150E-04 | global batch size: 512 | lm loss: 4.738942E+00 | loss scale: 32768.0 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 1690/ 3814 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 5.46 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 4.745144E+00 | loss scale: 32768.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.767 | TFLOPs: 70.82 | +[default7]: iteration 1691/ 3814 | consumed samples: 865792 | consumed tokens: 1773142016 | elapsed time per iteration (s): 5.44 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 4.739493E+00 | loss scale: 32768.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.075 | TFLOPs: 71.06 | +[default7]: iteration 1692/ 3814 | consumed samples: 866304 | consumed tokens: 1774190592 | elapsed time per iteration (s): 5.45 | learning rate: 1.148E-04 | global batch size: 512 | lm loss: 4.781138E+00 | loss scale: 32768.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.012 | TFLOPs: 71.01 | +[default7]: iteration 1693/ 3814 | consumed samples: 866816 | consumed tokens: 1775239168 | elapsed time per iteration (s): 5.46 | learning rate: 1.147E-04 | global batch size: 512 | lm loss: 4.744629E+00 | loss scale: 32768.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.757 | TFLOPs: 70.82 | +[default7]: iteration 1694/ 3814 | consumed samples: 867328 | consumed tokens: 1776287744 | elapsed time per iteration (s): 5.43 | learning rate: 1.147E-04 | global batch size: 512 | lm loss: 4.750660E+00 | loss scale: 32768.0 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.244 | TFLOPs: 71.18 | +[default7]: iteration 1695/ 3814 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 5.45 | learning rate: 1.146E-04 | global batch size: 512 | lm loss: 4.727031E+00 | loss scale: 32768.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.938 | TFLOPs: 70.95 | +[default7]: iteration 1696/ 3814 | consumed samples: 868352 | consumed tokens: 1778384896 | elapsed time per iteration (s): 5.45 | learning rate: 1.145E-04 | global batch size: 512 | lm loss: 4.738885E+00 | loss scale: 32768.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.934 | TFLOPs: 70.95 | +[default7]: iteration 1697/ 3814 | consumed samples: 868864 | consumed tokens: 1779433472 | elapsed time per iteration (s): 5.45 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 4.756821E+00 | loss scale: 32768.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.986 | TFLOPs: 70.99 | +[default7]: iteration 1698/ 3814 | consumed samples: 869376 | consumed tokens: 1780482048 | elapsed time per iteration (s): 5.44 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 4.737885E+00 | loss scale: 32768.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.034 | TFLOPs: 71.02 | +[default7]: iteration 1699/ 3814 | consumed samples: 869888 | consumed tokens: 1781530624 | elapsed time per iteration (s): 5.46 | learning rate: 1.143E-04 | global batch size: 512 | lm loss: 4.727823E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.734 | TFLOPs: 70.80 | +[default7]: iteration 1700/ 3814 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 5.47 | learning rate: 1.142E-04 | global batch size: 512 | lm loss: 4.750954E+00 | loss scale: 32768.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.565 | TFLOPs: 70.67 | +[default7]: iteration 1701/ 3814 | consumed samples: 870912 | consumed tokens: 1783627776 | elapsed time per iteration (s): 5.48 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 4.727320E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.408 | TFLOPs: 70.55 | +[default7]: iteration 1702/ 3814 | consumed samples: 871424 | consumed tokens: 1784676352 | elapsed time per iteration (s): 5.48 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 4.742568E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.452 | TFLOPs: 70.58 | +[default7]: iteration 1703/ 3814 | consumed samples: 871936 | consumed tokens: 1785724928 | elapsed time per iteration (s): 5.52 | learning rate: 1.140E-04 | global batch size: 512 | lm loss: 4.731103E+00 | loss scale: 32768.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 92.808 | TFLOPs: 70.10 | +[default7]: iteration 1704/ 3814 | consumed samples: 872448 | consumed tokens: 1786773504 | elapsed time per iteration (s): 5.45 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 4.737612E+00 | loss scale: 32768.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.954 | TFLOPs: 70.96 | +[default7]: iteration 1705/ 3814 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 5.45 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 4.728578E+00 | loss scale: 32768.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.001 | TFLOPs: 71.00 | +[default7]: iteration 1706/ 3814 | consumed samples: 873472 | consumed tokens: 1788870656 | elapsed time per iteration (s): 5.45 | learning rate: 1.138E-04 | global batch size: 512 | lm loss: 4.754846E+00 | loss scale: 32768.0 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.026 | TFLOPs: 71.02 | +[default7]: iteration 1707/ 3814 | consumed samples: 873984 | consumed tokens: 1789919232 | elapsed time per iteration (s): 5.45 | learning rate: 1.137E-04 | global batch size: 512 | lm loss: 4.727213E+00 | loss scale: 32768.0 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.892 | TFLOPs: 70.92 | +[default7]: iteration 1708/ 3814 | consumed samples: 874496 | consumed tokens: 1790967808 | elapsed time per iteration (s): 5.45 | learning rate: 1.136E-04 | global batch size: 512 | lm loss: 4.733772E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.963 | TFLOPs: 70.97 | +[default7]: iteration 1709/ 3814 | consumed samples: 875008 | consumed tokens: 1792016384 | elapsed time per iteration (s): 5.45 | learning rate: 1.136E-04 | global batch size: 512 | lm loss: 4.733488E+00 | loss scale: 32768.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.923 | TFLOPs: 70.94 | +[default7]: iteration 1710/ 3814 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 5.44 | learning rate: 1.135E-04 | global batch size: 512 | lm loss: 4.725793E+00 | loss scale: 32768.0 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.043 | TFLOPs: 71.03 | +[default7]: iteration 1711/ 3814 | consumed samples: 876032 | consumed tokens: 1794113536 | elapsed time per iteration (s): 5.45 | learning rate: 1.134E-04 | global batch size: 512 | lm loss: 4.732636E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.968 | TFLOPs: 70.97 | +[default7]: iteration 1712/ 3814 | consumed samples: 876544 | consumed tokens: 1795162112 | elapsed time per iteration (s): 5.46 | learning rate: 1.133E-04 | global batch size: 512 | lm loss: 4.713387E+00 | loss scale: 32768.0 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.842 | TFLOPs: 70.88 | +[default7]: iteration 1713/ 3814 | consumed samples: 877056 | consumed tokens: 1796210688 | elapsed time per iteration (s): 5.45 | learning rate: 1.133E-04 | global batch size: 512 | lm loss: 4.726791E+00 | loss scale: 32768.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.016 | TFLOPs: 71.01 | +[default7]: iteration 1714/ 3814 | consumed samples: 877568 | consumed tokens: 1797259264 | elapsed time per iteration (s): 5.43 | learning rate: 1.132E-04 | global batch size: 512 | lm loss: 4.721269E+00 | loss scale: 32768.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.257 | TFLOPs: 71.19 | +[default7]: iteration 1715/ 3814 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 5.44 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 4.716145E+00 | loss scale: 32768.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.163 | TFLOPs: 71.12 | +[default7]: iteration 1716/ 3814 | consumed samples: 878592 | consumed tokens: 1799356416 | elapsed time per iteration (s): 5.45 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 4.733264E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.009 | TFLOPs: 71.01 | +[default7]: iteration 1717/ 3814 | consumed samples: 879104 | consumed tokens: 1800404992 | elapsed time per iteration (s): 5.46 | learning rate: 1.130E-04 | global batch size: 512 | lm loss: 4.723214E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.794 | TFLOPs: 70.84 | +[default7]: iteration 1718/ 3814 | consumed samples: 879616 | consumed tokens: 1801453568 | elapsed time per iteration (s): 5.44 | learning rate: 1.129E-04 | global batch size: 512 | lm loss: 4.736583E+00 | loss scale: 32768.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.096 | TFLOPs: 71.07 | +[default7]: iteration 1719/ 3814 | consumed samples: 880128 | consumed tokens: 1802502144 | elapsed time per iteration (s): 5.44 | learning rate: 1.128E-04 | global batch size: 512 | lm loss: 4.728541E+00 | loss scale: 32768.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.090 | TFLOPs: 71.07 | +[default7]: iteration 1720/ 3814 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 5.47 | learning rate: 1.128E-04 | global batch size: 512 | lm loss: 4.726245E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.581 | TFLOPs: 70.68 | +[default7]: iteration 1721/ 3814 | consumed samples: 881152 | consumed tokens: 1804599296 | elapsed time per iteration (s): 5.45 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 4.722492E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.915 | TFLOPs: 70.93 | +[default7]: iteration 1722/ 3814 | consumed samples: 881664 | consumed tokens: 1805647872 | elapsed time per iteration (s): 5.46 | learning rate: 1.126E-04 | global batch size: 512 | lm loss: 4.719245E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.804 | TFLOPs: 70.85 | +[default7]: iteration 1723/ 3814 | consumed samples: 882176 | consumed tokens: 1806696448 | elapsed time per iteration (s): 5.46 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 4.681391E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.690 | TFLOPs: 70.77 | +[default7]: iteration 1724/ 3814 | consumed samples: 882688 | consumed tokens: 1807745024 | elapsed time per iteration (s): 5.46 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 4.716878E+00 | loss scale: 32768.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.790 | TFLOPs: 70.84 | +[default7]: iteration 1725/ 3814 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 5.48 | learning rate: 1.124E-04 | global batch size: 512 | lm loss: 4.700488E+00 | loss scale: 32768.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.395 | TFLOPs: 70.54 | +[default7]: iteration 1726/ 3814 | consumed samples: 883712 | consumed tokens: 1809842176 | elapsed time per iteration (s): 5.47 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 4.717879E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.653 | TFLOPs: 70.74 | +[default7]: iteration 1727/ 3814 | consumed samples: 884224 | consumed tokens: 1810890752 | elapsed time per iteration (s): 5.45 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 4.737057E+00 | loss scale: 32768.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.882 | TFLOPs: 70.91 | +[default7]: iteration 1728/ 3814 | consumed samples: 884736 | consumed tokens: 1811939328 | elapsed time per iteration (s): 5.46 | learning rate: 1.122E-04 | global batch size: 512 | lm loss: 4.715423E+00 | loss scale: 32768.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.720 | TFLOPs: 70.79 | +[default7]: iteration 1729/ 3814 | consumed samples: 885248 | consumed tokens: 1812987904 | elapsed time per iteration (s): 5.47 | learning rate: 1.121E-04 | global batch size: 512 | lm loss: 4.749941E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.603 | TFLOPs: 70.70 | +[default7]: iteration 1730/ 3814 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 5.46 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 4.723337E+00 | loss scale: 32768.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.785 | TFLOPs: 70.84 | +[default7]: iteration 1731/ 3814 | consumed samples: 886272 | consumed tokens: 1815085056 | elapsed time per iteration (s): 5.48 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 4.709738E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.467 | TFLOPs: 70.60 | +[default7]: iteration 1732/ 3814 | consumed samples: 886784 | consumed tokens: 1816133632 | elapsed time per iteration (s): 5.46 | learning rate: 1.119E-04 | global batch size: 512 | lm loss: 4.735427E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.758 | TFLOPs: 70.82 | +[default7]: iteration 1733/ 3814 | consumed samples: 887296 | consumed tokens: 1817182208 | elapsed time per iteration (s): 5.47 | learning rate: 1.118E-04 | global batch size: 512 | lm loss: 4.693318E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.518 | TFLOPs: 70.63 | +[default7]: iteration 1734/ 3814 | consumed samples: 887808 | consumed tokens: 1818230784 | elapsed time per iteration (s): 5.47 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 4.704624E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.683 | TFLOPs: 70.76 | +[default7]: iteration 1735/ 3814 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 5.46 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 4.701613E+00 | loss scale: 32768.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.731 | TFLOPs: 70.80 | +[default7]: iteration 1736/ 3814 | consumed samples: 888832 | consumed tokens: 1820327936 | elapsed time per iteration (s): 5.46 | learning rate: 1.116E-04 | global batch size: 512 | lm loss: 4.717681E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.703 | TFLOPs: 70.77 | +[default7]: iteration 1737/ 3814 | consumed samples: 889344 | consumed tokens: 1821376512 | elapsed time per iteration (s): 5.45 | learning rate: 1.115E-04 | global batch size: 512 | lm loss: 4.720580E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1738/ 3814 | consumed samples: 889856 | consumed tokens: 1822425088 | elapsed time per iteration (s): 5.47 | learning rate: 1.114E-04 | global batch size: 512 | lm loss: 4.715726E+00 | loss scale: 32768.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.620 | TFLOPs: 70.71 | +[default7]: iteration 1739/ 3814 | consumed samples: 890368 | consumed tokens: 1823473664 | elapsed time per iteration (s): 5.47 | learning rate: 1.114E-04 | global batch size: 512 | lm loss: 4.707571E+00 | loss scale: 32768.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.620 | TFLOPs: 70.71 | +[default7]: iteration 1740/ 3814 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 5.47 | learning rate: 1.113E-04 | global batch size: 512 | lm loss: 4.696026E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.676 | TFLOPs: 70.75 | +[default7]: iteration 1741/ 3814 | consumed samples: 891392 | consumed tokens: 1825570816 | elapsed time per iteration (s): 5.46 | learning rate: 1.112E-04 | global batch size: 512 | lm loss: 4.715469E+00 | loss scale: 32768.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.745 | TFLOPs: 70.81 | +[default7]: iteration 1742/ 3814 | consumed samples: 891904 | consumed tokens: 1826619392 | elapsed time per iteration (s): 5.46 | learning rate: 1.112E-04 | global batch size: 512 | lm loss: 4.718806E+00 | loss scale: 32768.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.826 | TFLOPs: 70.87 | +[default7]: iteration 1743/ 3814 | consumed samples: 892416 | consumed tokens: 1827667968 | elapsed time per iteration (s): 5.45 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 4.724098E+00 | loss scale: 32768.0 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.906 | TFLOPs: 70.93 | +[default7]: iteration 1744/ 3814 | consumed samples: 892928 | consumed tokens: 1828716544 | elapsed time per iteration (s): 5.45 | learning rate: 1.110E-04 | global batch size: 512 | lm loss: 4.708377E+00 | loss scale: 32768.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.879 | TFLOPs: 70.91 | +[default7]: iteration 1745/ 3814 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 5.46 | learning rate: 1.109E-04 | global batch size: 512 | lm loss: 4.698699E+00 | loss scale: 32768.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.779 | TFLOPs: 70.83 | +[default7]: iteration 1746/ 3814 | consumed samples: 893952 | consumed tokens: 1830813696 | elapsed time per iteration (s): 5.46 | learning rate: 1.109E-04 | global batch size: 512 | lm loss: 4.705235E+00 | loss scale: 32768.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.744 | TFLOPs: 70.81 | +[default7]: iteration 1747/ 3814 | consumed samples: 894464 | consumed tokens: 1831862272 | elapsed time per iteration (s): 5.46 | learning rate: 1.108E-04 | global batch size: 512 | lm loss: 4.710393E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.758 | TFLOPs: 70.82 | +[default7]: iteration 1748/ 3814 | consumed samples: 894976 | consumed tokens: 1832910848 | elapsed time per iteration (s): 5.48 | learning rate: 1.107E-04 | global batch size: 512 | lm loss: 4.722951E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.458 | TFLOPs: 70.59 | +[default7]: iteration 1749/ 3814 | consumed samples: 895488 | consumed tokens: 1833959424 | elapsed time per iteration (s): 5.46 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 4.696909E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.793 | TFLOPs: 70.84 | +[default7]: iteration 1750/ 3814 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 5.47 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 4.676532E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.672 | TFLOPs: 70.75 | +[default1]:[2023-02-16 13:58:36,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 1750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 13:58:36,228] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1750 is begin to save! +[default0]:[2023-02-16 13:58:36,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:36,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:36,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,449] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,456] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:36,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:36,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,614] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:36,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,679] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:36,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:36,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,797] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,783] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:36,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,854] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:36,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:36,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:36,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:36,947] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:36,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:36,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,005] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,079] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,080] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,058] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,114] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,134] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,187] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,223] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,243] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,333] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,352] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,387] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,441] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,459] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,496] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,742] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,764] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,817] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,799] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:37,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,853] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,876] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:37,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:37,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:37,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:37,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:37,967] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:38,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:38,023] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:38,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:38,046] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:38,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:38,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 13:58:38,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:38,079] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:38,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:38,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 13:58:38,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:38,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:38,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:38,214] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 13:58:38,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 13:58:38,216] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 13:58:38,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 13:58:38,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt. +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:58:38,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:38,185] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 13:58:38,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 13:58:38,187] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 13:58:38,187] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 13:58:38,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 13:58:38,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 13:58:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,738] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,753] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,775] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,765] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,782] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,765] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,785] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,794] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,823] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,797] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,750] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,758] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,752] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,779] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,844] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,882] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,868] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,802] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,822] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,845] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,888] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,811] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,851] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,828] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:38,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:38,842] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:38,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,910] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,910] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,910] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,837] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,875] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:38,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:38,863] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:38,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,894] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,857] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:38,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:38,882] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:38,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:38,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:38,902] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:38,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,861] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,880] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,924] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,919] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:38,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:38,886] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:38,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,916] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,883] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:38,914] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:38,914] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:38,914] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,951] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,951] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:38,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:38,943] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:38,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,970] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:38,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:38,919] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:38,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:38,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:38,924] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:38,924] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:38,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:38,990] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:38,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:38,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:38,941] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:38,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:39,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:39,013] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:39,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:39,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:39,023] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:39,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:39,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:39,023] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:39,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:39,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:39,008] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:39,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 13:58:39,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 13:58:39,021] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 13:58:39,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 13:58:39,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:39,000] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:39,000] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:39,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:39,040] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:39,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:39,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:39,008] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:39,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 13:58:38,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:38,985] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:38,985] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 13:58:39,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 13:58:39,065] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 13:58:39,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 13:58:39,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 13:58:39,004] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 13:58:39,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 13:58:39,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 13:58:39,044] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 13:58:39,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]: successfully saved checkpoint at iteration 1750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default5]:[2023-02-16 13:58:39,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 13:58:39,029] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 13:58:39,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 13:58:39,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 13:58:39,063] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 13:58:39,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:time (ms) | save-checkpoint: 2882.06 +[default7]:[2023-02-16 13:58:39,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 13:58:39,108] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 13:58:39,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 13:58:39,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 13:58:39,094] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 13:58:39,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]: iteration 1751/ 3814 | consumed samples: 896512 | consumed tokens: 1836056576 | elapsed time per iteration (s): 8.32 | learning rate: 1.105E-04 | global batch size: 512 | lm loss: 4.703920E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 61.519 | TFLOPs: 46.47 | +[default7]: iteration 1752/ 3814 | consumed samples: 897024 | consumed tokens: 1837105152 | elapsed time per iteration (s): 5.45 | learning rate: 1.104E-04 | global batch size: 512 | lm loss: 4.692410E+00 | loss scale: 32768.0 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.935 | TFLOPs: 70.95 | +[default7]: iteration 1753/ 3814 | consumed samples: 897536 | consumed tokens: 1838153728 | elapsed time per iteration (s): 5.46 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 4.708048E+00 | loss scale: 32768.0 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.842 | TFLOPs: 70.88 | +[default7]: iteration 1754/ 3814 | consumed samples: 898048 | consumed tokens: 1839202304 | elapsed time per iteration (s): 5.44 | learning rate: 1.103E-04 | global batch size: 512 | lm loss: 4.716537E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.061 | TFLOPs: 71.05 | +[default7]: iteration 1755/ 3814 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 5.45 | learning rate: 1.102E-04 | global batch size: 512 | lm loss: 4.699402E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.986 | TFLOPs: 70.99 | +[default7]: iteration 1756/ 3814 | consumed samples: 899072 | consumed tokens: 1841299456 | elapsed time per iteration (s): 5.44 | learning rate: 1.101E-04 | global batch size: 512 | lm loss: 4.697158E+00 | loss scale: 32768.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.055 | TFLOPs: 71.04 | +[default7]: iteration 1757/ 3814 | consumed samples: 899584 | consumed tokens: 1842348032 | elapsed time per iteration (s): 5.44 | learning rate: 1.100E-04 | global batch size: 512 | lm loss: 4.704868E+00 | loss scale: 32768.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.156 | TFLOPs: 71.12 | +[default7]: iteration 1758/ 3814 | consumed samples: 900096 | consumed tokens: 1843396608 | elapsed time per iteration (s): 5.46 | learning rate: 1.100E-04 | global batch size: 512 | lm loss: 4.685421E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.838 | TFLOPs: 70.88 | +[default7]: iteration 1759/ 3814 | consumed samples: 900608 | consumed tokens: 1844445184 | elapsed time per iteration (s): 5.46 | learning rate: 1.099E-04 | global batch size: 512 | lm loss: 4.706551E+00 | loss scale: 32768.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.826 | TFLOPs: 70.87 | +[default7]: iteration 1760/ 3814 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 5.45 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 4.684457E+00 | loss scale: 32768.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.894 | TFLOPs: 70.92 | +[default7]: iteration 1761/ 3814 | consumed samples: 901632 | consumed tokens: 1846542336 | elapsed time per iteration (s): 5.44 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 4.689311E+00 | loss scale: 32768.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.055 | TFLOPs: 71.04 | +[default7]: iteration 1762/ 3814 | consumed samples: 902144 | consumed tokens: 1847590912 | elapsed time per iteration (s): 5.46 | learning rate: 1.097E-04 | global batch size: 512 | lm loss: 4.690544E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.821 | TFLOPs: 70.86 | +[default7]: iteration 1763/ 3814 | consumed samples: 902656 | consumed tokens: 1848639488 | elapsed time per iteration (s): 5.47 | learning rate: 1.096E-04 | global batch size: 512 | lm loss: 4.725049E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.641 | TFLOPs: 70.73 | +[default7]: iteration 1764/ 3814 | consumed samples: 903168 | consumed tokens: 1849688064 | elapsed time per iteration (s): 5.47 | learning rate: 1.095E-04 | global batch size: 512 | lm loss: 4.723684E+00 | loss scale: 32768.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.587 | TFLOPs: 70.69 | +[default7]: iteration 1765/ 3814 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 5.46 | learning rate: 1.095E-04 | global batch size: 512 | lm loss: 4.691799E+00 | loss scale: 32768.0 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.858 | TFLOPs: 70.89 | +[default7]: iteration 1766/ 3814 | consumed samples: 904192 | consumed tokens: 1851785216 | elapsed time per iteration (s): 5.47 | learning rate: 1.094E-04 | global batch size: 512 | lm loss: 4.685299E+00 | loss scale: 32768.0 | grad norm: 0.453 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.527 | TFLOPs: 70.64 | +[default7]: iteration 1767/ 3814 | consumed samples: 904704 | consumed tokens: 1852833792 | elapsed time per iteration (s): 5.46 | learning rate: 1.093E-04 | global batch size: 512 | lm loss: 4.704016E+00 | loss scale: 32768.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.754 | TFLOPs: 70.81 | +[default7]: iteration 1768/ 3814 | consumed samples: 905216 | consumed tokens: 1853882368 | elapsed time per iteration (s): 5.45 | learning rate: 1.092E-04 | global batch size: 512 | lm loss: 4.731534E+00 | loss scale: 32768.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.950 | TFLOPs: 70.96 | +[default7]: iteration 1769/ 3814 | consumed samples: 905728 | consumed tokens: 1854930944 | elapsed time per iteration (s): 5.48 | learning rate: 1.092E-04 | global batch size: 512 | lm loss: 4.716983E+00 | loss scale: 32768.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.444 | TFLOPs: 70.58 | +[default7]: iteration 1770/ 3814 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 5.48 | learning rate: 1.091E-04 | global batch size: 512 | lm loss: 4.671546E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.353 | TFLOPs: 70.51 | +[default7]: iteration 1771/ 3814 | consumed samples: 906752 | consumed tokens: 1857028096 | elapsed time per iteration (s): 5.44 | learning rate: 1.090E-04 | global batch size: 512 | lm loss: 4.704595E+00 | loss scale: 32768.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 1772/ 3814 | consumed samples: 907264 | consumed tokens: 1858076672 | elapsed time per iteration (s): 5.48 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 4.688340E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.480 | TFLOPs: 70.61 | +[default7]: iteration 1773/ 3814 | consumed samples: 907776 | consumed tokens: 1859125248 | elapsed time per iteration (s): 5.46 | learning rate: 1.089E-04 | global batch size: 512 | lm loss: 4.685565E+00 | loss scale: 32768.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.801 | TFLOPs: 70.85 | +[default7]: iteration 1774/ 3814 | consumed samples: 908288 | consumed tokens: 1860173824 | elapsed time per iteration (s): 5.46 | learning rate: 1.088E-04 | global batch size: 512 | lm loss: 4.667248E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.812 | TFLOPs: 70.86 | +[default7]: iteration 1775/ 3814 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 5.45 | learning rate: 1.087E-04 | global batch size: 512 | lm loss: 4.688711E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.877 | TFLOPs: 70.91 | +[default7]: iteration 1776/ 3814 | consumed samples: 909312 | consumed tokens: 1862270976 | elapsed time per iteration (s): 5.46 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 4.678284E+00 | loss scale: 32768.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.799 | TFLOPs: 70.85 | +[default7]: iteration 1777/ 3814 | consumed samples: 909824 | consumed tokens: 1863319552 | elapsed time per iteration (s): 5.47 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 4.692427E+00 | loss scale: 32768.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.658 | TFLOPs: 70.74 | +[default7]: iteration 1778/ 3814 | consumed samples: 910336 | consumed tokens: 1864368128 | elapsed time per iteration (s): 5.46 | learning rate: 1.085E-04 | global batch size: 512 | lm loss: 4.689891E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.708 | TFLOPs: 70.78 | +[default7]: iteration 1779/ 3814 | consumed samples: 910848 | consumed tokens: 1865416704 | elapsed time per iteration (s): 5.48 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 4.654809E+00 | loss scale: 32768.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.420 | TFLOPs: 70.56 | +[default7]: iteration 1780/ 3814 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 5.45 | learning rate: 1.083E-04 | global batch size: 512 | lm loss: 4.670369E+00 | loss scale: 32768.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1781/ 3814 | consumed samples: 911872 | consumed tokens: 1867513856 | elapsed time per iteration (s): 5.47 | learning rate: 1.083E-04 | global batch size: 512 | lm loss: 4.676673E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.521 | TFLOPs: 70.64 | +[default7]: iteration 1782/ 3814 | consumed samples: 912384 | consumed tokens: 1868562432 | elapsed time per iteration (s): 5.48 | learning rate: 1.082E-04 | global batch size: 512 | lm loss: 4.664999E+00 | loss scale: 32768.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.382 | TFLOPs: 70.53 | +[default7]: iteration 1783/ 3814 | consumed samples: 912896 | consumed tokens: 1869611008 | elapsed time per iteration (s): 5.48 | learning rate: 1.081E-04 | global batch size: 512 | lm loss: 4.674204E+00 | loss scale: 32768.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.505 | TFLOPs: 70.63 | +[default7]: iteration 1784/ 3814 | consumed samples: 913408 | consumed tokens: 1870659584 | elapsed time per iteration (s): 5.44 | learning rate: 1.080E-04 | global batch size: 512 | lm loss: 4.662861E+00 | loss scale: 32768.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.087 | TFLOPs: 71.06 | +[default7]: iteration 1785/ 3814 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 5.47 | learning rate: 1.080E-04 | global batch size: 512 | lm loss: 4.690360E+00 | loss scale: 32768.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.586 | TFLOPs: 70.69 | +[default7]: iteration 1786/ 3814 | consumed samples: 914432 | consumed tokens: 1872756736 | elapsed time per iteration (s): 5.46 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 4.693444E+00 | loss scale: 32768.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.743 | TFLOPs: 70.81 | +[default7]: iteration 1787/ 3814 | consumed samples: 914944 | consumed tokens: 1873805312 | elapsed time per iteration (s): 5.44 | learning rate: 1.078E-04 | global batch size: 512 | lm loss: 4.678818E+00 | loss scale: 32768.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.134 | TFLOPs: 71.10 | +[default7]: iteration 1788/ 3814 | consumed samples: 915456 | consumed tokens: 1874853888 | elapsed time per iteration (s): 5.44 | learning rate: 1.078E-04 | global batch size: 512 | lm loss: 4.677126E+00 | loss scale: 32768.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.100 | TFLOPs: 71.07 | +[default7]: iteration 1789/ 3814 | consumed samples: 915968 | consumed tokens: 1875902464 | elapsed time per iteration (s): 5.45 | learning rate: 1.077E-04 | global batch size: 512 | lm loss: 4.691978E+00 | loss scale: 32768.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.003 | TFLOPs: 71.00 | +[default7]: iteration 1790/ 3814 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 5.46 | learning rate: 1.076E-04 | global batch size: 512 | lm loss: 4.704538E+00 | loss scale: 32768.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.787 | TFLOPs: 70.84 | +[default7]: iteration 1791/ 3814 | consumed samples: 916992 | consumed tokens: 1877999616 | elapsed time per iteration (s): 5.44 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 4.673013E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 1792/ 3814 | consumed samples: 917504 | consumed tokens: 1879048192 | elapsed time per iteration (s): 5.45 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 4.700624E+00 | loss scale: 32768.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.863 | TFLOPs: 70.90 | +[default7]: iteration 1793/ 3814 | consumed samples: 918016 | consumed tokens: 1880096768 | elapsed time per iteration (s): 5.46 | learning rate: 1.074E-04 | global batch size: 512 | lm loss: 4.672366E+00 | loss scale: 32768.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.773 | TFLOPs: 70.83 | +[default7]: iteration 1794/ 3814 | consumed samples: 918528 | consumed tokens: 1881145344 | elapsed time per iteration (s): 5.44 | learning rate: 1.073E-04 | global batch size: 512 | lm loss: 4.689821E+00 | loss scale: 32768.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.069 | TFLOPs: 71.05 | +[default7]: iteration 1795/ 3814 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 5.46 | learning rate: 1.072E-04 | global batch size: 512 | lm loss: 4.658365E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.831 | TFLOPs: 70.87 | +[default7]: iteration 1796/ 3814 | consumed samples: 919552 | consumed tokens: 1883242496 | elapsed time per iteration (s): 5.45 | learning rate: 1.072E-04 | global batch size: 512 | lm loss: 4.681365E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.931 | TFLOPs: 70.95 | +[default7]: iteration 1797/ 3814 | consumed samples: 920064 | consumed tokens: 1884291072 | elapsed time per iteration (s): 5.46 | learning rate: 1.071E-04 | global batch size: 512 | lm loss: 4.674818E+00 | loss scale: 32768.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.832 | TFLOPs: 70.87 | +[default7]: iteration 1798/ 3814 | consumed samples: 920576 | consumed tokens: 1885339648 | elapsed time per iteration (s): 5.43 | learning rate: 1.070E-04 | global batch size: 512 | lm loss: 4.647834E+00 | loss scale: 32768.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.289 | TFLOPs: 71.22 | +[default7]: iteration 1799/ 3814 | consumed samples: 921088 | consumed tokens: 1886388224 | elapsed time per iteration (s): 5.45 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 4.687032E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 1800/ 3814 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 5.44 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 4.672611E+00 | loss scale: 32768.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.161 | TFLOPs: 71.12 | +[default7]: iteration 1801/ 3814 | consumed samples: 922112 | consumed tokens: 1888485376 | elapsed time per iteration (s): 5.47 | learning rate: 1.068E-04 | global batch size: 512 | lm loss: 4.669076E+00 | loss scale: 32768.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.546 | TFLOPs: 70.66 | +[default7]: iteration 1802/ 3814 | consumed samples: 922624 | consumed tokens: 1889533952 | elapsed time per iteration (s): 5.46 | learning rate: 1.067E-04 | global batch size: 512 | lm loss: 4.653149E+00 | loss scale: 32768.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.752 | TFLOPs: 70.81 | +[default7]: iteration 1803/ 3814 | consumed samples: 923136 | consumed tokens: 1890582528 | elapsed time per iteration (s): 5.44 | learning rate: 1.066E-04 | global batch size: 512 | lm loss: 4.671153E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 1804/ 3814 | consumed samples: 923648 | consumed tokens: 1891631104 | elapsed time per iteration (s): 5.45 | learning rate: 1.066E-04 | global batch size: 512 | lm loss: 4.673843E+00 | loss scale: 32768.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 1805/ 3814 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 5.46 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 4.675381E+00 | loss scale: 32768.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.765 | TFLOPs: 70.82 | +[default7]: iteration 1806/ 3814 | consumed samples: 924672 | consumed tokens: 1893728256 | elapsed time per iteration (s): 5.45 | learning rate: 1.064E-04 | global batch size: 512 | lm loss: 4.644230E+00 | loss scale: 32768.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.012 | TFLOPs: 71.01 | +[default7]: iteration 1807/ 3814 | consumed samples: 925184 | consumed tokens: 1894776832 | elapsed time per iteration (s): 5.44 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 4.656935E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.117 | TFLOPs: 71.09 | +[default7]: iteration 1808/ 3814 | consumed samples: 925696 | consumed tokens: 1895825408 | elapsed time per iteration (s): 5.44 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 4.666531E+00 | loss scale: 32768.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.197 | TFLOPs: 71.15 | +[default7]: iteration 1809/ 3814 | consumed samples: 926208 | consumed tokens: 1896873984 | elapsed time per iteration (s): 5.46 | learning rate: 1.062E-04 | global batch size: 512 | lm loss: 4.679423E+00 | loss scale: 32768.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.846 | TFLOPs: 70.88 | +[default7]: iteration 1810/ 3814 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 5.44 | learning rate: 1.061E-04 | global batch size: 512 | lm loss: 4.641409E+00 | loss scale: 32768.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.099 | TFLOPs: 71.07 | +[default7]: iteration 1811/ 3814 | consumed samples: 927232 | consumed tokens: 1898971136 | elapsed time per iteration (s): 5.44 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 4.666923E+00 | loss scale: 32768.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.180 | TFLOPs: 71.13 | +[default7]: iteration 1812/ 3814 | consumed samples: 927744 | consumed tokens: 1900019712 | elapsed time per iteration (s): 5.44 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 4.679564E+00 | loss scale: 32768.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.152 | TFLOPs: 71.11 | +[default7]: iteration 1813/ 3814 | consumed samples: 928256 | consumed tokens: 1901068288 | elapsed time per iteration (s): 5.45 | learning rate: 1.059E-04 | global batch size: 512 | lm loss: 4.662350E+00 | loss scale: 32768.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.977 | TFLOPs: 70.98 | +[default7]: iteration 1814/ 3814 | consumed samples: 928768 | consumed tokens: 1902116864 | elapsed time per iteration (s): 5.46 | learning rate: 1.058E-04 | global batch size: 512 | lm loss: 4.652250E+00 | loss scale: 32768.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.825 | TFLOPs: 70.87 | +[default7]: iteration 1815/ 3814 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 5.46 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 4.649155E+00 | loss scale: 32768.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.713 | TFLOPs: 70.78 | +[default7]: iteration 1816/ 3814 | consumed samples: 929792 | consumed tokens: 1904214016 | elapsed time per iteration (s): 5.48 | learning rate: 1.057E-04 | global batch size: 512 | lm loss: 4.656361E+00 | loss scale: 32768.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.481 | TFLOPs: 70.61 | +[default7]: iteration 1817/ 3814 | consumed samples: 930304 | consumed tokens: 1905262592 | elapsed time per iteration (s): 5.45 | learning rate: 1.056E-04 | global batch size: 512 | lm loss: 4.659534E+00 | loss scale: 32768.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.946 | TFLOPs: 70.96 | +[default7]: iteration 1818/ 3814 | consumed samples: 930816 | consumed tokens: 1906311168 | elapsed time per iteration (s): 5.45 | learning rate: 1.055E-04 | global batch size: 512 | lm loss: 4.662024E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.025 | TFLOPs: 71.02 | +[default7]: iteration 1819/ 3814 | consumed samples: 931328 | consumed tokens: 1907359744 | elapsed time per iteration (s): 5.47 | learning rate: 1.054E-04 | global batch size: 512 | lm loss: 4.678576E+00 | loss scale: 32768.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.622 | TFLOPs: 70.71 | +[default7]: iteration 1820/ 3814 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 5.46 | learning rate: 1.054E-04 | global batch size: 512 | lm loss: 4.653054E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.796 | TFLOPs: 70.84 | +[default7]: iteration 1821/ 3814 | consumed samples: 932352 | consumed tokens: 1909456896 | elapsed time per iteration (s): 5.45 | learning rate: 1.053E-04 | global batch size: 512 | lm loss: 4.664270E+00 | loss scale: 32768.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.883 | TFLOPs: 70.91 | +[default7]: iteration 1822/ 3814 | consumed samples: 932864 | consumed tokens: 1910505472 | elapsed time per iteration (s): 5.46 | learning rate: 1.052E-04 | global batch size: 512 | lm loss: 4.653888E+00 | loss scale: 32768.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.708 | TFLOPs: 70.78 | +[default7]: iteration 1823/ 3814 | consumed samples: 933376 | consumed tokens: 1911554048 | elapsed time per iteration (s): 5.47 | learning rate: 1.051E-04 | global batch size: 512 | lm loss: 4.651220E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.528 | TFLOPs: 70.64 | +[default7]: iteration 1824/ 3814 | consumed samples: 933888 | consumed tokens: 1912602624 | elapsed time per iteration (s): 5.48 | learning rate: 1.051E-04 | global batch size: 512 | lm loss: 4.635427E+00 | loss scale: 32768.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.514 | TFLOPs: 70.63 | +[default7]: iteration 1825/ 3814 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 5.47 | learning rate: 1.050E-04 | global batch size: 512 | lm loss: 4.626842E+00 | loss scale: 32768.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.543 | TFLOPs: 70.65 | +[default7]: iteration 1826/ 3814 | consumed samples: 934912 | consumed tokens: 1914699776 | elapsed time per iteration (s): 5.47 | learning rate: 1.049E-04 | global batch size: 512 | lm loss: 4.649333E+00 | loss scale: 32768.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.673 | TFLOPs: 70.75 | +[default7]: iteration 1827/ 3814 | consumed samples: 935424 | consumed tokens: 1915748352 | elapsed time per iteration (s): 5.45 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 4.666372E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.939 | TFLOPs: 70.95 | +[default7]: iteration 1828/ 3814 | consumed samples: 935936 | consumed tokens: 1916796928 | elapsed time per iteration (s): 5.46 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 4.654003E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.854 | TFLOPs: 70.89 | +[default7]: iteration 1829/ 3814 | consumed samples: 936448 | consumed tokens: 1917845504 | elapsed time per iteration (s): 5.46 | learning rate: 1.047E-04 | global batch size: 512 | lm loss: 4.628225E+00 | loss scale: 32768.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.777 | TFLOPs: 70.83 | +[default7]: iteration 1830/ 3814 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 5.46 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 4.652021E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.855 | TFLOPs: 70.89 | +[default7]: iteration 1831/ 3814 | consumed samples: 937472 | consumed tokens: 1919942656 | elapsed time per iteration (s): 5.45 | learning rate: 1.045E-04 | global batch size: 512 | lm loss: 4.642107E+00 | loss scale: 32768.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.962 | TFLOPs: 70.97 | +[default7]: iteration 1832/ 3814 | consumed samples: 937984 | consumed tokens: 1920991232 | elapsed time per iteration (s): 5.46 | learning rate: 1.045E-04 | global batch size: 512 | lm loss: 4.641970E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.839 | TFLOPs: 70.88 | +[default7]: iteration 1833/ 3814 | consumed samples: 938496 | consumed tokens: 1922039808 | elapsed time per iteration (s): 5.47 | learning rate: 1.044E-04 | global batch size: 512 | lm loss: 4.660508E+00 | loss scale: 32768.0 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.610 | TFLOPs: 70.70 | +[default7]: iteration 1834/ 3814 | consumed samples: 939008 | consumed tokens: 1923088384 | elapsed time per iteration (s): 5.45 | learning rate: 1.043E-04 | global batch size: 512 | lm loss: 4.648737E+00 | loss scale: 32768.0 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.917 | TFLOPs: 70.94 | +[default7]: iteration 1835/ 3814 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 5.45 | learning rate: 1.042E-04 | global batch size: 512 | lm loss: 4.667592E+00 | loss scale: 32768.0 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.927 | TFLOPs: 70.94 | +[default7]: iteration 1836/ 3814 | consumed samples: 940032 | consumed tokens: 1925185536 | elapsed time per iteration (s): 5.45 | learning rate: 1.042E-04 | global batch size: 512 | lm loss: 4.665679E+00 | loss scale: 32768.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.897 | TFLOPs: 70.92 | +[default7]: iteration 1837/ 3814 | consumed samples: 940544 | consumed tokens: 1926234112 | elapsed time per iteration (s): 5.45 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 4.689733E+00 | loss scale: 32768.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.871 | TFLOPs: 70.90 | +[default7]: iteration 1838/ 3814 | consumed samples: 941056 | consumed tokens: 1927282688 | elapsed time per iteration (s): 5.47 | learning rate: 1.040E-04 | global batch size: 512 | lm loss: 4.661473E+00 | loss scale: 32768.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.520 | TFLOPs: 70.64 | +[default7]: iteration 1839/ 3814 | consumed samples: 941568 | consumed tokens: 1928331264 | elapsed time per iteration (s): 5.47 | learning rate: 1.039E-04 | global batch size: 512 | lm loss: 4.630226E+00 | loss scale: 32768.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.682 | TFLOPs: 70.76 | +[default7]: iteration 1840/ 3814 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 5.48 | learning rate: 1.039E-04 | global batch size: 512 | lm loss: 4.623364E+00 | loss scale: 32768.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.352 | TFLOPs: 70.51 | +[default7]: iteration 1841/ 3814 | consumed samples: 942592 | consumed tokens: 1930428416 | elapsed time per iteration (s): 5.49 | learning rate: 1.038E-04 | global batch size: 512 | lm loss: 4.617039E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.227 | TFLOPs: 70.42 | +[default7]: iteration 1842/ 3814 | consumed samples: 943104 | consumed tokens: 1931476992 | elapsed time per iteration (s): 5.49 | learning rate: 1.037E-04 | global batch size: 512 | lm loss: 4.638774E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.200 | TFLOPs: 70.40 | +[default7]: iteration 1843/ 3814 | consumed samples: 943616 | consumed tokens: 1932525568 | elapsed time per iteration (s): 5.50 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 4.650394E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.101 | TFLOPs: 70.32 | +[default7]: iteration 1844/ 3814 | consumed samples: 944128 | consumed tokens: 1933574144 | elapsed time per iteration (s): 5.48 | learning rate: 1.036E-04 | global batch size: 512 | lm loss: 4.647875E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.405 | TFLOPs: 70.55 | +[default7]: iteration 1845/ 3814 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 5.48 | learning rate: 1.035E-04 | global batch size: 512 | lm loss: 4.625604E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.358 | TFLOPs: 70.51 | +[default7]: iteration 1846/ 3814 | consumed samples: 945152 | consumed tokens: 1935671296 | elapsed time per iteration (s): 5.45 | learning rate: 1.034E-04 | global batch size: 512 | lm loss: 4.606248E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 1847/ 3814 | consumed samples: 945664 | consumed tokens: 1936719872 | elapsed time per iteration (s): 5.46 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 4.646855E+00 | loss scale: 32768.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.805 | TFLOPs: 70.85 | +[default7]: iteration 1848/ 3814 | consumed samples: 946176 | consumed tokens: 1937768448 | elapsed time per iteration (s): 5.46 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 4.641088E+00 | loss scale: 32768.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.783 | TFLOPs: 70.84 | +[default7]: iteration 1849/ 3814 | consumed samples: 946688 | consumed tokens: 1938817024 | elapsed time per iteration (s): 5.47 | learning rate: 1.032E-04 | global batch size: 512 | lm loss: 4.668555E+00 | loss scale: 32768.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.591 | TFLOPs: 70.69 | +[default7]: iteration 1850/ 3814 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 5.45 | learning rate: 1.031E-04 | global batch size: 512 | lm loss: 4.625287E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.886 | TFLOPs: 70.91 | +[default7]: iteration 1851/ 3814 | consumed samples: 947712 | consumed tokens: 1940914176 | elapsed time per iteration (s): 5.46 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 4.624249E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 1852/ 3814 | consumed samples: 948224 | consumed tokens: 1941962752 | elapsed time per iteration (s): 5.47 | learning rate: 1.030E-04 | global batch size: 512 | lm loss: 4.631860E+00 | loss scale: 32768.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.668 | TFLOPs: 70.75 | +[default7]: iteration 1853/ 3814 | consumed samples: 948736 | consumed tokens: 1943011328 | elapsed time per iteration (s): 5.46 | learning rate: 1.029E-04 | global batch size: 512 | lm loss: 4.636198E+00 | loss scale: 32768.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.825 | TFLOPs: 70.87 | +[default7]: iteration 1854/ 3814 | consumed samples: 949248 | consumed tokens: 1944059904 | elapsed time per iteration (s): 5.45 | learning rate: 1.028E-04 | global batch size: 512 | lm loss: 4.661757E+00 | loss scale: 32768.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.910 | TFLOPs: 70.93 | +[default7]: iteration 1855/ 3814 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 5.45 | learning rate: 1.027E-04 | global batch size: 512 | lm loss: 4.648646E+00 | loss scale: 32768.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.024 | TFLOPs: 71.02 | +[default7]: iteration 1856/ 3814 | consumed samples: 950272 | consumed tokens: 1946157056 | elapsed time per iteration (s): 5.45 | learning rate: 1.026E-04 | global batch size: 512 | lm loss: 4.610474E+00 | loss scale: 32768.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.901 | TFLOPs: 70.92 | +[default7]: iteration 1857/ 3814 | consumed samples: 950784 | consumed tokens: 1947205632 | elapsed time per iteration (s): 5.45 | learning rate: 1.026E-04 | global batch size: 512 | lm loss: 4.625597E+00 | loss scale: 32768.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.027 | TFLOPs: 71.02 | +[default7]: iteration 1858/ 3814 | consumed samples: 951296 | consumed tokens: 1948254208 | elapsed time per iteration (s): 5.45 | learning rate: 1.025E-04 | global batch size: 512 | lm loss: 4.648355E+00 | loss scale: 32768.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.989 | TFLOPs: 70.99 | +[default7]: iteration 1859/ 3814 | consumed samples: 951808 | consumed tokens: 1949302784 | elapsed time per iteration (s): 5.44 | learning rate: 1.024E-04 | global batch size: 512 | lm loss: 4.615052E+00 | loss scale: 32768.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.099 | TFLOPs: 71.07 | +[default7]: iteration 1860/ 3814 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 5.46 | learning rate: 1.023E-04 | global batch size: 512 | lm loss: 4.635680E+00 | loss scale: 32768.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.777 | TFLOPs: 70.83 | +[default7]: iteration 1861/ 3814 | consumed samples: 952832 | consumed tokens: 1951399936 | elapsed time per iteration (s): 5.46 | learning rate: 1.023E-04 | global batch size: 512 | lm loss: 4.612261E+00 | loss scale: 32768.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.759 | TFLOPs: 70.82 | +[default7]: iteration 1862/ 3814 | consumed samples: 953344 | consumed tokens: 1952448512 | elapsed time per iteration (s): 5.45 | learning rate: 1.022E-04 | global batch size: 512 | lm loss: 4.626225E+00 | loss scale: 32768.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.959 | TFLOPs: 70.97 | +[default7]: iteration 1863/ 3814 | consumed samples: 953856 | consumed tokens: 1953497088 | elapsed time per iteration (s): 5.45 | learning rate: 1.021E-04 | global batch size: 512 | lm loss: 4.646163E+00 | loss scale: 32768.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 1864/ 3814 | consumed samples: 954368 | consumed tokens: 1954545664 | elapsed time per iteration (s): 5.45 | learning rate: 1.020E-04 | global batch size: 512 | lm loss: 4.629185E+00 | loss scale: 32768.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.882 | TFLOPs: 70.91 | +[default7]: iteration 1865/ 3814 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 5.45 | learning rate: 1.020E-04 | global batch size: 512 | lm loss: 4.625241E+00 | loss scale: 32768.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.003 | TFLOPs: 71.00 | +[default7]: iteration 1866/ 3814 | consumed samples: 955392 | consumed tokens: 1956642816 | elapsed time per iteration (s): 5.45 | learning rate: 1.019E-04 | global batch size: 512 | lm loss: 4.627463E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.897 | TFLOPs: 70.92 | +[default7]: iteration 1867/ 3814 | consumed samples: 955904 | consumed tokens: 1957691392 | elapsed time per iteration (s): 5.45 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 4.600708E+00 | loss scale: 32768.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 1868/ 3814 | consumed samples: 956416 | consumed tokens: 1958739968 | elapsed time per iteration (s): 5.45 | learning rate: 1.017E-04 | global batch size: 512 | lm loss: 4.627954E+00 | loss scale: 32768.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.029 | TFLOPs: 71.02 | +[default7]: iteration 1869/ 3814 | consumed samples: 956928 | consumed tokens: 1959788544 | elapsed time per iteration (s): 5.45 | learning rate: 1.017E-04 | global batch size: 512 | lm loss: 4.616646E+00 | loss scale: 32768.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.888 | TFLOPs: 70.91 | +[default7]: iteration 1870/ 3814 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 5.45 | learning rate: 1.016E-04 | global batch size: 512 | lm loss: 4.599949E+00 | loss scale: 32768.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.864 | TFLOPs: 70.90 | +[default7]: iteration 1871/ 3814 | consumed samples: 957952 | consumed tokens: 1961885696 | elapsed time per iteration (s): 5.44 | learning rate: 1.015E-04 | global batch size: 512 | lm loss: 4.596817E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 1872/ 3814 | consumed samples: 958464 | consumed tokens: 1962934272 | elapsed time per iteration (s): 5.43 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 4.611609E+00 | loss scale: 32768.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.239 | TFLOPs: 71.18 | +[default7]: iteration 1873/ 3814 | consumed samples: 958976 | consumed tokens: 1963982848 | elapsed time per iteration (s): 5.45 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 4.648922E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 1874/ 3814 | consumed samples: 959488 | consumed tokens: 1965031424 | elapsed time per iteration (s): 5.45 | learning rate: 1.013E-04 | global batch size: 512 | lm loss: 4.622826E+00 | loss scale: 32768.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.908 | TFLOPs: 70.93 | +[default7]: iteration 1875/ 3814 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 5.46 | learning rate: 1.012E-04 | global batch size: 512 | lm loss: 4.635674E+00 | loss scale: 32768.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.853 | TFLOPs: 70.89 | +[default7]: iteration 1876/ 3814 | consumed samples: 960512 | consumed tokens: 1967128576 | elapsed time per iteration (s): 5.45 | learning rate: 1.011E-04 | global batch size: 512 | lm loss: 4.618641E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.981 | TFLOPs: 70.98 | +[default7]: iteration 1877/ 3814 | consumed samples: 961024 | consumed tokens: 1968177152 | elapsed time per iteration (s): 5.44 | learning rate: 1.011E-04 | global batch size: 512 | lm loss: 4.618596E+00 | loss scale: 32768.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.136 | TFLOPs: 71.10 | +[default7]: iteration 1878/ 3814 | consumed samples: 961536 | consumed tokens: 1969225728 | elapsed time per iteration (s): 5.45 | learning rate: 1.010E-04 | global batch size: 512 | lm loss: 4.619318E+00 | loss scale: 32768.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.89 | +[default7]: iteration 1879/ 3814 | consumed samples: 962048 | consumed tokens: 1970274304 | elapsed time per iteration (s): 5.43 | learning rate: 1.009E-04 | global batch size: 512 | lm loss: 4.613330E+00 | loss scale: 32768.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.310 | TFLOPs: 71.23 | +[default7]: iteration 1880/ 3814 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 5.43 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 4.657822E+00 | loss scale: 32768.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.339 | TFLOPs: 71.26 | +[default7]: iteration 1881/ 3814 | consumed samples: 963072 | consumed tokens: 1972371456 | elapsed time per iteration (s): 5.44 | learning rate: 1.008E-04 | global batch size: 512 | lm loss: 4.619240E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.143 | TFLOPs: 71.11 | +[default7]: iteration 1882/ 3814 | consumed samples: 963584 | consumed tokens: 1973420032 | elapsed time per iteration (s): 5.46 | learning rate: 1.007E-04 | global batch size: 512 | lm loss: 4.620292E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.798 | TFLOPs: 70.85 | +[default7]: iteration 1883/ 3814 | consumed samples: 964096 | consumed tokens: 1974468608 | elapsed time per iteration (s): 5.44 | learning rate: 1.006E-04 | global batch size: 512 | lm loss: 4.620101E+00 | loss scale: 32768.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.044 | TFLOPs: 71.03 | +[default7]: iteration 1884/ 3814 | consumed samples: 964608 | consumed tokens: 1975517184 | elapsed time per iteration (s): 5.45 | learning rate: 1.005E-04 | global batch size: 512 | lm loss: 4.634860E+00 | loss scale: 32768.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.006 | TFLOPs: 71.00 | +[default7]: iteration 1885/ 3814 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 5.44 | learning rate: 1.005E-04 | global batch size: 512 | lm loss: 4.638376E+00 | loss scale: 32768.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.079 | TFLOPs: 71.06 | +[default7]: iteration 1886/ 3814 | consumed samples: 965632 | consumed tokens: 1977614336 | elapsed time per iteration (s): 5.45 | learning rate: 1.004E-04 | global batch size: 512 | lm loss: 4.590636E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.966 | TFLOPs: 70.97 | +[default7]: iteration 1887/ 3814 | consumed samples: 966144 | consumed tokens: 1978662912 | elapsed time per iteration (s): 5.44 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 4.644829E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.097 | TFLOPs: 71.07 | +[default7]: iteration 1888/ 3814 | consumed samples: 966656 | consumed tokens: 1979711488 | elapsed time per iteration (s): 5.42 | learning rate: 1.002E-04 | global batch size: 512 | lm loss: 4.620299E+00 | loss scale: 32768.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.407 | TFLOPs: 71.31 | +[default7]: iteration 1889/ 3814 | consumed samples: 967168 | consumed tokens: 1980760064 | elapsed time per iteration (s): 5.40 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 4.611484E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.743 | TFLOPs: 71.56 | +[default7]: iteration 1890/ 3814 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 5.43 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 4.608237E+00 | loss scale: 32768.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 1891/ 3814 | consumed samples: 968192 | consumed tokens: 1982857216 | elapsed time per iteration (s): 5.44 | learning rate: 1.000E-04 | global batch size: 512 | lm loss: 4.609026E+00 | loss scale: 32768.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.141 | TFLOPs: 71.11 | +[default7]: iteration 1892/ 3814 | consumed samples: 968704 | consumed tokens: 1983905792 | elapsed time per iteration (s): 5.44 | learning rate: 9.992E-05 | global batch size: 512 | lm loss: 4.649868E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.110 | TFLOPs: 71.08 | +[default7]: iteration 1893/ 3814 | consumed samples: 969216 | consumed tokens: 1984954368 | elapsed time per iteration (s): 5.42 | learning rate: 9.984E-05 | global batch size: 512 | lm loss: 4.601906E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.436 | TFLOPs: 71.33 | +[default7]: iteration 1894/ 3814 | consumed samples: 969728 | consumed tokens: 1986002944 | elapsed time per iteration (s): 5.44 | learning rate: 9.977E-05 | global batch size: 512 | lm loss: 4.605451E+00 | loss scale: 32768.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.124 | TFLOPs: 71.09 | +[default7]: iteration 1895/ 3814 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 5.44 | learning rate: 9.969E-05 | global batch size: 512 | lm loss: 4.596756E+00 | loss scale: 32768.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.044 | TFLOPs: 71.03 | +[default7]: iteration 1896/ 3814 | consumed samples: 970752 | consumed tokens: 1988100096 | elapsed time per iteration (s): 5.42 | learning rate: 9.962E-05 | global batch size: 512 | lm loss: 4.647355E+00 | loss scale: 32768.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.399 | TFLOPs: 71.30 | +[default7]: iteration 1897/ 3814 | consumed samples: 971264 | consumed tokens: 1989148672 | elapsed time per iteration (s): 5.42 | learning rate: 9.954E-05 | global batch size: 512 | lm loss: 4.614803E+00 | loss scale: 32768.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.390 | TFLOPs: 71.29 | +[default7]: iteration 1898/ 3814 | consumed samples: 971776 | consumed tokens: 1990197248 | elapsed time per iteration (s): 5.43 | learning rate: 9.946E-05 | global batch size: 512 | lm loss: 4.624329E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.252 | TFLOPs: 71.19 | +[default7]: iteration 1899/ 3814 | consumed samples: 972288 | consumed tokens: 1991245824 | elapsed time per iteration (s): 5.45 | learning rate: 9.939E-05 | global batch size: 512 | lm loss: 4.614864E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.994 | TFLOPs: 70.99 | +[default7]: iteration 1900/ 3814 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 5.46 | learning rate: 9.931E-05 | global batch size: 512 | lm loss: 4.593512E+00 | loss scale: 32768.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.711 | TFLOPs: 70.78 | +[default7]: iteration 1901/ 3814 | consumed samples: 973312 | consumed tokens: 1993342976 | elapsed time per iteration (s): 5.48 | learning rate: 9.924E-05 | global batch size: 512 | lm loss: 4.596262E+00 | loss scale: 32768.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.471 | TFLOPs: 70.60 | +[default7]: iteration 1902/ 3814 | consumed samples: 973824 | consumed tokens: 1994391552 | elapsed time per iteration (s): 5.47 | learning rate: 9.916E-05 | global batch size: 512 | lm loss: 4.617615E+00 | loss scale: 32768.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.676 | TFLOPs: 70.75 | +[default7]: iteration 1903/ 3814 | consumed samples: 974336 | consumed tokens: 1995440128 | elapsed time per iteration (s): 5.45 | learning rate: 9.908E-05 | global batch size: 512 | lm loss: 4.618670E+00 | loss scale: 32768.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.913 | TFLOPs: 70.93 | +[default7]: iteration 1904/ 3814 | consumed samples: 974848 | consumed tokens: 1996488704 | elapsed time per iteration (s): 5.47 | learning rate: 9.901E-05 | global batch size: 512 | lm loss: 4.594509E+00 | loss scale: 32768.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.572 | TFLOPs: 70.68 | +[default7]: iteration 1905/ 3814 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 5.47 | learning rate: 9.893E-05 | global batch size: 512 | lm loss: 4.630579E+00 | loss scale: 32768.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.684 | TFLOPs: 70.76 | +[default7]: iteration 1906/ 3814 | consumed samples: 975872 | consumed tokens: 1998585856 | elapsed time per iteration (s): 5.47 | learning rate: 9.885E-05 | global batch size: 512 | lm loss: 4.591660E+00 | loss scale: 32768.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.625 | TFLOPs: 70.72 | +[default7]: iteration 1907/ 3814 | consumed samples: 976384 | consumed tokens: 1999634432 | elapsed time per iteration (s): 5.47 | learning rate: 9.878E-05 | global batch size: 512 | lm loss: 4.604711E+00 | loss scale: 32768.0 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.621 | TFLOPs: 70.71 | +[default7]: iteration 1908/ 3814 | consumed samples: 976896 | consumed tokens: 2000683008 | elapsed time per iteration (s): 5.46 | learning rate: 9.870E-05 | global batch size: 512 | lm loss: 4.650023E+00 | loss scale: 32768.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.731 | TFLOPs: 70.80 | +[default7]: iteration 1909/ 3814 | consumed samples: 977408 | consumed tokens: 2001731584 | elapsed time per iteration (s): 5.47 | learning rate: 9.863E-05 | global batch size: 512 | lm loss: 4.625462E+00 | loss scale: 32768.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.649 | TFLOPs: 70.73 | +[default7]: iteration 1910/ 3814 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 5.45 | learning rate: 9.855E-05 | global batch size: 512 | lm loss: 4.607483E+00 | loss scale: 32768.0 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.996 | TFLOPs: 71.00 | +[default7]: iteration 1911/ 3814 | consumed samples: 978432 | consumed tokens: 2003828736 | elapsed time per iteration (s): 5.47 | learning rate: 9.847E-05 | global batch size: 512 | lm loss: 4.595215E+00 | loss scale: 32768.0 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.570 | TFLOPs: 70.67 | +[default7]: iteration 1912/ 3814 | consumed samples: 978944 | consumed tokens: 2004877312 | elapsed time per iteration (s): 5.46 | learning rate: 9.840E-05 | global batch size: 512 | lm loss: 4.590663E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.741 | TFLOPs: 70.80 | +[default7]: iteration 1913/ 3814 | consumed samples: 979456 | consumed tokens: 2005925888 | elapsed time per iteration (s): 5.45 | learning rate: 9.832E-05 | global batch size: 512 | lm loss: 4.604550E+00 | loss scale: 32768.0 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.951 | TFLOPs: 70.96 | +[default7]: iteration 1914/ 3814 | consumed samples: 979968 | consumed tokens: 2006974464 | elapsed time per iteration (s): 5.45 | learning rate: 9.824E-05 | global batch size: 512 | lm loss: 4.601260E+00 | loss scale: 32768.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.933 | TFLOPs: 70.95 | +[default7]: iteration 1915/ 3814 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 5.46 | learning rate: 9.817E-05 | global batch size: 512 | lm loss: 4.586534E+00 | loss scale: 32768.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.765 | TFLOPs: 70.82 | +[default7]: iteration 1916/ 3814 | consumed samples: 980992 | consumed tokens: 2009071616 | elapsed time per iteration (s): 5.48 | learning rate: 9.809E-05 | global batch size: 512 | lm loss: 4.567101E+00 | loss scale: 32768.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.490 | TFLOPs: 70.61 | +[default7]: iteration 1917/ 3814 | consumed samples: 981504 | consumed tokens: 2010120192 | elapsed time per iteration (s): 5.46 | learning rate: 9.802E-05 | global batch size: 512 | lm loss: 4.601591E+00 | loss scale: 32768.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.717 | TFLOPs: 70.79 | +[default7]: iteration 1918/ 3814 | consumed samples: 982016 | consumed tokens: 2011168768 | elapsed time per iteration (s): 5.47 | learning rate: 9.794E-05 | global batch size: 512 | lm loss: 4.585199E+00 | loss scale: 32768.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.636 | TFLOPs: 70.72 | +[default7]: iteration 1919/ 3814 | consumed samples: 982528 | consumed tokens: 2012217344 | elapsed time per iteration (s): 5.45 | learning rate: 9.786E-05 | global batch size: 512 | lm loss: 4.568165E+00 | loss scale: 32768.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.900 | TFLOPs: 70.92 | +[default7]: iteration 1920/ 3814 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 5.45 | learning rate: 9.779E-05 | global batch size: 512 | lm loss: 4.599655E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.936 | TFLOPs: 70.95 | +[default7]: iteration 1921/ 3814 | consumed samples: 983552 | consumed tokens: 2014314496 | elapsed time per iteration (s): 5.45 | learning rate: 9.771E-05 | global batch size: 512 | lm loss: 4.593354E+00 | loss scale: 32768.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.901 | TFLOPs: 70.92 | +[default7]: iteration 1922/ 3814 | consumed samples: 984064 | consumed tokens: 2015363072 | elapsed time per iteration (s): 5.47 | learning rate: 9.763E-05 | global batch size: 512 | lm loss: 4.596706E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.666 | TFLOPs: 70.75 | +[default7]: iteration 1923/ 3814 | consumed samples: 984576 | consumed tokens: 2016411648 | elapsed time per iteration (s): 5.47 | learning rate: 9.756E-05 | global batch size: 512 | lm loss: 4.588316E+00 | loss scale: 32768.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.684 | TFLOPs: 70.76 | +[default7]: iteration 1924/ 3814 | consumed samples: 985088 | consumed tokens: 2017460224 | elapsed time per iteration (s): 5.45 | learning rate: 9.748E-05 | global batch size: 512 | lm loss: 4.623971E+00 | loss scale: 32768.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.925 | TFLOPs: 70.94 | +[default7]: iteration 1925/ 3814 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 5.46 | learning rate: 9.740E-05 | global batch size: 512 | lm loss: 4.614601E+00 | loss scale: 32768.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.735 | TFLOPs: 70.80 | +[default7]: iteration 1926/ 3814 | consumed samples: 986112 | consumed tokens: 2019557376 | elapsed time per iteration (s): 5.44 | learning rate: 9.733E-05 | global batch size: 512 | lm loss: 4.598593E+00 | loss scale: 32768.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.035 | TFLOPs: 71.03 | +[default7]: iteration 1927/ 3814 | consumed samples: 986624 | consumed tokens: 2020605952 | elapsed time per iteration (s): 5.46 | learning rate: 9.725E-05 | global batch size: 512 | lm loss: 4.596164E+00 | loss scale: 32768.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.726 | TFLOPs: 70.79 | +[default7]: iteration 1928/ 3814 | consumed samples: 987136 | consumed tokens: 2021654528 | elapsed time per iteration (s): 5.45 | learning rate: 9.717E-05 | global batch size: 512 | lm loss: 4.612191E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.931 | TFLOPs: 70.95 | +[default7]: iteration 1929/ 3814 | consumed samples: 987648 | consumed tokens: 2022703104 | elapsed time per iteration (s): 5.45 | learning rate: 9.710E-05 | global batch size: 512 | lm loss: 4.584521E+00 | loss scale: 32768.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.980 | TFLOPs: 70.98 | +[default7]: iteration 1930/ 3814 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 5.46 | learning rate: 9.702E-05 | global batch size: 512 | lm loss: 4.614274E+00 | loss scale: 32768.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.763 | TFLOPs: 70.82 | +[default7]: iteration 1931/ 3814 | consumed samples: 988672 | consumed tokens: 2024800256 | elapsed time per iteration (s): 5.45 | learning rate: 9.695E-05 | global batch size: 512 | lm loss: 4.567648E+00 | loss scale: 32768.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.882 | TFLOPs: 70.91 | +[default7]: iteration 1932/ 3814 | consumed samples: 989184 | consumed tokens: 2025848832 | elapsed time per iteration (s): 5.47 | learning rate: 9.687E-05 | global batch size: 512 | lm loss: 4.589433E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.631 | TFLOPs: 70.72 | +[default7]: iteration 1933/ 3814 | consumed samples: 989696 | consumed tokens: 2026897408 | elapsed time per iteration (s): 5.45 | learning rate: 9.679E-05 | global batch size: 512 | lm loss: 4.619996E+00 | loss scale: 32768.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.004 | TFLOPs: 71.00 | +[default7]: iteration 1934/ 3814 | consumed samples: 990208 | consumed tokens: 2027945984 | elapsed time per iteration (s): 5.44 | learning rate: 9.672E-05 | global batch size: 512 | lm loss: 4.595838E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.040 | TFLOPs: 71.03 | +[default7]: iteration 1935/ 3814 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 5.47 | learning rate: 9.664E-05 | global batch size: 512 | lm loss: 4.582786E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.603 | TFLOPs: 70.70 | +[default7]: iteration 1936/ 3814 | consumed samples: 991232 | consumed tokens: 2030043136 | elapsed time per iteration (s): 5.45 | learning rate: 9.656E-05 | global batch size: 512 | lm loss: 4.600330E+00 | loss scale: 32768.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 1937/ 3814 | consumed samples: 991744 | consumed tokens: 2031091712 | elapsed time per iteration (s): 5.45 | learning rate: 9.649E-05 | global batch size: 512 | lm loss: 4.582677E+00 | loss scale: 32768.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.938 | TFLOPs: 70.95 | +[default7]: iteration 1938/ 3814 | consumed samples: 992256 | consumed tokens: 2032140288 | elapsed time per iteration (s): 5.46 | learning rate: 9.641E-05 | global batch size: 512 | lm loss: 4.592419E+00 | loss scale: 32768.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.844 | TFLOPs: 70.88 | +[default7]: iteration 1939/ 3814 | consumed samples: 992768 | consumed tokens: 2033188864 | elapsed time per iteration (s): 5.46 | learning rate: 9.633E-05 | global batch size: 512 | lm loss: 4.582861E+00 | loss scale: 32768.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.819 | TFLOPs: 70.86 | +[default7]: iteration 1940/ 3814 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 5.45 | learning rate: 9.626E-05 | global batch size: 512 | lm loss: 4.578550E+00 | loss scale: 32768.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 1941/ 3814 | consumed samples: 993792 | consumed tokens: 2035286016 | elapsed time per iteration (s): 5.45 | learning rate: 9.618E-05 | global batch size: 512 | lm loss: 4.579281E+00 | loss scale: 32768.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.908 | TFLOPs: 70.93 | +[default7]: iteration 1942/ 3814 | consumed samples: 994304 | consumed tokens: 2036334592 | elapsed time per iteration (s): 5.46 | learning rate: 9.610E-05 | global batch size: 512 | lm loss: 4.597905E+00 | loss scale: 32768.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.824 | TFLOPs: 70.87 | +[default7]: iteration 1943/ 3814 | consumed samples: 994816 | consumed tokens: 2037383168 | elapsed time per iteration (s): 5.45 | learning rate: 9.603E-05 | global batch size: 512 | lm loss: 4.605120E+00 | loss scale: 32768.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.963 | TFLOPs: 70.97 | +[default7]: iteration 1944/ 3814 | consumed samples: 995328 | consumed tokens: 2038431744 | elapsed time per iteration (s): 5.46 | learning rate: 9.595E-05 | global batch size: 512 | lm loss: 4.626605E+00 | loss scale: 32768.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.735 | TFLOPs: 70.80 | +[default7]: iteration 1945/ 3814 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 5.44 | learning rate: 9.587E-05 | global batch size: 512 | lm loss: 4.610441E+00 | loss scale: 32768.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.033 | TFLOPs: 71.02 | +[default7]: iteration 1946/ 3814 | consumed samples: 996352 | consumed tokens: 2040528896 | elapsed time per iteration (s): 5.44 | learning rate: 9.580E-05 | global batch size: 512 | lm loss: 4.573172E+00 | loss scale: 32768.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.063 | TFLOPs: 71.05 | +[default7]: iteration 1947/ 3814 | consumed samples: 996864 | consumed tokens: 2041577472 | elapsed time per iteration (s): 5.45 | learning rate: 9.572E-05 | global batch size: 512 | lm loss: 4.575069E+00 | loss scale: 32768.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.947 | TFLOPs: 70.96 | +[default7]: iteration 1948/ 3814 | consumed samples: 997376 | consumed tokens: 2042626048 | elapsed time per iteration (s): 5.45 | learning rate: 9.564E-05 | global batch size: 512 | lm loss: 4.550076E+00 | loss scale: 32768.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.900 | TFLOPs: 70.92 | +[default7]: iteration 1949/ 3814 | consumed samples: 997888 | consumed tokens: 2043674624 | elapsed time per iteration (s): 5.45 | learning rate: 9.557E-05 | global batch size: 512 | lm loss: 4.592851E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.000 | TFLOPs: 71.00 | +[default7]: iteration 1950/ 3814 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 5.45 | learning rate: 9.549E-05 | global batch size: 512 | lm loss: 4.578896E+00 | loss scale: 32768.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default7]: iteration 1951/ 3814 | consumed samples: 998912 | consumed tokens: 2045771776 | elapsed time per iteration (s): 5.46 | learning rate: 9.541E-05 | global batch size: 512 | lm loss: 4.582358E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.793 | TFLOPs: 70.84 | +[default7]: iteration 1952/ 3814 | consumed samples: 999424 | consumed tokens: 2046820352 | elapsed time per iteration (s): 5.45 | learning rate: 9.534E-05 | global batch size: 512 | lm loss: 4.583004E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.910 | TFLOPs: 70.93 | +[default7]: iteration 1953/ 3814 | consumed samples: 999936 | consumed tokens: 2047868928 | elapsed time per iteration (s): 5.45 | learning rate: 9.526E-05 | global batch size: 512 | lm loss: 4.574358E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.964 | TFLOPs: 70.97 | +[default7]: iteration 1954/ 3814 | consumed samples: 1000448 | consumed tokens: 2048917504 | elapsed time per iteration (s): 5.46 | learning rate: 9.518E-05 | global batch size: 512 | lm loss: 4.582236E+00 | loss scale: 32768.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.820 | TFLOPs: 70.86 | +[default7]: iteration 1955/ 3814 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 5.45 | learning rate: 9.511E-05 | global batch size: 512 | lm loss: 4.572843E+00 | loss scale: 32768.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.929 | TFLOPs: 70.95 | +[default7]: iteration 1956/ 3814 | consumed samples: 1001472 | consumed tokens: 2051014656 | elapsed time per iteration (s): 5.47 | learning rate: 9.503E-05 | global batch size: 512 | lm loss: 4.594588E+00 | loss scale: 32768.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.597 | TFLOPs: 70.69 | +[default7]: iteration 1957/ 3814 | consumed samples: 1001984 | consumed tokens: 2052063232 | elapsed time per iteration (s): 5.46 | learning rate: 9.495E-05 | global batch size: 512 | lm loss: 4.583011E+00 | loss scale: 32768.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.705 | TFLOPs: 70.78 | +[default7]: iteration 1958/ 3814 | consumed samples: 1002496 | consumed tokens: 2053111808 | elapsed time per iteration (s): 5.45 | learning rate: 9.488E-05 | global batch size: 512 | lm loss: 4.560341E+00 | loss scale: 32768.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.019 | TFLOPs: 71.01 | +[default7]: iteration 1959/ 3814 | consumed samples: 1003008 | consumed tokens: 2054160384 | elapsed time per iteration (s): 5.45 | learning rate: 9.480E-05 | global batch size: 512 | lm loss: 4.598887E+00 | loss scale: 32768.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default7]: iteration 1960/ 3814 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 5.45 | learning rate: 9.472E-05 | global batch size: 512 | lm loss: 4.605993E+00 | loss scale: 32768.0 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.998 | TFLOPs: 71.00 | +[default7]: iteration 1961/ 3814 | consumed samples: 1004032 | consumed tokens: 2056257536 | elapsed time per iteration (s): 5.44 | learning rate: 9.465E-05 | global batch size: 512 | lm loss: 4.584411E+00 | loss scale: 32768.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.175 | TFLOPs: 71.13 | +[default7]: iteration 1962/ 3814 | consumed samples: 1004544 | consumed tokens: 2057306112 | elapsed time per iteration (s): 5.45 | learning rate: 9.457E-05 | global batch size: 512 | lm loss: 4.552691E+00 | loss scale: 32768.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 1963/ 3814 | consumed samples: 1005056 | consumed tokens: 2058354688 | elapsed time per iteration (s): 5.45 | learning rate: 9.449E-05 | global batch size: 512 | lm loss: 4.561486E+00 | loss scale: 32768.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 1964/ 3814 | consumed samples: 1005568 | consumed tokens: 2059403264 | elapsed time per iteration (s): 5.46 | learning rate: 9.442E-05 | global batch size: 512 | lm loss: 4.546251E+00 | loss scale: 32768.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.842 | TFLOPs: 70.88 | +[default7]: iteration 1965/ 3814 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 5.45 | learning rate: 9.434E-05 | global batch size: 512 | lm loss: 4.565257E+00 | loss scale: 32768.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 1966/ 3814 | consumed samples: 1006592 | consumed tokens: 2061500416 | elapsed time per iteration (s): 5.45 | learning rate: 9.426E-05 | global batch size: 512 | lm loss: 4.538069E+00 | loss scale: 32768.0 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.985 | TFLOPs: 70.99 | +[default7]: iteration 1967/ 3814 | consumed samples: 1007104 | consumed tokens: 2062548992 | elapsed time per iteration (s): 5.45 | learning rate: 9.419E-05 | global batch size: 512 | lm loss: 4.584559E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.89 | +[default7]: iteration 1968/ 3814 | consumed samples: 1007616 | consumed tokens: 2063597568 | elapsed time per iteration (s): 5.45 | learning rate: 9.411E-05 | global batch size: 512 | lm loss: 4.558007E+00 | loss scale: 32768.0 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.902 | TFLOPs: 70.93 | +[default7]: iteration 1969/ 3814 | consumed samples: 1008128 | consumed tokens: 2064646144 | elapsed time per iteration (s): 5.45 | learning rate: 9.403E-05 | global batch size: 512 | lm loss: 4.563388E+00 | loss scale: 32768.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.859 | TFLOPs: 70.89 | +[default7]: iteration 1970/ 3814 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 5.44 | learning rate: 9.396E-05 | global batch size: 512 | lm loss: 4.569027E+00 | loss scale: 32768.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.042 | TFLOPs: 71.03 | +[default7]: iteration 1971/ 3814 | consumed samples: 1009152 | consumed tokens: 2066743296 | elapsed time per iteration (s): 5.45 | learning rate: 9.388E-05 | global batch size: 512 | lm loss: 4.564066E+00 | loss scale: 32768.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.924 | TFLOPs: 70.94 | +[default7]: iteration 1972/ 3814 | consumed samples: 1009664 | consumed tokens: 2067791872 | elapsed time per iteration (s): 5.45 | learning rate: 9.380E-05 | global batch size: 512 | lm loss: 4.544582E+00 | loss scale: 32768.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 1973/ 3814 | consumed samples: 1010176 | consumed tokens: 2068840448 | elapsed time per iteration (s): 5.45 | learning rate: 9.373E-05 | global batch size: 512 | lm loss: 4.574890E+00 | loss scale: 32768.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 1974/ 3814 | consumed samples: 1010688 | consumed tokens: 2069889024 | elapsed time per iteration (s): 5.43 | learning rate: 9.365E-05 | global batch size: 512 | lm loss: 4.601029E+00 | loss scale: 32768.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 1975/ 3814 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 5.43 | learning rate: 9.357E-05 | global batch size: 512 | lm loss: 4.563743E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.218 | TFLOPs: 71.16 | +[default7]: iteration 1976/ 3814 | consumed samples: 1011712 | consumed tokens: 2071986176 | elapsed time per iteration (s): 5.43 | learning rate: 9.350E-05 | global batch size: 512 | lm loss: 4.565231E+00 | loss scale: 32768.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.299 | TFLOPs: 71.22 | +[default7]: iteration 1977/ 3814 | consumed samples: 1012224 | consumed tokens: 2073034752 | elapsed time per iteration (s): 5.43 | learning rate: 9.342E-05 | global batch size: 512 | lm loss: 4.580276E+00 | loss scale: 32768.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.312 | TFLOPs: 71.23 | +[default7]: iteration 1978/ 3814 | consumed samples: 1012736 | consumed tokens: 2074083328 | elapsed time per iteration (s): 5.43 | learning rate: 9.334E-05 | global batch size: 512 | lm loss: 4.559215E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.367 | TFLOPs: 71.28 | +[default7]: iteration 1979/ 3814 | consumed samples: 1013248 | consumed tokens: 2075131904 | elapsed time per iteration (s): 5.43 | learning rate: 9.326E-05 | global batch size: 512 | lm loss: 4.566166E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.353 | TFLOPs: 71.27 | +[default7]: iteration 1980/ 3814 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 5.44 | learning rate: 9.319E-05 | global batch size: 512 | lm loss: 4.567459E+00 | loss scale: 32768.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 1981/ 3814 | consumed samples: 1014272 | consumed tokens: 2077229056 | elapsed time per iteration (s): 5.46 | learning rate: 9.311E-05 | global batch size: 512 | lm loss: 4.537037E+00 | loss scale: 32768.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.828 | TFLOPs: 70.87 | +[default7]: iteration 1982/ 3814 | consumed samples: 1014784 | consumed tokens: 2078277632 | elapsed time per iteration (s): 5.44 | learning rate: 9.303E-05 | global batch size: 512 | lm loss: 4.581811E+00 | loss scale: 32768.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.033 | TFLOPs: 71.02 | +[default7]: iteration 1983/ 3814 | consumed samples: 1015296 | consumed tokens: 2079326208 | elapsed time per iteration (s): 5.45 | learning rate: 9.296E-05 | global batch size: 512 | lm loss: 4.583554E+00 | loss scale: 32768.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.990 | TFLOPs: 70.99 | +[default7]: iteration 1984/ 3814 | consumed samples: 1015808 | consumed tokens: 2080374784 | elapsed time per iteration (s): 5.43 | learning rate: 9.288E-05 | global batch size: 512 | lm loss: 4.560905E+00 | loss scale: 32768.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 1985/ 3814 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 5.43 | learning rate: 9.280E-05 | global batch size: 512 | lm loss: 4.570708E+00 | loss scale: 32768.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.222 | TFLOPs: 71.17 | +[default7]: iteration 1986/ 3814 | consumed samples: 1016832 | consumed tokens: 2082471936 | elapsed time per iteration (s): 5.44 | learning rate: 9.273E-05 | global batch size: 512 | lm loss: 4.553664E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.076 | TFLOPs: 71.06 | +[default7]: iteration 1987/ 3814 | consumed samples: 1017344 | consumed tokens: 2083520512 | elapsed time per iteration (s): 5.43 | learning rate: 9.265E-05 | global batch size: 512 | lm loss: 4.559820E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.239 | TFLOPs: 71.18 | +[default7]: iteration 1988/ 3814 | consumed samples: 1017856 | consumed tokens: 2084569088 | elapsed time per iteration (s): 5.44 | learning rate: 9.257E-05 | global batch size: 512 | lm loss: 4.567852E+00 | loss scale: 32768.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.116 | TFLOPs: 71.09 | +[default7]: iteration 1989/ 3814 | consumed samples: 1018368 | consumed tokens: 2085617664 | elapsed time per iteration (s): 5.44 | learning rate: 9.250E-05 | global batch size: 512 | lm loss: 4.538291E+00 | loss scale: 32768.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.150 | TFLOPs: 71.11 | +[default7]: iteration 1990/ 3814 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 5.43 | learning rate: 9.242E-05 | global batch size: 512 | lm loss: 4.546114E+00 | loss scale: 32768.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.221 | TFLOPs: 71.17 | +[default7]: iteration 1991/ 3814 | consumed samples: 1019392 | consumed tokens: 2087714816 | elapsed time per iteration (s): 5.43 | learning rate: 9.234E-05 | global batch size: 512 | lm loss: 4.524523E+00 | loss scale: 32768.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.223 | TFLOPs: 71.17 | +[default7]: iteration 1992/ 3814 | consumed samples: 1019904 | consumed tokens: 2088763392 | elapsed time per iteration (s): 5.44 | learning rate: 9.226E-05 | global batch size: 512 | lm loss: 4.581615E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.152 | TFLOPs: 71.11 | +[default7]: iteration 1993/ 3814 | consumed samples: 1020416 | consumed tokens: 2089811968 | elapsed time per iteration (s): 5.45 | learning rate: 9.219E-05 | global batch size: 512 | lm loss: 4.563101E+00 | loss scale: 32768.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.007 | TFLOPs: 71.00 | +[default7]: iteration 1994/ 3814 | consumed samples: 1020928 | consumed tokens: 2090860544 | elapsed time per iteration (s): 5.44 | learning rate: 9.211E-05 | global batch size: 512 | lm loss: 4.558438E+00 | loss scale: 32768.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.151 | TFLOPs: 71.11 | +[default7]: iteration 1995/ 3814 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 5.42 | learning rate: 9.203E-05 | global batch size: 512 | lm loss: 4.523809E+00 | loss scale: 32768.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.388 | TFLOPs: 71.29 | +[default7]: iteration 1996/ 3814 | consumed samples: 1021952 | consumed tokens: 2092957696 | elapsed time per iteration (s): 5.45 | learning rate: 9.196E-05 | global batch size: 512 | lm loss: 4.568559E+00 | loss scale: 32768.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.985 | TFLOPs: 70.99 | +[default7]: iteration 1997/ 3814 | consumed samples: 1022464 | consumed tokens: 2094006272 | elapsed time per iteration (s): 5.43 | learning rate: 9.188E-05 | global batch size: 512 | lm loss: 4.558148E+00 | loss scale: 32768.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 1998/ 3814 | consumed samples: 1022976 | consumed tokens: 2095054848 | elapsed time per iteration (s): 5.43 | learning rate: 9.180E-05 | global batch size: 512 | lm loss: 4.570784E+00 | loss scale: 32768.0 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.238 | TFLOPs: 71.18 | +[default7]: iteration 1999/ 3814 | consumed samples: 1023488 | consumed tokens: 2096103424 | elapsed time per iteration (s): 5.45 | learning rate: 9.173E-05 | global batch size: 512 | lm loss: 4.520056E+00 | loss scale: 32768.0 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.950 | TFLOPs: 70.96 | +[default0]:[2023-02-16 14:21:22,197] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[9.164864365335951e-05, 4.5824321826679754e-05, 0.0009164864365335952, 4.5824321826679754e-05, 9.164864365335951e-05, 0.0009164864365335952], mom=[(0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95)] +[default0]:steps: 2000 loss: 4.5410 iter time (s): 5.360 samples/sec: 95.520 +[default7]: iteration 2000/ 3814 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 5.44 | learning rate: 9.165E-05 | global batch size: 512 | lm loss: 4.540959E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.119 | TFLOPs: 71.09 | +[default0]:saving checkpoint at iteration 2000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 14:21:23,274] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +[default7]:------------------------------------------------------------------------------------------ +[default7]:valid loss at iteration 2000 | lm loss value: 4.511817E+00 | lm loss PPL: 9.108713E+01 | +[default7]:------------------------------------------------------------------------------------------ +[default1]:[2023-02-16 14:21:23,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:23,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_00-model_states.pt. +[default1]:[2023-02-16 14:21:23,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_00-model_states.pt. +[default1]:[2023-02-16 14:21:23,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,578] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:23,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,642] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,646] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:23,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_01-model_states.pt. +[default0]:[2023-02-16 14:21:23,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,708] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_00-model_states.pt. +[default1]:[2023-02-16 14:21:23,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:23,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,767] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:23,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,831] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:23,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,903] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:23,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:23,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:23,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:23,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:23,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,028] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,024] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,092] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:24,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,277] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,278] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:24,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,428] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:24,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,672] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:24,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,738] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:24,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,859] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:24,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,925] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:24,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:24,985] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:25,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:24,989] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:24,990] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:25,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:25,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,116] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:25,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:25,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,182] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:25,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,241] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:25,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,186] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:25,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:25,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:25,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:25,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,305] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:25,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,369] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 14:21:25,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,428] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 14:21:25,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_00-model_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:21:25,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 14:21:25,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 14:21:25,493] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt +[default1]:[2023-02-16 14:21:25,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 14:21:25,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:21:25,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 14:21:25,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 14:21:25,497] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt +[default0]:[2023-02-16 14:21:25,497] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 14:21:25,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:21:25,534] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:21:25,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:25,996] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:25,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,070] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,063] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,081] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,081] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,104] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,097] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,115] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,127] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,191] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,205] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,193] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,167] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,217] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,215] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,185] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,146] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,218] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,214] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,182] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,219] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,193] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,220] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,203] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,234] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,252] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,240] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,273] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,262] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,252] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,218] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,238] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,227] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,236] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,245] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,220] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,197] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,203] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,282] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,218] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,279] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,266] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,317] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,248] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,333] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 14:21:26,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,326] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,256] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,335] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,271] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,287] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 14:21:26,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:21:26,325] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:21:26,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,287] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,310] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,320] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,367] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,367] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,317] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,351] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,351] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 14:21:26,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:21:26,360] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:21:26,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 14:21:26,344] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:21:26,344] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:21:26,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 14:21:26,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:21:26,364] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:21:26,364] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,458] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 14:21:26,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:21:26,391] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:21:26,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]: successfully saved checkpoint at iteration 2000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default4]:[2023-02-16 14:21:26,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:21:26,410] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:21:26,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 14:21:26,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:21:26,404] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:21:26,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 14:21:26,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:21:26,452] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:21:26,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:time (ms) | save-checkpoint: 3185.22 +[default7]: iteration 2001/ 3814 | consumed samples: 1024512 | consumed tokens: 2098200576 | elapsed time per iteration (s): 9.64 | learning rate: 9.157E-05 | global batch size: 512 | lm loss: 4.572244E+00 | loss scale: 65536.0 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 53.123 | TFLOPs: 40.12 | +[default7]: iteration 2002/ 3814 | consumed samples: 1025024 | consumed tokens: 2099249152 | elapsed time per iteration (s): 5.46 | learning rate: 9.149E-05 | global batch size: 512 | lm loss: 4.552001E+00 | loss scale: 65536.0 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.780 | TFLOPs: 70.83 | +[default7]: iteration 2003/ 3814 | consumed samples: 1025536 | consumed tokens: 2100297728 | elapsed time per iteration (s): 5.47 | learning rate: 9.142E-05 | global batch size: 512 | lm loss: 4.551000E+00 | loss scale: 65536.0 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.638 | TFLOPs: 70.73 | +[default7]: iteration 2004/ 3814 | consumed samples: 1026048 | consumed tokens: 2101346304 | elapsed time per iteration (s): 5.47 | learning rate: 9.134E-05 | global batch size: 512 | lm loss: 4.545208E+00 | loss scale: 65536.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.528 | TFLOPs: 70.64 | +[default7]: iteration 2005/ 3814 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 5.46 | learning rate: 9.126E-05 | global batch size: 512 | lm loss: 4.552608E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.751 | TFLOPs: 70.81 | +[default7]: iteration 2006/ 3814 | consumed samples: 1027072 | consumed tokens: 2103443456 | elapsed time per iteration (s): 5.46 | learning rate: 9.119E-05 | global batch size: 512 | lm loss: 4.533473E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.697 | TFLOPs: 70.77 | +[default7]: iteration 2007/ 3814 | consumed samples: 1027584 | consumed tokens: 2104492032 | elapsed time per iteration (s): 5.46 | learning rate: 9.111E-05 | global batch size: 512 | lm loss: 4.546027E+00 | loss scale: 65536.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.722 | TFLOPs: 70.79 | +[default7]: iteration 2008/ 3814 | consumed samples: 1028096 | consumed tokens: 2105540608 | elapsed time per iteration (s): 5.45 | learning rate: 9.103E-05 | global batch size: 512 | lm loss: 4.555826E+00 | loss scale: 65536.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.943 | TFLOPs: 70.96 | +[default7]: iteration 2009/ 3814 | consumed samples: 1028608 | consumed tokens: 2106589184 | elapsed time per iteration (s): 5.45 | learning rate: 9.096E-05 | global batch size: 512 | lm loss: 4.553384E+00 | loss scale: 65536.0 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.874 | TFLOPs: 70.90 | +[default7]: iteration 2010/ 3814 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 5.47 | learning rate: 9.088E-05 | global batch size: 512 | lm loss: 4.570604E+00 | loss scale: 65536.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.643 | TFLOPs: 70.73 | +[default7]: iteration 2011/ 3814 | consumed samples: 1029632 | consumed tokens: 2108686336 | elapsed time per iteration (s): 5.48 | learning rate: 9.080E-05 | global batch size: 512 | lm loss: 4.571728E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.383 | TFLOPs: 70.53 | +[default7]: iteration 2012/ 3814 | consumed samples: 1030144 | consumed tokens: 2109734912 | elapsed time per iteration (s): 5.46 | learning rate: 9.072E-05 | global batch size: 512 | lm loss: 4.544832E+00 | loss scale: 65536.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.715 | TFLOPs: 70.78 | +[default7]: iteration 2013/ 3814 | consumed samples: 1030656 | consumed tokens: 2110783488 | elapsed time per iteration (s): 5.47 | learning rate: 9.065E-05 | global batch size: 512 | lm loss: 4.539944E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.588 | TFLOPs: 70.69 | +[default7]: iteration 2014/ 3814 | consumed samples: 1031168 | consumed tokens: 2111832064 | elapsed time per iteration (s): 5.49 | learning rate: 9.057E-05 | global batch size: 512 | lm loss: 4.559639E+00 | loss scale: 65536.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.315 | TFLOPs: 70.48 | +[default7]: iteration 2015/ 3814 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 5.47 | learning rate: 9.049E-05 | global batch size: 512 | lm loss: 4.585619E+00 | loss scale: 65536.0 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.552 | TFLOPs: 70.66 | +[default7]: iteration 2016/ 3814 | consumed samples: 1032192 | consumed tokens: 2113929216 | elapsed time per iteration (s): 5.49 | learning rate: 9.042E-05 | global batch size: 512 | lm loss: 4.568936E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.312 | TFLOPs: 70.48 | +[default7]: iteration 2017/ 3814 | consumed samples: 1032704 | consumed tokens: 2114977792 | elapsed time per iteration (s): 5.49 | learning rate: 9.034E-05 | global batch size: 512 | lm loss: 4.564395E+00 | loss scale: 65536.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.201 | TFLOPs: 70.40 | +[default7]: iteration 2018/ 3814 | consumed samples: 1033216 | consumed tokens: 2116026368 | elapsed time per iteration (s): 5.48 | learning rate: 9.026E-05 | global batch size: 512 | lm loss: 4.546805E+00 | loss scale: 65536.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.471 | TFLOPs: 70.60 | +[default7]: iteration 2019/ 3814 | consumed samples: 1033728 | consumed tokens: 2117074944 | elapsed time per iteration (s): 5.47 | learning rate: 9.018E-05 | global batch size: 512 | lm loss: 4.538428E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.539 | TFLOPs: 70.65 | +[default7]: iteration 2020/ 3814 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 5.46 | learning rate: 9.011E-05 | global batch size: 512 | lm loss: 4.530963E+00 | loss scale: 65536.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.771 | TFLOPs: 70.83 | +[default7]: iteration 2021/ 3814 | consumed samples: 1034752 | consumed tokens: 2119172096 | elapsed time per iteration (s): 5.47 | learning rate: 9.003E-05 | global batch size: 512 | lm loss: 4.519834E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.525 | TFLOPs: 70.64 | +[default7]: iteration 2022/ 3814 | consumed samples: 1035264 | consumed tokens: 2120220672 | elapsed time per iteration (s): 5.46 | learning rate: 8.995E-05 | global batch size: 512 | lm loss: 4.547222E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.735 | TFLOPs: 70.80 | +[default7]: iteration 2023/ 3814 | consumed samples: 1035776 | consumed tokens: 2121269248 | elapsed time per iteration (s): 5.48 | learning rate: 8.988E-05 | global batch size: 512 | lm loss: 4.528087E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.501 | TFLOPs: 70.62 | +[default7]: iteration 2024/ 3814 | consumed samples: 1036288 | consumed tokens: 2122317824 | elapsed time per iteration (s): 5.48 | learning rate: 8.980E-05 | global batch size: 512 | lm loss: 4.543900E+00 | loss scale: 65536.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.440 | TFLOPs: 70.58 | +[default7]: iteration 2025/ 3814 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 5.49 | learning rate: 8.972E-05 | global batch size: 512 | lm loss: 4.554760E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.189 | TFLOPs: 70.39 | +[default7]: iteration 2026/ 3814 | consumed samples: 1037312 | consumed tokens: 2124414976 | elapsed time per iteration (s): 5.47 | learning rate: 8.964E-05 | global batch size: 512 | lm loss: 4.539897E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.656 | TFLOPs: 70.74 | +[default7]: iteration 2027/ 3814 | consumed samples: 1037824 | consumed tokens: 2125463552 | elapsed time per iteration (s): 5.46 | learning rate: 8.957E-05 | global batch size: 512 | lm loss: 4.525445E+00 | loss scale: 65536.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.704 | TFLOPs: 70.78 | +[default7]: iteration 2028/ 3814 | consumed samples: 1038336 | consumed tokens: 2126512128 | elapsed time per iteration (s): 5.46 | learning rate: 8.949E-05 | global batch size: 512 | lm loss: 4.574347E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.711 | TFLOPs: 70.78 | +[default7]: iteration 2029/ 3814 | consumed samples: 1038848 | consumed tokens: 2127560704 | elapsed time per iteration (s): 5.47 | learning rate: 8.941E-05 | global batch size: 512 | lm loss: 4.539248E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.583 | TFLOPs: 70.68 | +[default7]: iteration 2030/ 3814 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 5.47 | learning rate: 8.934E-05 | global batch size: 512 | lm loss: 4.521113E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.679 | TFLOPs: 70.76 | +[default7]: iteration 2031/ 3814 | consumed samples: 1039872 | consumed tokens: 2129657856 | elapsed time per iteration (s): 5.46 | learning rate: 8.926E-05 | global batch size: 512 | lm loss: 4.523688E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.820 | TFLOPs: 70.86 | +[default7]: iteration 2032/ 3814 | consumed samples: 1040384 | consumed tokens: 2130706432 | elapsed time per iteration (s): 5.46 | learning rate: 8.918E-05 | global batch size: 512 | lm loss: 4.559801E+00 | loss scale: 65536.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.776 | TFLOPs: 70.83 | +[default7]: iteration 2033/ 3814 | consumed samples: 1040896 | consumed tokens: 2131755008 | elapsed time per iteration (s): 5.47 | learning rate: 8.910E-05 | global batch size: 512 | lm loss: 4.533936E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.656 | TFLOPs: 70.74 | +[default7]: iteration 2034/ 3814 | consumed samples: 1041408 | consumed tokens: 2132803584 | elapsed time per iteration (s): 5.46 | learning rate: 8.903E-05 | global batch size: 512 | lm loss: 4.513160E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.802 | TFLOPs: 70.85 | +[default7]: iteration 2035/ 3814 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 5.44 | learning rate: 8.895E-05 | global batch size: 512 | lm loss: 4.553459E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.048 | TFLOPs: 71.04 | +[default7]: iteration 2036/ 3814 | consumed samples: 1042432 | consumed tokens: 2134900736 | elapsed time per iteration (s): 5.45 | learning rate: 8.887E-05 | global batch size: 512 | lm loss: 4.540084E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.942 | TFLOPs: 70.96 | +[default7]: iteration 2037/ 3814 | consumed samples: 1042944 | consumed tokens: 2135949312 | elapsed time per iteration (s): 5.45 | learning rate: 8.880E-05 | global batch size: 512 | lm loss: 4.540951E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 2038/ 3814 | consumed samples: 1043456 | consumed tokens: 2136997888 | elapsed time per iteration (s): 5.47 | learning rate: 8.872E-05 | global batch size: 512 | lm loss: 4.495380E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.610 | TFLOPs: 70.70 | +[default7]: iteration 2039/ 3814 | consumed samples: 1043968 | consumed tokens: 2138046464 | elapsed time per iteration (s): 5.47 | learning rate: 8.864E-05 | global batch size: 512 | lm loss: 4.531937E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.619 | TFLOPs: 70.71 | +[default7]: iteration 2040/ 3814 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 5.47 | learning rate: 8.856E-05 | global batch size: 512 | lm loss: 4.557389E+00 | loss scale: 65536.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.599 | TFLOPs: 70.70 | +[default7]: iteration 2041/ 3814 | consumed samples: 1044992 | consumed tokens: 2140143616 | elapsed time per iteration (s): 5.47 | learning rate: 8.849E-05 | global batch size: 512 | lm loss: 4.528131E+00 | loss scale: 65536.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.556 | TFLOPs: 70.66 | +[default7]: iteration 2042/ 3814 | consumed samples: 1045504 | consumed tokens: 2141192192 | elapsed time per iteration (s): 5.48 | learning rate: 8.841E-05 | global batch size: 512 | lm loss: 4.542218E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.443 | TFLOPs: 70.58 | +[default7]: iteration 2043/ 3814 | consumed samples: 1046016 | consumed tokens: 2142240768 | elapsed time per iteration (s): 5.47 | learning rate: 8.833E-05 | global batch size: 512 | lm loss: 4.549363E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.684 | TFLOPs: 70.76 | +[default7]: iteration 2044/ 3814 | consumed samples: 1046528 | consumed tokens: 2143289344 | elapsed time per iteration (s): 5.46 | learning rate: 8.826E-05 | global batch size: 512 | lm loss: 4.522311E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.696 | TFLOPs: 70.77 | +[default7]: iteration 2045/ 3814 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 5.48 | learning rate: 8.818E-05 | global batch size: 512 | lm loss: 4.545067E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.419 | TFLOPs: 70.56 | +[default7]: iteration 2046/ 3814 | consumed samples: 1047552 | consumed tokens: 2145386496 | elapsed time per iteration (s): 5.48 | learning rate: 8.810E-05 | global batch size: 512 | lm loss: 4.525419E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.483 | TFLOPs: 70.61 | +[default7]: iteration 2047/ 3814 | consumed samples: 1048064 | consumed tokens: 2146435072 | elapsed time per iteration (s): 5.46 | learning rate: 8.802E-05 | global batch size: 512 | lm loss: 4.537577E+00 | loss scale: 65536.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.695 | TFLOPs: 70.77 | +[default7]: iteration 2048/ 3814 | consumed samples: 1048576 | consumed tokens: 2147483648 | elapsed time per iteration (s): 5.46 | learning rate: 8.795E-05 | global batch size: 512 | lm loss: 4.538331E+00 | loss scale: 65536.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.849 | TFLOPs: 70.89 | +[default7]: iteration 2049/ 3814 | consumed samples: 1049088 | consumed tokens: 2148532224 | elapsed time per iteration (s): 5.46 | learning rate: 8.787E-05 | global batch size: 512 | lm loss: 4.509868E+00 | loss scale: 65536.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.850 | TFLOPs: 70.89 | +[default7]: iteration 2050/ 3814 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 5.44 | learning rate: 8.779E-05 | global batch size: 512 | lm loss: 4.537294E+00 | loss scale: 65536.0 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.119 | TFLOPs: 71.09 | +[default7]: iteration 2051/ 3814 | consumed samples: 1050112 | consumed tokens: 2150629376 | elapsed time per iteration (s): 5.47 | learning rate: 8.772E-05 | global batch size: 512 | lm loss: 4.530303E+00 | loss scale: 65536.0 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.639 | TFLOPs: 70.73 | +[default7]: iteration 2052/ 3814 | consumed samples: 1050624 | consumed tokens: 2151677952 | elapsed time per iteration (s): 5.47 | learning rate: 8.764E-05 | global batch size: 512 | lm loss: 4.549403E+00 | loss scale: 65536.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.540 | TFLOPs: 70.65 | +[default7]: iteration 2053/ 3814 | consumed samples: 1051136 | consumed tokens: 2152726528 | elapsed time per iteration (s): 5.47 | learning rate: 8.756E-05 | global batch size: 512 | lm loss: 4.522768E+00 | loss scale: 65536.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.590 | TFLOPs: 70.69 | +[default7]: iteration 2054/ 3814 | consumed samples: 1051648 | consumed tokens: 2153775104 | elapsed time per iteration (s): 5.48 | learning rate: 8.748E-05 | global batch size: 512 | lm loss: 4.519965E+00 | loss scale: 65536.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.474 | TFLOPs: 70.60 | +[default7]: iteration 2055/ 3814 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 5.46 | learning rate: 8.741E-05 | global batch size: 512 | lm loss: 4.524118E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.762 | TFLOPs: 70.82 | +[default7]: iteration 2056/ 3814 | consumed samples: 1052672 | consumed tokens: 2155872256 | elapsed time per iteration (s): 5.48 | learning rate: 8.733E-05 | global batch size: 512 | lm loss: 4.511625E+00 | loss scale: 65536.0 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.474 | TFLOPs: 70.60 | +[default7]: iteration 2057/ 3814 | consumed samples: 1053184 | consumed tokens: 2156920832 | elapsed time per iteration (s): 5.48 | learning rate: 8.725E-05 | global batch size: 512 | lm loss: 4.527478E+00 | loss scale: 65536.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.397 | TFLOPs: 70.54 | +[default7]: iteration 2058/ 3814 | consumed samples: 1053696 | consumed tokens: 2157969408 | elapsed time per iteration (s): 5.48 | learning rate: 8.718E-05 | global batch size: 512 | lm loss: 4.532701E+00 | loss scale: 65536.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.431 | TFLOPs: 70.57 | +[default7]: iteration 2059/ 3814 | consumed samples: 1054208 | consumed tokens: 2159017984 | elapsed time per iteration (s): 5.47 | learning rate: 8.710E-05 | global batch size: 512 | lm loss: 4.546751E+00 | loss scale: 65536.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.586 | TFLOPs: 70.69 | +[default7]: iteration 2060/ 3814 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 5.47 | learning rate: 8.702E-05 | global batch size: 512 | lm loss: 4.529485E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.677 | TFLOPs: 70.76 | +[default7]: iteration 2061/ 3814 | consumed samples: 1055232 | consumed tokens: 2161115136 | elapsed time per iteration (s): 5.47 | learning rate: 8.694E-05 | global batch size: 512 | lm loss: 4.513539E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.587 | TFLOPs: 70.69 | +[default7]: iteration 2062/ 3814 | consumed samples: 1055744 | consumed tokens: 2162163712 | elapsed time per iteration (s): 5.47 | learning rate: 8.687E-05 | global batch size: 512 | lm loss: 4.499883E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.663 | TFLOPs: 70.74 | +[default7]: iteration 2063/ 3814 | consumed samples: 1056256 | consumed tokens: 2163212288 | elapsed time per iteration (s): 5.49 | learning rate: 8.679E-05 | global batch size: 512 | lm loss: 4.511192E+00 | loss scale: 65536.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.308 | TFLOPs: 70.48 | +[default7]: iteration 2064/ 3814 | consumed samples: 1056768 | consumed tokens: 2164260864 | elapsed time per iteration (s): 5.46 | learning rate: 8.671E-05 | global batch size: 512 | lm loss: 4.519623E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.745 | TFLOPs: 70.81 | +[default7]: iteration 2065/ 3814 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 5.47 | learning rate: 8.663E-05 | global batch size: 512 | lm loss: 4.509145E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.610 | TFLOPs: 70.70 | +[default7]: iteration 2066/ 3814 | consumed samples: 1057792 | consumed tokens: 2166358016 | elapsed time per iteration (s): 5.47 | learning rate: 8.656E-05 | global batch size: 512 | lm loss: 4.514247E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.609 | TFLOPs: 70.70 | +[default7]: iteration 2067/ 3814 | consumed samples: 1058304 | consumed tokens: 2167406592 | elapsed time per iteration (s): 5.46 | learning rate: 8.648E-05 | global batch size: 512 | lm loss: 4.534826E+00 | loss scale: 65536.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.694 | TFLOPs: 70.77 | +[default7]: iteration 2068/ 3814 | consumed samples: 1058816 | consumed tokens: 2168455168 | elapsed time per iteration (s): 5.47 | learning rate: 8.640E-05 | global batch size: 512 | lm loss: 4.519842E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.557 | TFLOPs: 70.66 | +[default7]: iteration 2069/ 3814 | consumed samples: 1059328 | consumed tokens: 2169503744 | elapsed time per iteration (s): 5.47 | learning rate: 8.633E-05 | global batch size: 512 | lm loss: 4.506504E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.654 | TFLOPs: 70.74 | +[default7]: iteration 2070/ 3814 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 5.47 | learning rate: 8.625E-05 | global batch size: 512 | lm loss: 4.507790E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.639 | TFLOPs: 70.73 | +[default7]: iteration 2071/ 3814 | consumed samples: 1060352 | consumed tokens: 2171600896 | elapsed time per iteration (s): 5.46 | learning rate: 8.617E-05 | global batch size: 512 | lm loss: 4.529567E+00 | loss scale: 65536.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.770 | TFLOPs: 70.83 | +[default7]: iteration 2072/ 3814 | consumed samples: 1060864 | consumed tokens: 2172649472 | elapsed time per iteration (s): 5.48 | learning rate: 8.609E-05 | global batch size: 512 | lm loss: 4.511786E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.506 | TFLOPs: 70.63 | +[default7]: iteration 2073/ 3814 | consumed samples: 1061376 | consumed tokens: 2173698048 | elapsed time per iteration (s): 5.49 | learning rate: 8.602E-05 | global batch size: 512 | lm loss: 4.532354E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.304 | TFLOPs: 70.47 | +[default7]: iteration 2074/ 3814 | consumed samples: 1061888 | consumed tokens: 2174746624 | elapsed time per iteration (s): 5.47 | learning rate: 8.594E-05 | global batch size: 512 | lm loss: 4.539856E+00 | loss scale: 65536.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.623 | TFLOPs: 70.71 | +[default7]: iteration 2075/ 3814 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 5.47 | learning rate: 8.586E-05 | global batch size: 512 | lm loss: 4.543521E+00 | loss scale: 65536.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.526 | TFLOPs: 70.64 | +[default7]: iteration 2076/ 3814 | consumed samples: 1062912 | consumed tokens: 2176843776 | elapsed time per iteration (s): 5.47 | learning rate: 8.578E-05 | global batch size: 512 | lm loss: 4.507142E+00 | loss scale: 65536.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.623 | TFLOPs: 70.71 | +[default7]: iteration 2077/ 3814 | consumed samples: 1063424 | consumed tokens: 2177892352 | elapsed time per iteration (s): 5.46 | learning rate: 8.571E-05 | global batch size: 512 | lm loss: 4.532397E+00 | loss scale: 65536.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.780 | TFLOPs: 70.83 | +[default7]: iteration 2078/ 3814 | consumed samples: 1063936 | consumed tokens: 2178940928 | elapsed time per iteration (s): 5.48 | learning rate: 8.563E-05 | global batch size: 512 | lm loss: 4.507734E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.379 | TFLOPs: 70.53 | +[default7]: iteration 2079/ 3814 | consumed samples: 1064448 | consumed tokens: 2179989504 | elapsed time per iteration (s): 5.51 | learning rate: 8.555E-05 | global batch size: 512 | lm loss: 4.538468E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 92.996 | TFLOPs: 70.24 | +[default7]: iteration 2080/ 3814 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 5.45 | learning rate: 8.548E-05 | global batch size: 512 | lm loss: 4.541183E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.891 | TFLOPs: 70.92 | +[default7]: iteration 2081/ 3814 | consumed samples: 1065472 | consumed tokens: 2182086656 | elapsed time per iteration (s): 5.45 | learning rate: 8.540E-05 | global batch size: 512 | lm loss: 4.485594E+00 | loss scale: 65536.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.928 | TFLOPs: 70.94 | +[default7]: iteration 2082/ 3814 | consumed samples: 1065984 | consumed tokens: 2183135232 | elapsed time per iteration (s): 5.43 | learning rate: 8.532E-05 | global batch size: 512 | lm loss: 4.505302E+00 | loss scale: 65536.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.234 | TFLOPs: 71.18 | +[default7]: iteration 2083/ 3814 | consumed samples: 1066496 | consumed tokens: 2184183808 | elapsed time per iteration (s): 5.47 | learning rate: 8.524E-05 | global batch size: 512 | lm loss: 4.482728E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.651 | TFLOPs: 70.74 | +[default7]: iteration 2084/ 3814 | consumed samples: 1067008 | consumed tokens: 2185232384 | elapsed time per iteration (s): 5.49 | learning rate: 8.517E-05 | global batch size: 512 | lm loss: 4.493680E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.245 | TFLOPs: 70.43 | +[default7]: iteration 2085/ 3814 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 5.45 | learning rate: 8.509E-05 | global batch size: 512 | lm loss: 4.524200E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.979 | TFLOPs: 70.98 | +[default7]: iteration 2086/ 3814 | consumed samples: 1068032 | consumed tokens: 2187329536 | elapsed time per iteration (s): 5.42 | learning rate: 8.501E-05 | global batch size: 512 | lm loss: 4.507804E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.425 | TFLOPs: 71.32 | +[default7]: iteration 2087/ 3814 | consumed samples: 1068544 | consumed tokens: 2188378112 | elapsed time per iteration (s): 5.45 | learning rate: 8.494E-05 | global batch size: 512 | lm loss: 4.521204E+00 | loss scale: 65536.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 2088/ 3814 | consumed samples: 1069056 | consumed tokens: 2189426688 | elapsed time per iteration (s): 5.44 | learning rate: 8.486E-05 | global batch size: 512 | lm loss: 4.491171E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 2089/ 3814 | consumed samples: 1069568 | consumed tokens: 2190475264 | elapsed time per iteration (s): 5.46 | learning rate: 8.478E-05 | global batch size: 512 | lm loss: 4.498718E+00 | loss scale: 65536.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.854 | TFLOPs: 70.89 | +[default7]: iteration 2090/ 3814 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 5.44 | learning rate: 8.470E-05 | global batch size: 512 | lm loss: 4.508765E+00 | loss scale: 65536.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.095 | TFLOPs: 71.07 | +[default7]: iteration 2091/ 3814 | consumed samples: 1070592 | consumed tokens: 2192572416 | elapsed time per iteration (s): 5.45 | learning rate: 8.463E-05 | global batch size: 512 | lm loss: 4.505984E+00 | loss scale: 65536.0 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.939 | TFLOPs: 70.95 | +[default7]: iteration 2092/ 3814 | consumed samples: 1071104 | consumed tokens: 2193620992 | elapsed time per iteration (s): 5.46 | learning rate: 8.455E-05 | global batch size: 512 | lm loss: 4.508070E+00 | loss scale: 65536.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.750 | TFLOPs: 70.81 | +[default7]: iteration 2093/ 3814 | consumed samples: 1071616 | consumed tokens: 2194669568 | elapsed time per iteration (s): 5.45 | learning rate: 8.447E-05 | global batch size: 512 | lm loss: 4.494323E+00 | loss scale: 65536.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.913 | TFLOPs: 70.93 | +[default7]: iteration 2094/ 3814 | consumed samples: 1072128 | consumed tokens: 2195718144 | elapsed time per iteration (s): 5.45 | learning rate: 8.439E-05 | global batch size: 512 | lm loss: 4.526884E+00 | loss scale: 65536.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.871 | TFLOPs: 70.90 | +[default7]: iteration 2095/ 3814 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 5.46 | learning rate: 8.432E-05 | global batch size: 512 | lm loss: 4.491107E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.788 | TFLOPs: 70.84 | +[default7]: iteration 2096/ 3814 | consumed samples: 1073152 | consumed tokens: 2197815296 | elapsed time per iteration (s): 5.45 | learning rate: 8.424E-05 | global batch size: 512 | lm loss: 4.484284E+00 | loss scale: 65536.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.875 | TFLOPs: 70.90 | +[default7]: iteration 2097/ 3814 | consumed samples: 1073664 | consumed tokens: 2198863872 | elapsed time per iteration (s): 5.46 | learning rate: 8.416E-05 | global batch size: 512 | lm loss: 4.519411E+00 | loss scale: 65536.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.756 | TFLOPs: 70.82 | +[default7]: iteration 2098/ 3814 | consumed samples: 1074176 | consumed tokens: 2199912448 | elapsed time per iteration (s): 5.45 | learning rate: 8.409E-05 | global batch size: 512 | lm loss: 4.502837E+00 | loss scale: 65536.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 2099/ 3814 | consumed samples: 1074688 | consumed tokens: 2200961024 | elapsed time per iteration (s): 5.47 | learning rate: 8.401E-05 | global batch size: 512 | lm loss: 4.471559E+00 | loss scale: 65536.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.620 | TFLOPs: 70.71 | +[default7]: iteration 2100/ 3814 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 5.45 | learning rate: 8.393E-05 | global batch size: 512 | lm loss: 4.490039E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.887 | TFLOPs: 70.91 | +[default7]: iteration 2101/ 3814 | consumed samples: 1075712 | consumed tokens: 2203058176 | elapsed time per iteration (s): 5.44 | learning rate: 8.385E-05 | global batch size: 512 | lm loss: 4.509351E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.043 | TFLOPs: 71.03 | +[default7]: iteration 2102/ 3814 | consumed samples: 1076224 | consumed tokens: 2204106752 | elapsed time per iteration (s): 5.45 | learning rate: 8.378E-05 | global batch size: 512 | lm loss: 4.522108E+00 | loss scale: 65536.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.962 | TFLOPs: 70.97 | +[default7]: iteration 2103/ 3814 | consumed samples: 1076736 | consumed tokens: 2205155328 | elapsed time per iteration (s): 5.47 | learning rate: 8.370E-05 | global batch size: 512 | lm loss: 4.488785E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.576 | TFLOPs: 70.68 | +[default7]: iteration 2104/ 3814 | consumed samples: 1077248 | consumed tokens: 2206203904 | elapsed time per iteration (s): 5.50 | learning rate: 8.362E-05 | global batch size: 512 | lm loss: 4.498169E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.174 | TFLOPs: 70.38 | +[default7]: iteration 2105/ 3814 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 5.49 | learning rate: 8.354E-05 | global batch size: 512 | lm loss: 4.491157E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.311 | TFLOPs: 70.48 | +[default7]: iteration 2106/ 3814 | consumed samples: 1078272 | consumed tokens: 2208301056 | elapsed time per iteration (s): 5.48 | learning rate: 8.347E-05 | global batch size: 512 | lm loss: 4.524982E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.423 | TFLOPs: 70.56 | +[default7]: iteration 2107/ 3814 | consumed samples: 1078784 | consumed tokens: 2209349632 | elapsed time per iteration (s): 5.48 | learning rate: 8.339E-05 | global batch size: 512 | lm loss: 4.509370E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.494 | TFLOPs: 70.62 | +[default7]: iteration 2108/ 3814 | consumed samples: 1079296 | consumed tokens: 2210398208 | elapsed time per iteration (s): 5.48 | learning rate: 8.331E-05 | global batch size: 512 | lm loss: 4.509936E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.418 | TFLOPs: 70.56 | +[default7]: iteration 2109/ 3814 | consumed samples: 1079808 | consumed tokens: 2211446784 | elapsed time per iteration (s): 5.49 | learning rate: 8.324E-05 | global batch size: 512 | lm loss: 4.507986E+00 | loss scale: 65536.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.339 | TFLOPs: 70.50 | +[default7]: iteration 2110/ 3814 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 5.48 | learning rate: 8.316E-05 | global batch size: 512 | lm loss: 4.493701E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.406 | TFLOPs: 70.55 | +[default7]: iteration 2111/ 3814 | consumed samples: 1080832 | consumed tokens: 2213543936 | elapsed time per iteration (s): 5.47 | learning rate: 8.308E-05 | global batch size: 512 | lm loss: 4.505945E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.577 | TFLOPs: 70.68 | +[default7]: iteration 2112/ 3814 | consumed samples: 1081344 | consumed tokens: 2214592512 | elapsed time per iteration (s): 5.47 | learning rate: 8.300E-05 | global batch size: 512 | lm loss: 4.489606E+00 | loss scale: 65536.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.643 | TFLOPs: 70.73 | +[default7]: iteration 2113/ 3814 | consumed samples: 1081856 | consumed tokens: 2215641088 | elapsed time per iteration (s): 5.45 | learning rate: 8.293E-05 | global batch size: 512 | lm loss: 4.496648E+00 | loss scale: 65536.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.865 | TFLOPs: 70.90 | +[default7]: iteration 2114/ 3814 | consumed samples: 1082368 | consumed tokens: 2216689664 | elapsed time per iteration (s): 5.48 | learning rate: 8.285E-05 | global batch size: 512 | lm loss: 4.519042E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.447 | TFLOPs: 70.58 | +[default7]: iteration 2115/ 3814 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 5.49 | learning rate: 8.277E-05 | global batch size: 512 | lm loss: 4.521071E+00 | loss scale: 65536.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.258 | TFLOPs: 70.44 | +[default7]: iteration 2116/ 3814 | consumed samples: 1083392 | consumed tokens: 2218786816 | elapsed time per iteration (s): 5.47 | learning rate: 8.270E-05 | global batch size: 512 | lm loss: 4.517894E+00 | loss scale: 65536.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.518 | TFLOPs: 70.64 | +[default7]: iteration 2117/ 3814 | consumed samples: 1083904 | consumed tokens: 2219835392 | elapsed time per iteration (s): 5.47 | learning rate: 8.262E-05 | global batch size: 512 | lm loss: 4.480013E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.576 | TFLOPs: 70.68 | +[default7]: iteration 2118/ 3814 | consumed samples: 1084416 | consumed tokens: 2220883968 | elapsed time per iteration (s): 5.46 | learning rate: 8.254E-05 | global batch size: 512 | lm loss: 4.495346E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.732 | TFLOPs: 70.80 | +[default7]: iteration 2119/ 3814 | consumed samples: 1084928 | consumed tokens: 2221932544 | elapsed time per iteration (s): 5.46 | learning rate: 8.246E-05 | global batch size: 512 | lm loss: 4.510448E+00 | loss scale: 65536.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.718 | TFLOPs: 70.79 | +[default7]: iteration 2120/ 3814 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 5.48 | learning rate: 8.239E-05 | global batch size: 512 | lm loss: 4.475894E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.507 | TFLOPs: 70.63 | +[default7]: iteration 2121/ 3814 | consumed samples: 1085952 | consumed tokens: 2224029696 | elapsed time per iteration (s): 5.48 | learning rate: 8.231E-05 | global batch size: 512 | lm loss: 4.471994E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.427 | TFLOPs: 70.57 | +[default7]: iteration 2122/ 3814 | consumed samples: 1086464 | consumed tokens: 2225078272 | elapsed time per iteration (s): 5.46 | learning rate: 8.223E-05 | global batch size: 512 | lm loss: 4.470301E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.767 | TFLOPs: 70.82 | +[default7]: iteration 2123/ 3814 | consumed samples: 1086976 | consumed tokens: 2226126848 | elapsed time per iteration (s): 5.47 | learning rate: 8.216E-05 | global batch size: 512 | lm loss: 4.502178E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.576 | TFLOPs: 70.68 | +[default7]: iteration 2124/ 3814 | consumed samples: 1087488 | consumed tokens: 2227175424 | elapsed time per iteration (s): 5.49 | learning rate: 8.208E-05 | global batch size: 512 | lm loss: 4.492885E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.194 | TFLOPs: 70.39 | +[default7]: iteration 2125/ 3814 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 5.49 | learning rate: 8.200E-05 | global batch size: 512 | lm loss: 4.494401E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.194 | TFLOPs: 70.39 | +[default7]: iteration 2126/ 3814 | consumed samples: 1088512 | consumed tokens: 2229272576 | elapsed time per iteration (s): 5.49 | learning rate: 8.192E-05 | global batch size: 512 | lm loss: 4.479565E+00 | loss scale: 65536.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.255 | TFLOPs: 70.44 | +[default7]: iteration 2127/ 3814 | consumed samples: 1089024 | consumed tokens: 2230321152 | elapsed time per iteration (s): 5.50 | learning rate: 8.185E-05 | global batch size: 512 | lm loss: 4.495805E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.156 | TFLOPs: 70.36 | +[default7]: iteration 2128/ 3814 | consumed samples: 1089536 | consumed tokens: 2231369728 | elapsed time per iteration (s): 5.50 | learning rate: 8.177E-05 | global batch size: 512 | lm loss: 4.506560E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.136 | TFLOPs: 70.35 | +[default7]: iteration 2129/ 3814 | consumed samples: 1090048 | consumed tokens: 2232418304 | elapsed time per iteration (s): 5.48 | learning rate: 8.169E-05 | global batch size: 512 | lm loss: 4.494247E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.457 | TFLOPs: 70.59 | +[default7]: iteration 2130/ 3814 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 5.48 | learning rate: 8.161E-05 | global batch size: 512 | lm loss: 4.469273E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.514 | TFLOPs: 70.63 | +[default7]: iteration 2131/ 3814 | consumed samples: 1091072 | consumed tokens: 2234515456 | elapsed time per iteration (s): 5.48 | learning rate: 8.154E-05 | global batch size: 512 | lm loss: 4.506862E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.403 | TFLOPs: 70.55 | +[default7]: iteration 2132/ 3814 | consumed samples: 1091584 | consumed tokens: 2235564032 | elapsed time per iteration (s): 5.48 | learning rate: 8.146E-05 | global batch size: 512 | lm loss: 4.487588E+00 | loss scale: 65536.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.368 | TFLOPs: 70.52 | +[default7]: iteration 2133/ 3814 | consumed samples: 1092096 | consumed tokens: 2236612608 | elapsed time per iteration (s): 5.48 | learning rate: 8.138E-05 | global batch size: 512 | lm loss: 4.511074E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.512 | TFLOPs: 70.63 | +[default7]: iteration 2134/ 3814 | consumed samples: 1092608 | consumed tokens: 2237661184 | elapsed time per iteration (s): 5.48 | learning rate: 8.131E-05 | global batch size: 512 | lm loss: 4.479859E+00 | loss scale: 65536.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.364 | TFLOPs: 70.52 | +[default7]: iteration 2135/ 3814 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 5.49 | learning rate: 8.123E-05 | global batch size: 512 | lm loss: 4.485518E+00 | loss scale: 65536.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.333 | TFLOPs: 70.50 | +[default7]: iteration 2136/ 3814 | consumed samples: 1093632 | consumed tokens: 2239758336 | elapsed time per iteration (s): 5.47 | learning rate: 8.115E-05 | global batch size: 512 | lm loss: 4.488137E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.569 | TFLOPs: 70.67 | +[default7]: iteration 2137/ 3814 | consumed samples: 1094144 | consumed tokens: 2240806912 | elapsed time per iteration (s): 5.48 | learning rate: 8.107E-05 | global batch size: 512 | lm loss: 4.501334E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.508 | TFLOPs: 70.63 | +[default7]: iteration 2138/ 3814 | consumed samples: 1094656 | consumed tokens: 2241855488 | elapsed time per iteration (s): 5.47 | learning rate: 8.100E-05 | global batch size: 512 | lm loss: 4.490570E+00 | loss scale: 65536.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.537 | TFLOPs: 70.65 | +[default7]: iteration 2139/ 3814 | consumed samples: 1095168 | consumed tokens: 2242904064 | elapsed time per iteration (s): 5.48 | learning rate: 8.092E-05 | global batch size: 512 | lm loss: 4.468272E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.504 | TFLOPs: 70.62 | +[default7]: iteration 2140/ 3814 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 5.49 | learning rate: 8.084E-05 | global batch size: 512 | lm loss: 4.468681E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.301 | TFLOPs: 70.47 | +[default7]: iteration 2141/ 3814 | consumed samples: 1096192 | consumed tokens: 2245001216 | elapsed time per iteration (s): 5.46 | learning rate: 8.077E-05 | global batch size: 512 | lm loss: 4.479623E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.711 | TFLOPs: 70.78 | +[default7]: iteration 2142/ 3814 | consumed samples: 1096704 | consumed tokens: 2246049792 | elapsed time per iteration (s): 5.46 | learning rate: 8.069E-05 | global batch size: 512 | lm loss: 4.493261E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.695 | TFLOPs: 70.77 | +[default7]: iteration 2143/ 3814 | consumed samples: 1097216 | consumed tokens: 2247098368 | elapsed time per iteration (s): 5.48 | learning rate: 8.061E-05 | global batch size: 512 | lm loss: 4.472646E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.502 | TFLOPs: 70.62 | +[default7]: iteration 2144/ 3814 | consumed samples: 1097728 | consumed tokens: 2248146944 | elapsed time per iteration (s): 5.45 | learning rate: 8.053E-05 | global batch size: 512 | lm loss: 4.486711E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.898 | TFLOPs: 70.92 | +[default7]: iteration 2145/ 3814 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 5.45 | learning rate: 8.046E-05 | global batch size: 512 | lm loss: 4.470657E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.010 | TFLOPs: 71.01 | +[default7]: iteration 2146/ 3814 | consumed samples: 1098752 | consumed tokens: 2250244096 | elapsed time per iteration (s): 5.47 | learning rate: 8.038E-05 | global batch size: 512 | lm loss: 4.489738E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.673 | TFLOPs: 70.75 | +[default7]: iteration 2147/ 3814 | consumed samples: 1099264 | consumed tokens: 2251292672 | elapsed time per iteration (s): 5.47 | learning rate: 8.030E-05 | global batch size: 512 | lm loss: 4.486914E+00 | loss scale: 65536.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.631 | TFLOPs: 70.72 | +[default7]: iteration 2148/ 3814 | consumed samples: 1099776 | consumed tokens: 2252341248 | elapsed time per iteration (s): 5.45 | learning rate: 8.023E-05 | global batch size: 512 | lm loss: 4.487199E+00 | loss scale: 65536.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.877 | TFLOPs: 70.91 | +[default7]: iteration 2149/ 3814 | consumed samples: 1100288 | consumed tokens: 2253389824 | elapsed time per iteration (s): 5.46 | learning rate: 8.015E-05 | global batch size: 512 | lm loss: 4.461621E+00 | loss scale: 65536.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.827 | TFLOPs: 70.87 | +[default7]: iteration 2150/ 3814 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 5.46 | learning rate: 8.007E-05 | global batch size: 512 | lm loss: 4.494339E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.764 | TFLOPs: 70.82 | +[default7]: iteration 2151/ 3814 | consumed samples: 1101312 | consumed tokens: 2255486976 | elapsed time per iteration (s): 5.49 | learning rate: 7.999E-05 | global batch size: 512 | lm loss: 4.482142E+00 | loss scale: 65536.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.332 | TFLOPs: 70.49 | +[default7]: iteration 2152/ 3814 | consumed samples: 1101824 | consumed tokens: 2256535552 | elapsed time per iteration (s): 5.47 | learning rate: 7.992E-05 | global batch size: 512 | lm loss: 4.474633E+00 | loss scale: 65536.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.612 | TFLOPs: 70.71 | +[default7]: iteration 2153/ 3814 | consumed samples: 1102336 | consumed tokens: 2257584128 | elapsed time per iteration (s): 5.48 | learning rate: 7.984E-05 | global batch size: 512 | lm loss: 4.467730E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.461 | TFLOPs: 70.59 | +[default7]: iteration 2154/ 3814 | consumed samples: 1102848 | consumed tokens: 2258632704 | elapsed time per iteration (s): 5.47 | learning rate: 7.976E-05 | global batch size: 512 | lm loss: 4.484496E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.565 | TFLOPs: 70.67 | +[default7]: iteration 2155/ 3814 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 5.49 | learning rate: 7.969E-05 | global batch size: 512 | lm loss: 4.491659E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.327 | TFLOPs: 70.49 | +[default7]: iteration 2156/ 3814 | consumed samples: 1103872 | consumed tokens: 2260729856 | elapsed time per iteration (s): 5.47 | learning rate: 7.961E-05 | global batch size: 512 | lm loss: 4.483784E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.593 | TFLOPs: 70.69 | +[default7]: iteration 2157/ 3814 | consumed samples: 1104384 | consumed tokens: 2261778432 | elapsed time per iteration (s): 5.46 | learning rate: 7.953E-05 | global batch size: 512 | lm loss: 4.480958E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.764 | TFLOPs: 70.82 | +[default7]: iteration 2158/ 3814 | consumed samples: 1104896 | consumed tokens: 2262827008 | elapsed time per iteration (s): 5.47 | learning rate: 7.945E-05 | global batch size: 512 | lm loss: 4.477269E+00 | loss scale: 65536.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.684 | TFLOPs: 70.76 | +[default7]: iteration 2159/ 3814 | consumed samples: 1105408 | consumed tokens: 2263875584 | elapsed time per iteration (s): 5.48 | learning rate: 7.938E-05 | global batch size: 512 | lm loss: 4.471805E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.347 | TFLOPs: 70.51 | +[default7]: iteration 2160/ 3814 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 5.48 | learning rate: 7.930E-05 | global batch size: 512 | lm loss: 4.475212E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.449 | TFLOPs: 70.58 | +[default7]: iteration 2161/ 3814 | consumed samples: 1106432 | consumed tokens: 2265972736 | elapsed time per iteration (s): 5.49 | learning rate: 7.922E-05 | global batch size: 512 | lm loss: 4.476121E+00 | loss scale: 65536.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.311 | TFLOPs: 70.48 | +[default7]: iteration 2162/ 3814 | consumed samples: 1106944 | consumed tokens: 2267021312 | elapsed time per iteration (s): 5.48 | learning rate: 7.915E-05 | global batch size: 512 | lm loss: 4.460417E+00 | loss scale: 65536.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.458 | TFLOPs: 70.59 | +[default7]: iteration 2163/ 3814 | consumed samples: 1107456 | consumed tokens: 2268069888 | elapsed time per iteration (s): 5.48 | learning rate: 7.907E-05 | global batch size: 512 | lm loss: 4.492331E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.501 | TFLOPs: 70.62 | +[default7]: iteration 2164/ 3814 | consumed samples: 1107968 | consumed tokens: 2269118464 | elapsed time per iteration (s): 5.47 | learning rate: 7.899E-05 | global batch size: 512 | lm loss: 4.453871E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.674 | TFLOPs: 70.75 | +[default7]: iteration 2165/ 3814 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 5.45 | learning rate: 7.892E-05 | global batch size: 512 | lm loss: 4.498915E+00 | loss scale: 65536.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.900 | TFLOPs: 70.92 | +[default7]: iteration 2166/ 3814 | consumed samples: 1108992 | consumed tokens: 2271215616 | elapsed time per iteration (s): 5.46 | learning rate: 7.884E-05 | global batch size: 512 | lm loss: 4.479038E+00 | loss scale: 65536.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.701 | TFLOPs: 70.77 | +[default7]: iteration 2167/ 3814 | consumed samples: 1109504 | consumed tokens: 2272264192 | elapsed time per iteration (s): 5.46 | learning rate: 7.876E-05 | global batch size: 512 | lm loss: 4.462771E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.728 | TFLOPs: 70.79 | +[default7]: iteration 2168/ 3814 | consumed samples: 1110016 | consumed tokens: 2273312768 | elapsed time per iteration (s): 5.47 | learning rate: 7.868E-05 | global batch size: 512 | lm loss: 4.444714E+00 | loss scale: 65536.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.638 | TFLOPs: 70.73 | +[default7]: iteration 2169/ 3814 | consumed samples: 1110528 | consumed tokens: 2274361344 | elapsed time per iteration (s): 5.46 | learning rate: 7.861E-05 | global batch size: 512 | lm loss: 4.464656E+00 | loss scale: 65536.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.802 | TFLOPs: 70.85 | +[default7]: iteration 2170/ 3814 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 5.46 | learning rate: 7.853E-05 | global batch size: 512 | lm loss: 4.466877E+00 | loss scale: 65536.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.746 | TFLOPs: 70.81 | +[default7]: iteration 2171/ 3814 | consumed samples: 1111552 | consumed tokens: 2276458496 | elapsed time per iteration (s): 5.49 | learning rate: 7.845E-05 | global batch size: 512 | lm loss: 4.465550E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.314 | TFLOPs: 70.48 | +[default7]: iteration 2172/ 3814 | consumed samples: 1112064 | consumed tokens: 2277507072 | elapsed time per iteration (s): 5.46 | learning rate: 7.838E-05 | global batch size: 512 | lm loss: 4.443608E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.725 | TFLOPs: 70.79 | +[default7]: iteration 2173/ 3814 | consumed samples: 1112576 | consumed tokens: 2278555648 | elapsed time per iteration (s): 5.46 | learning rate: 7.830E-05 | global batch size: 512 | lm loss: 4.490176E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.740 | TFLOPs: 70.80 | +[default7]: iteration 2174/ 3814 | consumed samples: 1113088 | consumed tokens: 2279604224 | elapsed time per iteration (s): 5.47 | learning rate: 7.822E-05 | global batch size: 512 | lm loss: 4.491118E+00 | loss scale: 65536.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.655 | TFLOPs: 70.74 | +[default7]: iteration 2175/ 3814 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 5.46 | learning rate: 7.815E-05 | global batch size: 512 | lm loss: 4.464286E+00 | loss scale: 65536.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.797 | TFLOPs: 70.85 | +[default7]: iteration 2176/ 3814 | consumed samples: 1114112 | consumed tokens: 2281701376 | elapsed time per iteration (s): 5.44 | learning rate: 7.807E-05 | global batch size: 512 | lm loss: 4.448228E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.164 | TFLOPs: 71.12 | +[default7]: iteration 2177/ 3814 | consumed samples: 1114624 | consumed tokens: 2282749952 | elapsed time per iteration (s): 5.48 | learning rate: 7.799E-05 | global batch size: 512 | lm loss: 4.476686E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.413 | TFLOPs: 70.56 | +[default7]: iteration 2178/ 3814 | consumed samples: 1115136 | consumed tokens: 2283798528 | elapsed time per iteration (s): 5.48 | learning rate: 7.791E-05 | global batch size: 512 | lm loss: 4.504617E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.365 | TFLOPs: 70.52 | +[default7]: iteration 2179/ 3814 | consumed samples: 1115648 | consumed tokens: 2284847104 | elapsed time per iteration (s): 5.46 | learning rate: 7.784E-05 | global batch size: 512 | lm loss: 4.479357E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.696 | TFLOPs: 70.77 | +[default7]: iteration 2180/ 3814 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 5.49 | learning rate: 7.776E-05 | global batch size: 512 | lm loss: 4.470504E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.300 | TFLOPs: 70.47 | +[default7]: iteration 2181/ 3814 | consumed samples: 1116672 | consumed tokens: 2286944256 | elapsed time per iteration (s): 5.48 | learning rate: 7.768E-05 | global batch size: 512 | lm loss: 4.468180E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.431 | TFLOPs: 70.57 | +[default7]: iteration 2182/ 3814 | consumed samples: 1117184 | consumed tokens: 2287992832 | elapsed time per iteration (s): 5.50 | learning rate: 7.761E-05 | global batch size: 512 | lm loss: 4.466324E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.116 | TFLOPs: 70.33 | +[default7]: iteration 2183/ 3814 | consumed samples: 1117696 | consumed tokens: 2289041408 | elapsed time per iteration (s): 5.49 | learning rate: 7.753E-05 | global batch size: 512 | lm loss: 4.442025E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.186 | TFLOPs: 70.38 | +[default7]: iteration 2184/ 3814 | consumed samples: 1118208 | consumed tokens: 2290089984 | elapsed time per iteration (s): 5.49 | learning rate: 7.745E-05 | global batch size: 512 | lm loss: 4.493073E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.267 | TFLOPs: 70.45 | +[default7]: iteration 2185/ 3814 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 5.49 | learning rate: 7.738E-05 | global batch size: 512 | lm loss: 4.454032E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.249 | TFLOPs: 70.43 | +[default7]: iteration 2186/ 3814 | consumed samples: 1119232 | consumed tokens: 2292187136 | elapsed time per iteration (s): 5.47 | learning rate: 7.730E-05 | global batch size: 512 | lm loss: 4.475557E+00 | loss scale: 65536.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.619 | TFLOPs: 70.71 | +[default7]: iteration 2187/ 3814 | consumed samples: 1119744 | consumed tokens: 2293235712 | elapsed time per iteration (s): 5.47 | learning rate: 7.722E-05 | global batch size: 512 | lm loss: 4.481802E+00 | loss scale: 65536.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.564 | TFLOPs: 70.67 | +[default7]: iteration 2188/ 3814 | consumed samples: 1120256 | consumed tokens: 2294284288 | elapsed time per iteration (s): 5.47 | learning rate: 7.714E-05 | global batch size: 512 | lm loss: 4.456216E+00 | loss scale: 65536.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.647 | TFLOPs: 70.73 | +[default7]: iteration 2189/ 3814 | consumed samples: 1120768 | consumed tokens: 2295332864 | elapsed time per iteration (s): 5.48 | learning rate: 7.707E-05 | global batch size: 512 | lm loss: 4.476274E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.397 | TFLOPs: 70.54 | +[default7]: iteration 2190/ 3814 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 5.47 | learning rate: 7.699E-05 | global batch size: 512 | lm loss: 4.464686E+00 | loss scale: 65536.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.627 | TFLOPs: 70.72 | +[default7]: iteration 2191/ 3814 | consumed samples: 1121792 | consumed tokens: 2297430016 | elapsed time per iteration (s): 5.47 | learning rate: 7.691E-05 | global batch size: 512 | lm loss: 4.468720E+00 | loss scale: 65536.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.614 | TFLOPs: 70.71 | +[default7]: iteration 2192/ 3814 | consumed samples: 1122304 | consumed tokens: 2298478592 | elapsed time per iteration (s): 5.46 | learning rate: 7.684E-05 | global batch size: 512 | lm loss: 4.466136E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.771 | TFLOPs: 70.83 | +[default7]: iteration 2193/ 3814 | consumed samples: 1122816 | consumed tokens: 2299527168 | elapsed time per iteration (s): 5.47 | learning rate: 7.676E-05 | global batch size: 512 | lm loss: 4.484074E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.519 | TFLOPs: 70.64 | +[default7]: iteration 2194/ 3814 | consumed samples: 1123328 | consumed tokens: 2300575744 | elapsed time per iteration (s): 5.46 | learning rate: 7.668E-05 | global batch size: 512 | lm loss: 4.486758E+00 | loss scale: 65536.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.711 | TFLOPs: 70.78 | +[default7]: iteration 2195/ 3814 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 5.46 | learning rate: 7.661E-05 | global batch size: 512 | lm loss: 4.478808E+00 | loss scale: 65536.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.777 | TFLOPs: 70.83 | +[default7]: iteration 2196/ 3814 | consumed samples: 1124352 | consumed tokens: 2302672896 | elapsed time per iteration (s): 5.43 | learning rate: 7.653E-05 | global batch size: 512 | lm loss: 4.446139E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 2197/ 3814 | consumed samples: 1124864 | consumed tokens: 2303721472 | elapsed time per iteration (s): 5.47 | learning rate: 7.645E-05 | global batch size: 512 | lm loss: 4.473352E+00 | loss scale: 65536.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.622 | TFLOPs: 70.71 | +[default7]: iteration 2198/ 3814 | consumed samples: 1125376 | consumed tokens: 2304770048 | elapsed time per iteration (s): 5.46 | learning rate: 7.638E-05 | global batch size: 512 | lm loss: 4.461140E+00 | loss scale: 65536.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.807 | TFLOPs: 70.85 | +[default7]: iteration 2199/ 3814 | consumed samples: 1125888 | consumed tokens: 2305818624 | elapsed time per iteration (s): 5.48 | learning rate: 7.630E-05 | global batch size: 512 | lm loss: 4.427883E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.436 | TFLOPs: 70.57 | +[default7]: iteration 2200/ 3814 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 5.46 | learning rate: 7.622E-05 | global batch size: 512 | lm loss: 4.466843E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.750 | TFLOPs: 70.81 | +[default7]: iteration 2201/ 3814 | consumed samples: 1126912 | consumed tokens: 2307915776 | elapsed time per iteration (s): 5.45 | learning rate: 7.615E-05 | global batch size: 512 | lm loss: 4.468472E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.951 | TFLOPs: 70.96 | +[default7]: iteration 2202/ 3814 | consumed samples: 1127424 | consumed tokens: 2308964352 | elapsed time per iteration (s): 5.46 | learning rate: 7.607E-05 | global batch size: 512 | lm loss: 4.466290E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.742 | TFLOPs: 70.80 | +[default7]: iteration 2203/ 3814 | consumed samples: 1127936 | consumed tokens: 2310012928 | elapsed time per iteration (s): 5.44 | learning rate: 7.599E-05 | global batch size: 512 | lm loss: 4.444793E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.046 | TFLOPs: 71.03 | +[default7]: iteration 2204/ 3814 | consumed samples: 1128448 | consumed tokens: 2311061504 | elapsed time per iteration (s): 5.44 | learning rate: 7.592E-05 | global batch size: 512 | lm loss: 4.434297E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 2205/ 3814 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 5.44 | learning rate: 7.584E-05 | global batch size: 512 | lm loss: 4.476741E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.188 | TFLOPs: 71.14 | +[default7]: iteration 2206/ 3814 | consumed samples: 1129472 | consumed tokens: 2313158656 | elapsed time per iteration (s): 5.43 | learning rate: 7.576E-05 | global batch size: 512 | lm loss: 4.470006E+00 | loss scale: 65536.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 2207/ 3814 | consumed samples: 1129984 | consumed tokens: 2314207232 | elapsed time per iteration (s): 5.44 | learning rate: 7.568E-05 | global batch size: 512 | lm loss: 4.449365E+00 | loss scale: 65536.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 2208/ 3814 | consumed samples: 1130496 | consumed tokens: 2315255808 | elapsed time per iteration (s): 5.43 | learning rate: 7.561E-05 | global batch size: 512 | lm loss: 4.458086E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.238 | TFLOPs: 71.18 | +[default7]: iteration 2209/ 3814 | consumed samples: 1131008 | consumed tokens: 2316304384 | elapsed time per iteration (s): 5.45 | learning rate: 7.553E-05 | global batch size: 512 | lm loss: 4.458913E+00 | loss scale: 65536.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.955 | TFLOPs: 70.96 | +[default7]: iteration 2210/ 3814 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 5.44 | learning rate: 7.545E-05 | global batch size: 512 | lm loss: 4.476953E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.146 | TFLOPs: 71.11 | +[default7]: iteration 2211/ 3814 | consumed samples: 1132032 | consumed tokens: 2318401536 | elapsed time per iteration (s): 5.46 | learning rate: 7.538E-05 | global batch size: 512 | lm loss: 4.438626E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.796 | TFLOPs: 70.85 | +[default7]: iteration 2212/ 3814 | consumed samples: 1132544 | consumed tokens: 2319450112 | elapsed time per iteration (s): 5.45 | learning rate: 7.530E-05 | global batch size: 512 | lm loss: 4.460618E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.888 | TFLOPs: 70.91 | +[default7]: iteration 2213/ 3814 | consumed samples: 1133056 | consumed tokens: 2320498688 | elapsed time per iteration (s): 5.45 | learning rate: 7.522E-05 | global batch size: 512 | lm loss: 4.462653E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.016 | TFLOPs: 71.01 | +[default7]: iteration 2214/ 3814 | consumed samples: 1133568 | consumed tokens: 2321547264 | elapsed time per iteration (s): 5.44 | learning rate: 7.515E-05 | global batch size: 512 | lm loss: 4.443022E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.112 | TFLOPs: 71.08 | +[default7]: iteration 2215/ 3814 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 5.47 | learning rate: 7.507E-05 | global batch size: 512 | lm loss: 4.448401E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.672 | TFLOPs: 70.75 | +[default7]: iteration 2216/ 3814 | consumed samples: 1134592 | consumed tokens: 2323644416 | elapsed time per iteration (s): 5.46 | learning rate: 7.499E-05 | global batch size: 512 | lm loss: 4.455767E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.737 | TFLOPs: 70.80 | +[default7]: iteration 2217/ 3814 | consumed samples: 1135104 | consumed tokens: 2324692992 | elapsed time per iteration (s): 5.46 | learning rate: 7.492E-05 | global batch size: 512 | lm loss: 4.456684E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.727 | TFLOPs: 70.79 | +[default7]: iteration 2218/ 3814 | consumed samples: 1135616 | consumed tokens: 2325741568 | elapsed time per iteration (s): 5.45 | learning rate: 7.484E-05 | global batch size: 512 | lm loss: 4.474514E+00 | loss scale: 65536.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.016 | TFLOPs: 71.01 | +[default7]: iteration 2219/ 3814 | consumed samples: 1136128 | consumed tokens: 2326790144 | elapsed time per iteration (s): 5.44 | learning rate: 7.476E-05 | global batch size: 512 | lm loss: 4.450318E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 2220/ 3814 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 5.46 | learning rate: 7.469E-05 | global batch size: 512 | lm loss: 4.434642E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.722 | TFLOPs: 70.79 | +[default7]: iteration 2221/ 3814 | consumed samples: 1137152 | consumed tokens: 2328887296 | elapsed time per iteration (s): 5.47 | learning rate: 7.461E-05 | global batch size: 512 | lm loss: 4.488637E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.625 | TFLOPs: 70.72 | +[default7]: iteration 2222/ 3814 | consumed samples: 1137664 | consumed tokens: 2329935872 | elapsed time per iteration (s): 5.46 | learning rate: 7.453E-05 | global batch size: 512 | lm loss: 4.439715E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.714 | TFLOPs: 70.78 | +[default7]: iteration 2223/ 3814 | consumed samples: 1138176 | consumed tokens: 2330984448 | elapsed time per iteration (s): 5.45 | learning rate: 7.446E-05 | global batch size: 512 | lm loss: 4.454924E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.876 | TFLOPs: 70.91 | +[default7]: iteration 2224/ 3814 | consumed samples: 1138688 | consumed tokens: 2332033024 | elapsed time per iteration (s): 5.47 | learning rate: 7.438E-05 | global batch size: 512 | lm loss: 4.474217E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.685 | TFLOPs: 70.76 | +[default7]: iteration 2225/ 3814 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 5.46 | learning rate: 7.430E-05 | global batch size: 512 | lm loss: 4.478107E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.805 | TFLOPs: 70.85 | +[default7]: iteration 2226/ 3814 | consumed samples: 1139712 | consumed tokens: 2334130176 | elapsed time per iteration (s): 5.44 | learning rate: 7.423E-05 | global batch size: 512 | lm loss: 4.451006E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 2227/ 3814 | consumed samples: 1140224 | consumed tokens: 2335178752 | elapsed time per iteration (s): 5.45 | learning rate: 7.415E-05 | global batch size: 512 | lm loss: 4.441426E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.873 | TFLOPs: 70.90 | +[default7]: iteration 2228/ 3814 | consumed samples: 1140736 | consumed tokens: 2336227328 | elapsed time per iteration (s): 5.45 | learning rate: 7.407E-05 | global batch size: 512 | lm loss: 4.460960E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.986 | TFLOPs: 70.99 | +[default7]: iteration 2229/ 3814 | consumed samples: 1141248 | consumed tokens: 2337275904 | elapsed time per iteration (s): 5.45 | learning rate: 7.400E-05 | global batch size: 512 | lm loss: 4.443700E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.954 | TFLOPs: 70.96 | +[default7]: iteration 2230/ 3814 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 5.47 | learning rate: 7.392E-05 | global batch size: 512 | lm loss: 4.441212E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.521 | TFLOPs: 70.64 | +[default7]: iteration 2231/ 3814 | consumed samples: 1142272 | consumed tokens: 2339373056 | elapsed time per iteration (s): 5.47 | learning rate: 7.384E-05 | global batch size: 512 | lm loss: 4.402623E+00 | loss scale: 65536.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.650 | TFLOPs: 70.73 | +[default7]: iteration 2232/ 3814 | consumed samples: 1142784 | consumed tokens: 2340421632 | elapsed time per iteration (s): 5.44 | learning rate: 7.377E-05 | global batch size: 512 | lm loss: 4.443705E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.104 | TFLOPs: 71.08 | +[default7]: iteration 2233/ 3814 | consumed samples: 1143296 | consumed tokens: 2341470208 | elapsed time per iteration (s): 5.45 | learning rate: 7.369E-05 | global batch size: 512 | lm loss: 4.441974E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.911 | TFLOPs: 70.93 | +[default7]: iteration 2234/ 3814 | consumed samples: 1143808 | consumed tokens: 2342518784 | elapsed time per iteration (s): 5.44 | learning rate: 7.361E-05 | global batch size: 512 | lm loss: 4.453985E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.175 | TFLOPs: 71.13 | +[default7]: iteration 2235/ 3814 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 5.45 | learning rate: 7.354E-05 | global batch size: 512 | lm loss: 4.445972E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.925 | TFLOPs: 70.94 | +[default7]: iteration 2236/ 3814 | consumed samples: 1144832 | consumed tokens: 2344615936 | elapsed time per iteration (s): 5.45 | learning rate: 7.346E-05 | global batch size: 512 | lm loss: 4.472097E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.891 | TFLOPs: 70.92 | +[default7]: iteration 2237/ 3814 | consumed samples: 1145344 | consumed tokens: 2345664512 | elapsed time per iteration (s): 5.46 | learning rate: 7.339E-05 | global batch size: 512 | lm loss: 4.428170E+00 | loss scale: 65536.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.851 | TFLOPs: 70.89 | +[default7]: iteration 2238/ 3814 | consumed samples: 1145856 | consumed tokens: 2346713088 | elapsed time per iteration (s): 5.47 | learning rate: 7.331E-05 | global batch size: 512 | lm loss: 4.439850E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.639 | TFLOPs: 70.73 | +[default7]: iteration 2239/ 3814 | consumed samples: 1146368 | consumed tokens: 2347761664 | elapsed time per iteration (s): 5.49 | learning rate: 7.323E-05 | global batch size: 512 | lm loss: 4.444293E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.337 | TFLOPs: 70.50 | +[default7]: iteration 2240/ 3814 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 5.46 | learning rate: 7.316E-05 | global batch size: 512 | lm loss: 4.433697E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.756 | TFLOPs: 70.82 | +[default7]: iteration 2241/ 3814 | consumed samples: 1147392 | consumed tokens: 2349858816 | elapsed time per iteration (s): 5.46 | learning rate: 7.308E-05 | global batch size: 512 | lm loss: 4.440627E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.746 | TFLOPs: 70.81 | +[default7]: iteration 2242/ 3814 | consumed samples: 1147904 | consumed tokens: 2350907392 | elapsed time per iteration (s): 5.48 | learning rate: 7.300E-05 | global batch size: 512 | lm loss: 4.419806E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.478 | TFLOPs: 70.60 | +[default7]: iteration 2243/ 3814 | consumed samples: 1148416 | consumed tokens: 2351955968 | elapsed time per iteration (s): 5.44 | learning rate: 7.293E-05 | global batch size: 512 | lm loss: 4.414628E+00 | loss scale: 65536.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.084 | TFLOPs: 71.06 | +[default7]: iteration 2244/ 3814 | consumed samples: 1148928 | consumed tokens: 2353004544 | elapsed time per iteration (s): 5.46 | learning rate: 7.285E-05 | global batch size: 512 | lm loss: 4.464672E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.765 | TFLOPs: 70.82 | +[default7]: iteration 2245/ 3814 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 5.45 | learning rate: 7.277E-05 | global batch size: 512 | lm loss: 4.438881E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.980 | TFLOPs: 70.98 | +[default7]: iteration 2246/ 3814 | consumed samples: 1149952 | consumed tokens: 2355101696 | elapsed time per iteration (s): 5.45 | learning rate: 7.270E-05 | global batch size: 512 | lm loss: 4.436606E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.017 | TFLOPs: 71.01 | +[default7]: iteration 2247/ 3814 | consumed samples: 1150464 | consumed tokens: 2356150272 | elapsed time per iteration (s): 5.47 | learning rate: 7.262E-05 | global batch size: 512 | lm loss: 4.442920E+00 | loss scale: 65536.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.597 | TFLOPs: 70.69 | +[default7]: iteration 2248/ 3814 | consumed samples: 1150976 | consumed tokens: 2357198848 | elapsed time per iteration (s): 5.46 | learning rate: 7.254E-05 | global batch size: 512 | lm loss: 4.443066E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.832 | TFLOPs: 70.87 | +[default7]: iteration 2249/ 3814 | consumed samples: 1151488 | consumed tokens: 2358247424 | elapsed time per iteration (s): 5.45 | learning rate: 7.247E-05 | global batch size: 512 | lm loss: 4.398654E+00 | loss scale: 65536.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.002 | TFLOPs: 71.00 | +[default7]: iteration 2250/ 3814 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 5.44 | learning rate: 7.239E-05 | global batch size: 512 | lm loss: 4.428164E+00 | loss scale: 65536.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.077 | TFLOPs: 71.06 | +[default0]:saving checkpoint at iteration 2250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 14:44:12,938] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2250 is begin to save! +[default0]:[2023-02-16 14:44:12,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:12,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,108] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,111] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,163] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,227] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,282] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,396] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,387] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,509] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,554] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,664] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,675] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,716] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,809] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,867] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:13,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,903] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:13,955] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:13,955] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:13,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:13,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:13,974] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,006] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,027] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,085] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,121] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,173] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,282] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,336] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,369] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,390] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,449] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,424] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,485] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,578] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,680] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,747] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,738] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,796] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,802] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,855] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 14:44:14,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,851] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,907] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:44:14,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 14:44:14,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 14:44:14,913] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:14,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 14:44:14,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:44:14,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,959] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 14:44:14,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 14:44:14,961] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 14:44:14,961] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 14:44:14,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 14:44:14,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 14:44:15,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,509] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,516] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,528] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,535] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,566] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,553] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,525] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,535] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,558] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,594] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,582] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,551] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,562] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,582] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,618] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,640] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,650] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,628] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,635] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,620] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,674] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,677] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,692] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,618] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,625] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,709] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,644] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,703] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,680] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,675] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,663] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,680] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,666] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,688] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,667] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,657] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,752] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,740] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,724] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,714] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,682] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,713] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,706] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,691] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,706] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,766] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 14:44:15,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 14:44:15,745] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 14:44:15,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,775] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,817] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,765] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,754] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,827] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 14:44:15,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 14:44:15,815] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 14:44:15,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,845] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 14:44:15,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 14:44:15,854] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 14:44:15,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 14:44:15,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 14:44:15,798] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 14:44:15,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 14:44:15,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,805] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,797] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,811] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 14:44:15,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 14:44:15,852] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 14:44:15,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:time (ms) | save-checkpoint: 2918.21 +[default0]: successfully saved checkpoint at iteration 2250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:[2023-02-16 14:44:15,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 14:44:15,831] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 14:44:15,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 14:44:15,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 14:44:15,824] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 14:44:15,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 14:44:15,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 14:44:15,826] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 14:44:15,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]: iteration 2251/ 3814 | consumed samples: 1152512 | consumed tokens: 2360344576 | elapsed time per iteration (s): 8.37 | learning rate: 7.231E-05 | global batch size: 512 | lm loss: 4.435579E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 61.180 | TFLOPs: 46.21 | +[default7]: iteration 2252/ 3814 | consumed samples: 1153024 | consumed tokens: 2361393152 | elapsed time per iteration (s): 5.45 | learning rate: 7.224E-05 | global batch size: 512 | lm loss: 4.419803E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.978 | TFLOPs: 70.98 | +[default7]: iteration 2253/ 3814 | consumed samples: 1153536 | consumed tokens: 2362441728 | elapsed time per iteration (s): 5.44 | learning rate: 7.216E-05 | global batch size: 512 | lm loss: 4.413712E+00 | loss scale: 65536.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.089 | TFLOPs: 71.07 | +[default7]: iteration 2254/ 3814 | consumed samples: 1154048 | consumed tokens: 2363490304 | elapsed time per iteration (s): 5.44 | learning rate: 7.209E-05 | global batch size: 512 | lm loss: 4.444790E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 2255/ 3814 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 5.45 | learning rate: 7.201E-05 | global batch size: 512 | lm loss: 4.420563E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.893 | TFLOPs: 70.92 | +[default7]: iteration 2256/ 3814 | consumed samples: 1155072 | consumed tokens: 2365587456 | elapsed time per iteration (s): 5.44 | learning rate: 7.193E-05 | global batch size: 512 | lm loss: 4.425757E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.070 | TFLOPs: 71.05 | +[default7]: iteration 2257/ 3814 | consumed samples: 1155584 | consumed tokens: 2366636032 | elapsed time per iteration (s): 5.45 | learning rate: 7.186E-05 | global batch size: 512 | lm loss: 4.432553E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.989 | TFLOPs: 70.99 | +[default7]: iteration 2258/ 3814 | consumed samples: 1156096 | consumed tokens: 2367684608 | elapsed time per iteration (s): 5.45 | learning rate: 7.178E-05 | global batch size: 512 | lm loss: 4.428664E+00 | loss scale: 65536.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.965 | TFLOPs: 70.97 | +[default7]: iteration 2259/ 3814 | consumed samples: 1156608 | consumed tokens: 2368733184 | elapsed time per iteration (s): 5.45 | learning rate: 7.170E-05 | global batch size: 512 | lm loss: 4.437041E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.920 | TFLOPs: 70.94 | +[default7]: iteration 2260/ 3814 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 5.45 | learning rate: 7.163E-05 | global batch size: 512 | lm loss: 4.448740E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.012 | TFLOPs: 71.01 | +[default7]: iteration 2261/ 3814 | consumed samples: 1157632 | consumed tokens: 2370830336 | elapsed time per iteration (s): 5.46 | learning rate: 7.155E-05 | global batch size: 512 | lm loss: 4.411252E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.849 | TFLOPs: 70.89 | +[default7]: iteration 2262/ 3814 | consumed samples: 1158144 | consumed tokens: 2371878912 | elapsed time per iteration (s): 5.45 | learning rate: 7.148E-05 | global batch size: 512 | lm loss: 4.430361E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.975 | TFLOPs: 70.98 | +[default7]: iteration 2263/ 3814 | consumed samples: 1158656 | consumed tokens: 2372927488 | elapsed time per iteration (s): 5.44 | learning rate: 7.140E-05 | global batch size: 512 | lm loss: 4.435050E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.114 | TFLOPs: 71.09 | +[default7]: iteration 2264/ 3814 | consumed samples: 1159168 | consumed tokens: 2373976064 | elapsed time per iteration (s): 5.45 | learning rate: 7.132E-05 | global batch size: 512 | lm loss: 4.421616E+00 | loss scale: 65536.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.023 | TFLOPs: 71.02 | +[default7]: iteration 2265/ 3814 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 5.45 | learning rate: 7.125E-05 | global batch size: 512 | lm loss: 4.413078E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.904 | TFLOPs: 70.93 | +[default7]: iteration 2266/ 3814 | consumed samples: 1160192 | consumed tokens: 2376073216 | elapsed time per iteration (s): 5.43 | learning rate: 7.117E-05 | global batch size: 512 | lm loss: 4.428423E+00 | loss scale: 65536.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.221 | TFLOPs: 71.17 | +[default7]: iteration 2267/ 3814 | consumed samples: 1160704 | consumed tokens: 2377121792 | elapsed time per iteration (s): 5.44 | learning rate: 7.109E-05 | global batch size: 512 | lm loss: 4.462213E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 2268/ 3814 | consumed samples: 1161216 | consumed tokens: 2378170368 | elapsed time per iteration (s): 5.43 | learning rate: 7.102E-05 | global batch size: 512 | lm loss: 4.414899E+00 | loss scale: 65536.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.368 | TFLOPs: 71.28 | +[default7]: iteration 2269/ 3814 | consumed samples: 1161728 | consumed tokens: 2379218944 | elapsed time per iteration (s): 5.44 | learning rate: 7.094E-05 | global batch size: 512 | lm loss: 4.448836E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 2270/ 3814 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 5.47 | learning rate: 7.087E-05 | global batch size: 512 | lm loss: 4.428165E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.551 | TFLOPs: 70.66 | +[default7]: iteration 2271/ 3814 | consumed samples: 1162752 | consumed tokens: 2381316096 | elapsed time per iteration (s): 5.44 | learning rate: 7.079E-05 | global batch size: 512 | lm loss: 4.425276E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.104 | TFLOPs: 71.08 | +[default7]: iteration 2272/ 3814 | consumed samples: 1163264 | consumed tokens: 2382364672 | elapsed time per iteration (s): 5.43 | learning rate: 7.071E-05 | global batch size: 512 | lm loss: 4.446184E+00 | loss scale: 65536.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 2273/ 3814 | consumed samples: 1163776 | consumed tokens: 2383413248 | elapsed time per iteration (s): 5.45 | learning rate: 7.064E-05 | global batch size: 512 | lm loss: 4.415312E+00 | loss scale: 65536.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.894 | TFLOPs: 70.92 | +[default7]: iteration 2274/ 3814 | consumed samples: 1164288 | consumed tokens: 2384461824 | elapsed time per iteration (s): 5.45 | learning rate: 7.056E-05 | global batch size: 512 | lm loss: 4.435437E+00 | loss scale: 65536.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.939 | TFLOPs: 70.95 | +[default7]: iteration 2275/ 3814 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 5.46 | learning rate: 7.049E-05 | global batch size: 512 | lm loss: 4.478637E+00 | loss scale: 65536.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.816 | TFLOPs: 70.86 | +[default7]: iteration 2276/ 3814 | consumed samples: 1165312 | consumed tokens: 2386558976 | elapsed time per iteration (s): 5.46 | learning rate: 7.041E-05 | global batch size: 512 | lm loss: 4.439253E+00 | loss scale: 65536.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.766 | TFLOPs: 70.82 | +[default7]: iteration 2277/ 3814 | consumed samples: 1165824 | consumed tokens: 2387607552 | elapsed time per iteration (s): 5.45 | learning rate: 7.033E-05 | global batch size: 512 | lm loss: 4.431737E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 2278/ 3814 | consumed samples: 1166336 | consumed tokens: 2388656128 | elapsed time per iteration (s): 5.44 | learning rate: 7.026E-05 | global batch size: 512 | lm loss: 4.442285E+00 | loss scale: 65536.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.162 | TFLOPs: 71.12 | +[default7]: iteration 2279/ 3814 | consumed samples: 1166848 | consumed tokens: 2389704704 | elapsed time per iteration (s): 5.48 | learning rate: 7.018E-05 | global batch size: 512 | lm loss: 4.429021E+00 | loss scale: 65536.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.445 | TFLOPs: 70.58 | +[default7]: iteration 2280/ 3814 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 5.50 | learning rate: 7.010E-05 | global batch size: 512 | lm loss: 4.436137E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.106 | TFLOPs: 70.32 | +[default7]: iteration 2281/ 3814 | consumed samples: 1167872 | consumed tokens: 2391801856 | elapsed time per iteration (s): 5.48 | learning rate: 7.003E-05 | global batch size: 512 | lm loss: 4.440622E+00 | loss scale: 65536.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.441 | TFLOPs: 70.58 | +[default7]: iteration 2282/ 3814 | consumed samples: 1168384 | consumed tokens: 2392850432 | elapsed time per iteration (s): 5.45 | learning rate: 6.995E-05 | global batch size: 512 | lm loss: 4.426609E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.023 | TFLOPs: 71.02 | +[default7]: iteration 2283/ 3814 | consumed samples: 1168896 | consumed tokens: 2393899008 | elapsed time per iteration (s): 5.46 | learning rate: 6.988E-05 | global batch size: 512 | lm loss: 4.418245E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.803 | TFLOPs: 70.85 | +[default7]: iteration 2284/ 3814 | consumed samples: 1169408 | consumed tokens: 2394947584 | elapsed time per iteration (s): 5.47 | learning rate: 6.980E-05 | global batch size: 512 | lm loss: 4.437566E+00 | loss scale: 65536.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.573 | TFLOPs: 70.68 | +[default7]: iteration 2285/ 3814 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 5.47 | learning rate: 6.972E-05 | global batch size: 512 | lm loss: 4.413123E+00 | loss scale: 65536.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.558 | TFLOPs: 70.67 | +[default7]: iteration 2286/ 3814 | consumed samples: 1170432 | consumed tokens: 2397044736 | elapsed time per iteration (s): 5.46 | learning rate: 6.965E-05 | global batch size: 512 | lm loss: 4.425911E+00 | loss scale: 65536.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.787 | TFLOPs: 70.84 | +[default7]: iteration 2287/ 3814 | consumed samples: 1170944 | consumed tokens: 2398093312 | elapsed time per iteration (s): 5.45 | learning rate: 6.957E-05 | global batch size: 512 | lm loss: 4.417615E+00 | loss scale: 65536.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.955 | TFLOPs: 70.97 | +[default7]: iteration 2288/ 3814 | consumed samples: 1171456 | consumed tokens: 2399141888 | elapsed time per iteration (s): 5.45 | learning rate: 6.950E-05 | global batch size: 512 | lm loss: 4.435789E+00 | loss scale: 65536.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.861 | TFLOPs: 70.89 | +[default7]: iteration 2289/ 3814 | consumed samples: 1171968 | consumed tokens: 2400190464 | elapsed time per iteration (s): 5.46 | learning rate: 6.942E-05 | global batch size: 512 | lm loss: 4.442879E+00 | loss scale: 65536.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.842 | TFLOPs: 70.88 | +[default7]: iteration 2290/ 3814 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 5.48 | learning rate: 6.934E-05 | global batch size: 512 | lm loss: 4.450299E+00 | loss scale: 65536.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.364 | TFLOPs: 70.52 | +[default7]: iteration 2291/ 3814 | consumed samples: 1172992 | consumed tokens: 2402287616 | elapsed time per iteration (s): 5.48 | learning rate: 6.927E-05 | global batch size: 512 | lm loss: 4.414422E+00 | loss scale: 65536.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.434 | TFLOPs: 70.57 | +[default7]: iteration 2292/ 3814 | consumed samples: 1173504 | consumed tokens: 2403336192 | elapsed time per iteration (s): 5.48 | learning rate: 6.919E-05 | global batch size: 512 | lm loss: 4.435231E+00 | loss scale: 65536.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.368 | TFLOPs: 70.52 | +[default7]: iteration 2293/ 3814 | consumed samples: 1174016 | consumed tokens: 2404384768 | elapsed time per iteration (s): 5.46 | learning rate: 6.912E-05 | global batch size: 512 | lm loss: 4.435076E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.832 | TFLOPs: 70.87 | +[default7]: iteration 2294/ 3814 | consumed samples: 1174528 | consumed tokens: 2405433344 | elapsed time per iteration (s): 5.45 | learning rate: 6.904E-05 | global batch size: 512 | lm loss: 4.430775E+00 | loss scale: 65536.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.898 | TFLOPs: 70.92 | +[default7]: iteration 2295/ 3814 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 5.44 | learning rate: 6.897E-05 | global batch size: 512 | lm loss: 4.436388E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.107 | TFLOPs: 71.08 | +[default7]: iteration 2296/ 3814 | consumed samples: 1175552 | consumed tokens: 2407530496 | elapsed time per iteration (s): 5.42 | learning rate: 6.889E-05 | global batch size: 512 | lm loss: 4.426991E+00 | loss scale: 65536.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.450 | TFLOPs: 71.34 | +[default7]: iteration 2297/ 3814 | consumed samples: 1176064 | consumed tokens: 2408579072 | elapsed time per iteration (s): 5.44 | learning rate: 6.881E-05 | global batch size: 512 | lm loss: 4.388618E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.193 | TFLOPs: 71.15 | +[default7]: iteration 2298/ 3814 | consumed samples: 1176576 | consumed tokens: 2409627648 | elapsed time per iteration (s): 5.44 | learning rate: 6.874E-05 | global batch size: 512 | lm loss: 4.436992E+00 | loss scale: 65536.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 2299/ 3814 | consumed samples: 1177088 | consumed tokens: 2410676224 | elapsed time per iteration (s): 5.43 | learning rate: 6.866E-05 | global batch size: 512 | lm loss: 4.442232E+00 | loss scale: 65536.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.377 | TFLOPs: 71.28 | +[default7]: iteration 2300/ 3814 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 5.43 | learning rate: 6.859E-05 | global batch size: 512 | lm loss: 4.436619E+00 | loss scale: 65536.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.350 | TFLOPs: 71.26 | +[default7]: iteration 2301/ 3814 | consumed samples: 1178112 | consumed tokens: 2412773376 | elapsed time per iteration (s): 5.42 | learning rate: 6.851E-05 | global batch size: 512 | lm loss: 4.447064E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.414 | TFLOPs: 71.31 | +[default7]: iteration 2302/ 3814 | consumed samples: 1178624 | consumed tokens: 2413821952 | elapsed time per iteration (s): 5.45 | learning rate: 6.843E-05 | global batch size: 512 | lm loss: 4.421586E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.030 | TFLOPs: 71.02 | +[default7]: iteration 2303/ 3814 | consumed samples: 1179136 | consumed tokens: 2414870528 | elapsed time per iteration (s): 5.45 | learning rate: 6.836E-05 | global batch size: 512 | lm loss: 4.436189E+00 | loss scale: 65536.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.997 | TFLOPs: 71.00 | +[default7]: iteration 2304/ 3814 | consumed samples: 1179648 | consumed tokens: 2415919104 | elapsed time per iteration (s): 5.44 | learning rate: 6.828E-05 | global batch size: 512 | lm loss: 4.432937E+00 | loss scale: 65536.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.064 | TFLOPs: 71.05 | +[default7]: iteration 2305/ 3814 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 5.42 | learning rate: 6.821E-05 | global batch size: 512 | lm loss: 4.440015E+00 | loss scale: 65536.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.380 | TFLOPs: 71.29 | +[default7]: iteration 2306/ 3814 | consumed samples: 1180672 | consumed tokens: 2418016256 | elapsed time per iteration (s): 5.42 | learning rate: 6.813E-05 | global batch size: 512 | lm loss: 4.426295E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.475 | TFLOPs: 71.36 | +[default7]: iteration 2307/ 3814 | consumed samples: 1181184 | consumed tokens: 2419064832 | elapsed time per iteration (s): 5.42 | learning rate: 6.806E-05 | global batch size: 512 | lm loss: 4.440430E+00 | loss scale: 65536.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.498 | TFLOPs: 71.38 | +[default7]: iteration 2308/ 3814 | consumed samples: 1181696 | consumed tokens: 2420113408 | elapsed time per iteration (s): 5.43 | learning rate: 6.798E-05 | global batch size: 512 | lm loss: 4.412834E+00 | loss scale: 65536.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.270 | TFLOPs: 71.20 | +[default7]: iteration 2309/ 3814 | consumed samples: 1182208 | consumed tokens: 2421161984 | elapsed time per iteration (s): 5.43 | learning rate: 6.790E-05 | global batch size: 512 | lm loss: 4.410872E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.251 | TFLOPs: 71.19 | +[default7]: iteration 2310/ 3814 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 5.43 | learning rate: 6.783E-05 | global batch size: 512 | lm loss: 4.402090E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.351 | TFLOPs: 71.26 | +[default7]: iteration 2311/ 3814 | consumed samples: 1183232 | consumed tokens: 2423259136 | elapsed time per iteration (s): 5.42 | learning rate: 6.775E-05 | global batch size: 512 | lm loss: 4.435336E+00 | loss scale: 65536.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.528 | TFLOPs: 71.40 | +[default7]: iteration 2312/ 3814 | consumed samples: 1183744 | consumed tokens: 2424307712 | elapsed time per iteration (s): 5.42 | learning rate: 6.768E-05 | global batch size: 512 | lm loss: 4.422261E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.471 | TFLOPs: 71.35 | +[default7]: iteration 2313/ 3814 | consumed samples: 1184256 | consumed tokens: 2425356288 | elapsed time per iteration (s): 5.42 | learning rate: 6.760E-05 | global batch size: 512 | lm loss: 4.414734E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.456 | TFLOPs: 71.34 | +[default7]: iteration 2314/ 3814 | consumed samples: 1184768 | consumed tokens: 2426404864 | elapsed time per iteration (s): 5.45 | learning rate: 6.753E-05 | global batch size: 512 | lm loss: 4.405212E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.912 | TFLOPs: 70.93 | +[default7]: iteration 2315/ 3814 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 5.45 | learning rate: 6.745E-05 | global batch size: 512 | lm loss: 4.401884E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.992 | TFLOPs: 70.99 | +[default7]: iteration 2316/ 3814 | consumed samples: 1185792 | consumed tokens: 2428502016 | elapsed time per iteration (s): 5.43 | learning rate: 6.738E-05 | global batch size: 512 | lm loss: 4.387477E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.303 | TFLOPs: 71.23 | +[default7]: iteration 2317/ 3814 | consumed samples: 1186304 | consumed tokens: 2429550592 | elapsed time per iteration (s): 5.43 | learning rate: 6.730E-05 | global batch size: 512 | lm loss: 4.385784E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.333 | TFLOPs: 71.25 | +[default7]: iteration 2318/ 3814 | consumed samples: 1186816 | consumed tokens: 2430599168 | elapsed time per iteration (s): 5.44 | learning rate: 6.722E-05 | global batch size: 512 | lm loss: 4.423287E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.095 | TFLOPs: 71.07 | +[default7]: iteration 2319/ 3814 | consumed samples: 1187328 | consumed tokens: 2431647744 | elapsed time per iteration (s): 5.43 | learning rate: 6.715E-05 | global batch size: 512 | lm loss: 4.419905E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.372 | TFLOPs: 71.28 | +[default7]: iteration 2320/ 3814 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 5.42 | learning rate: 6.707E-05 | global batch size: 512 | lm loss: 4.410198E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.495 | TFLOPs: 71.37 | +[default7]: iteration 2321/ 3814 | consumed samples: 1188352 | consumed tokens: 2433744896 | elapsed time per iteration (s): 5.42 | learning rate: 6.700E-05 | global batch size: 512 | lm loss: 4.426462E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.482 | TFLOPs: 71.36 | +[default7]: iteration 2322/ 3814 | consumed samples: 1188864 | consumed tokens: 2434793472 | elapsed time per iteration (s): 5.41 | learning rate: 6.692E-05 | global batch size: 512 | lm loss: 4.405106E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.697 | TFLOPs: 71.53 | +[default7]: iteration 2323/ 3814 | consumed samples: 1189376 | consumed tokens: 2435842048 | elapsed time per iteration (s): 5.42 | learning rate: 6.685E-05 | global batch size: 512 | lm loss: 4.431170E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.521 | TFLOPs: 71.39 | +[default7]: iteration 2324/ 3814 | consumed samples: 1189888 | consumed tokens: 2436890624 | elapsed time per iteration (s): 5.41 | learning rate: 6.677E-05 | global batch size: 512 | lm loss: 4.417706E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.590 | TFLOPs: 71.44 | +[default7]: iteration 2325/ 3814 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 5.40 | learning rate: 6.670E-05 | global batch size: 512 | lm loss: 4.423425E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.768 | TFLOPs: 71.58 | +[default7]: iteration 2326/ 3814 | consumed samples: 1190912 | consumed tokens: 2438987776 | elapsed time per iteration (s): 5.41 | learning rate: 6.662E-05 | global batch size: 512 | lm loss: 4.398756E+00 | loss scale: 65536.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.669 | TFLOPs: 71.50 | +[default7]: iteration 2327/ 3814 | consumed samples: 1191424 | consumed tokens: 2440036352 | elapsed time per iteration (s): 5.43 | learning rate: 6.655E-05 | global batch size: 512 | lm loss: 4.390408E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 2328/ 3814 | consumed samples: 1191936 | consumed tokens: 2441084928 | elapsed time per iteration (s): 5.42 | learning rate: 6.647E-05 | global batch size: 512 | lm loss: 4.412524E+00 | loss scale: 65536.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.490 | TFLOPs: 71.37 | +[default7]: iteration 2329/ 3814 | consumed samples: 1192448 | consumed tokens: 2442133504 | elapsed time per iteration (s): 5.41 | learning rate: 6.639E-05 | global batch size: 512 | lm loss: 4.424618E+00 | loss scale: 65536.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.724 | TFLOPs: 71.55 | +[default7]: iteration 2330/ 3814 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 5.43 | learning rate: 6.632E-05 | global batch size: 512 | lm loss: 4.408066E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.340 | TFLOPs: 71.26 | +[default7]: iteration 2331/ 3814 | consumed samples: 1193472 | consumed tokens: 2444230656 | elapsed time per iteration (s): 5.42 | learning rate: 6.624E-05 | global batch size: 512 | lm loss: 4.394911E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.405 | TFLOPs: 71.31 | +[default7]: iteration 2332/ 3814 | consumed samples: 1193984 | consumed tokens: 2445279232 | elapsed time per iteration (s): 5.44 | learning rate: 6.617E-05 | global batch size: 512 | lm loss: 4.420221E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 2333/ 3814 | consumed samples: 1194496 | consumed tokens: 2446327808 | elapsed time per iteration (s): 5.43 | learning rate: 6.609E-05 | global batch size: 512 | lm loss: 4.403319E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 2334/ 3814 | consumed samples: 1195008 | consumed tokens: 2447376384 | elapsed time per iteration (s): 5.42 | learning rate: 6.602E-05 | global batch size: 512 | lm loss: 4.404672E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.467 | TFLOPs: 71.35 | +[default7]: iteration 2335/ 3814 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 5.41 | learning rate: 6.594E-05 | global batch size: 512 | lm loss: 4.402931E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.581 | TFLOPs: 71.44 | +[default7]: iteration 2336/ 3814 | consumed samples: 1196032 | consumed tokens: 2449473536 | elapsed time per iteration (s): 5.42 | learning rate: 6.587E-05 | global batch size: 512 | lm loss: 4.433072E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.481 | TFLOPs: 71.36 | +[default7]: iteration 2337/ 3814 | consumed samples: 1196544 | consumed tokens: 2450522112 | elapsed time per iteration (s): 5.41 | learning rate: 6.579E-05 | global batch size: 512 | lm loss: 4.415832E+00 | loss scale: 65536.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.583 | TFLOPs: 71.44 | +[default7]: iteration 2338/ 3814 | consumed samples: 1197056 | consumed tokens: 2451570688 | elapsed time per iteration (s): 5.41 | learning rate: 6.572E-05 | global batch size: 512 | lm loss: 4.396952E+00 | loss scale: 65536.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.584 | TFLOPs: 71.44 | +[default7]: iteration 2339/ 3814 | consumed samples: 1197568 | consumed tokens: 2452619264 | elapsed time per iteration (s): 5.41 | learning rate: 6.564E-05 | global batch size: 512 | lm loss: 4.400002E+00 | loss scale: 65536.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.598 | TFLOPs: 71.45 | +[default7]: iteration 2340/ 3814 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 5.42 | learning rate: 6.557E-05 | global batch size: 512 | lm loss: 4.448464E+00 | loss scale: 65536.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 2341/ 3814 | consumed samples: 1198592 | consumed tokens: 2454716416 | elapsed time per iteration (s): 5.42 | learning rate: 6.549E-05 | global batch size: 512 | lm loss: 4.414094E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.539 | TFLOPs: 71.41 | +[default7]: iteration 2342/ 3814 | consumed samples: 1199104 | consumed tokens: 2455764992 | elapsed time per iteration (s): 5.43 | learning rate: 6.542E-05 | global batch size: 512 | lm loss: 4.397080E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.351 | TFLOPs: 71.26 | +[default7]: iteration 2343/ 3814 | consumed samples: 1199616 | consumed tokens: 2456813568 | elapsed time per iteration (s): 5.41 | learning rate: 6.534E-05 | global batch size: 512 | lm loss: 4.426124E+00 | loss scale: 65536.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.610 | TFLOPs: 71.46 | +[default7]: iteration 2344/ 3814 | consumed samples: 1200128 | consumed tokens: 2457862144 | elapsed time per iteration (s): 5.42 | learning rate: 6.527E-05 | global batch size: 512 | lm loss: 4.416447E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.480 | TFLOPs: 71.36 | +[default7]: iteration 2345/ 3814 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 5.44 | learning rate: 6.519E-05 | global batch size: 512 | lm loss: 4.392009E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.176 | TFLOPs: 71.13 | +[default7]: iteration 2346/ 3814 | consumed samples: 1201152 | consumed tokens: 2459959296 | elapsed time per iteration (s): 5.42 | learning rate: 6.512E-05 | global batch size: 512 | lm loss: 4.416889E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.527 | TFLOPs: 71.40 | +[default7]: iteration 2347/ 3814 | consumed samples: 1201664 | consumed tokens: 2461007872 | elapsed time per iteration (s): 5.44 | learning rate: 6.504E-05 | global batch size: 512 | lm loss: 4.385870E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.124 | TFLOPs: 71.09 | +[default7]: iteration 2348/ 3814 | consumed samples: 1202176 | consumed tokens: 2462056448 | elapsed time per iteration (s): 5.45 | learning rate: 6.497E-05 | global batch size: 512 | lm loss: 4.409597E+00 | loss scale: 65536.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.932 | TFLOPs: 70.95 | +[default7]: iteration 2349/ 3814 | consumed samples: 1202688 | consumed tokens: 2463105024 | elapsed time per iteration (s): 5.43 | learning rate: 6.489E-05 | global batch size: 512 | lm loss: 4.400961E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 2350/ 3814 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 5.45 | learning rate: 6.481E-05 | global batch size: 512 | lm loss: 4.400161E+00 | loss scale: 65536.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.005 | TFLOPs: 71.00 | +[default7]: iteration 2351/ 3814 | consumed samples: 1203712 | consumed tokens: 2465202176 | elapsed time per iteration (s): 5.44 | learning rate: 6.474E-05 | global batch size: 512 | lm loss: 4.387984E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.126 | TFLOPs: 71.09 | +[default7]: iteration 2352/ 3814 | consumed samples: 1204224 | consumed tokens: 2466250752 | elapsed time per iteration (s): 5.43 | learning rate: 6.466E-05 | global batch size: 512 | lm loss: 4.411724E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.259 | TFLOPs: 71.19 | +[default7]: iteration 2353/ 3814 | consumed samples: 1204736 | consumed tokens: 2467299328 | elapsed time per iteration (s): 5.43 | learning rate: 6.459E-05 | global batch size: 512 | lm loss: 4.385480E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.225 | TFLOPs: 71.17 | +[default7]: iteration 2354/ 3814 | consumed samples: 1205248 | consumed tokens: 2468347904 | elapsed time per iteration (s): 5.45 | learning rate: 6.451E-05 | global batch size: 512 | lm loss: 4.381973E+00 | loss scale: 65536.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.961 | TFLOPs: 70.97 | +[default7]: iteration 2355/ 3814 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 5.44 | learning rate: 6.444E-05 | global batch size: 512 | lm loss: 4.405865E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.070 | TFLOPs: 71.05 | +[default7]: iteration 2356/ 3814 | consumed samples: 1206272 | consumed tokens: 2470445056 | elapsed time per iteration (s): 5.43 | learning rate: 6.437E-05 | global batch size: 512 | lm loss: 4.382961E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.298 | TFLOPs: 71.22 | +[default7]: iteration 2357/ 3814 | consumed samples: 1206784 | consumed tokens: 2471493632 | elapsed time per iteration (s): 5.43 | learning rate: 6.429E-05 | global batch size: 512 | lm loss: 4.414845E+00 | loss scale: 65536.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.268 | TFLOPs: 71.20 | +[default7]: iteration 2358/ 3814 | consumed samples: 1207296 | consumed tokens: 2472542208 | elapsed time per iteration (s): 5.43 | learning rate: 6.422E-05 | global batch size: 512 | lm loss: 4.417936E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.277 | TFLOPs: 71.21 | +[default7]: iteration 2359/ 3814 | consumed samples: 1207808 | consumed tokens: 2473590784 | elapsed time per iteration (s): 5.43 | learning rate: 6.414E-05 | global batch size: 512 | lm loss: 4.381775E+00 | loss scale: 65536.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.281 | TFLOPs: 71.21 | +[default7]: iteration 2360/ 3814 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 5.47 | learning rate: 6.407E-05 | global batch size: 512 | lm loss: 4.404259E+00 | loss scale: 65536.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.626 | TFLOPs: 70.72 | +[default7]: iteration 2361/ 3814 | consumed samples: 1208832 | consumed tokens: 2475687936 | elapsed time per iteration (s): 5.44 | learning rate: 6.399E-05 | global batch size: 512 | lm loss: 4.416044E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.153 | TFLOPs: 71.11 | +[default7]: iteration 2362/ 3814 | consumed samples: 1209344 | consumed tokens: 2476736512 | elapsed time per iteration (s): 5.43 | learning rate: 6.392E-05 | global batch size: 512 | lm loss: 4.406817E+00 | loss scale: 65536.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.279 | TFLOPs: 71.21 | +[default7]: iteration 2363/ 3814 | consumed samples: 1209856 | consumed tokens: 2477785088 | elapsed time per iteration (s): 5.45 | learning rate: 6.384E-05 | global batch size: 512 | lm loss: 4.426893E+00 | loss scale: 65536.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.931 | TFLOPs: 70.95 | +[default7]: iteration 2364/ 3814 | consumed samples: 1210368 | consumed tokens: 2478833664 | elapsed time per iteration (s): 5.45 | learning rate: 6.377E-05 | global batch size: 512 | lm loss: 4.413322E+00 | loss scale: 65536.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.027 | TFLOPs: 71.02 | +[default7]: iteration 2365/ 3814 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 5.45 | learning rate: 6.369E-05 | global batch size: 512 | lm loss: 4.405114E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.019 | TFLOPs: 71.01 | +[default7]: iteration 2366/ 3814 | consumed samples: 1211392 | consumed tokens: 2480930816 | elapsed time per iteration (s): 5.45 | learning rate: 6.362E-05 | global batch size: 512 | lm loss: 4.415636E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.932 | TFLOPs: 70.95 | +[default7]: iteration 2367/ 3814 | consumed samples: 1211904 | consumed tokens: 2481979392 | elapsed time per iteration (s): 5.45 | learning rate: 6.354E-05 | global batch size: 512 | lm loss: 4.413763E+00 | loss scale: 65536.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.869 | TFLOPs: 70.90 | +[default7]: iteration 2368/ 3814 | consumed samples: 1212416 | consumed tokens: 2483027968 | elapsed time per iteration (s): 5.44 | learning rate: 6.347E-05 | global batch size: 512 | lm loss: 4.391559E+00 | loss scale: 65536.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.114 | TFLOPs: 71.09 | +[default7]: iteration 2369/ 3814 | consumed samples: 1212928 | consumed tokens: 2484076544 | elapsed time per iteration (s): 5.44 | learning rate: 6.339E-05 | global batch size: 512 | lm loss: 4.375243E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 2370/ 3814 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 5.43 | learning rate: 6.332E-05 | global batch size: 512 | lm loss: 4.395556E+00 | loss scale: 65536.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.302 | TFLOPs: 71.23 | +[default7]: iteration 2371/ 3814 | consumed samples: 1213952 | consumed tokens: 2486173696 | elapsed time per iteration (s): 5.45 | learning rate: 6.324E-05 | global batch size: 512 | lm loss: 4.390180E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.875 | TFLOPs: 70.90 | +[default7]: iteration 2372/ 3814 | consumed samples: 1214464 | consumed tokens: 2487222272 | elapsed time per iteration (s): 5.44 | learning rate: 6.317E-05 | global batch size: 512 | lm loss: 4.412543E+00 | loss scale: 65536.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.191 | TFLOPs: 71.14 | +[default7]: iteration 2373/ 3814 | consumed samples: 1214976 | consumed tokens: 2488270848 | elapsed time per iteration (s): 5.44 | learning rate: 6.309E-05 | global batch size: 512 | lm loss: 4.434603E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.050 | TFLOPs: 71.04 | +[default7]: iteration 2374/ 3814 | consumed samples: 1215488 | consumed tokens: 2489319424 | elapsed time per iteration (s): 5.42 | learning rate: 6.302E-05 | global batch size: 512 | lm loss: 4.408839E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.444 | TFLOPs: 71.33 | +[default7]: iteration 2375/ 3814 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 5.43 | learning rate: 6.294E-05 | global batch size: 512 | lm loss: 4.397501E+00 | loss scale: 65536.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.339 | TFLOPs: 71.26 | +[default7]: iteration 2376/ 3814 | consumed samples: 1216512 | consumed tokens: 2491416576 | elapsed time per iteration (s): 5.43 | learning rate: 6.287E-05 | global batch size: 512 | lm loss: 4.389263E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.289 | TFLOPs: 71.22 | +[default7]: iteration 2377/ 3814 | consumed samples: 1217024 | consumed tokens: 2492465152 | elapsed time per iteration (s): 5.47 | learning rate: 6.280E-05 | global batch size: 512 | lm loss: 4.406111E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.652 | TFLOPs: 70.74 | +[default7]: iteration 2378/ 3814 | consumed samples: 1217536 | consumed tokens: 2493513728 | elapsed time per iteration (s): 5.45 | learning rate: 6.272E-05 | global batch size: 512 | lm loss: 4.377131E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.892 | TFLOPs: 70.92 | +[default7]: iteration 2379/ 3814 | consumed samples: 1218048 | consumed tokens: 2494562304 | elapsed time per iteration (s): 5.47 | learning rate: 6.265E-05 | global batch size: 512 | lm loss: 4.397145E+00 | loss scale: 65536.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.646 | TFLOPs: 70.73 | +[default7]: iteration 2380/ 3814 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 5.44 | learning rate: 6.257E-05 | global batch size: 512 | lm loss: 4.401872E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.069 | TFLOPs: 71.05 | +[default7]: iteration 2381/ 3814 | consumed samples: 1219072 | consumed tokens: 2496659456 | elapsed time per iteration (s): 5.46 | learning rate: 6.250E-05 | global batch size: 512 | lm loss: 4.404151E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.735 | TFLOPs: 70.80 | +[default7]: iteration 2382/ 3814 | consumed samples: 1219584 | consumed tokens: 2497708032 | elapsed time per iteration (s): 5.44 | learning rate: 6.242E-05 | global batch size: 512 | lm loss: 4.398123E+00 | loss scale: 65536.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 2383/ 3814 | consumed samples: 1220096 | consumed tokens: 2498756608 | elapsed time per iteration (s): 5.45 | learning rate: 6.235E-05 | global batch size: 512 | lm loss: 4.378440E+00 | loss scale: 65536.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.006 | TFLOPs: 71.00 | +[default7]: iteration 2384/ 3814 | consumed samples: 1220608 | consumed tokens: 2499805184 | elapsed time per iteration (s): 5.45 | learning rate: 6.227E-05 | global batch size: 512 | lm loss: 4.388189E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.028 | TFLOPs: 71.02 | +[default7]: iteration 2385/ 3814 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 5.46 | learning rate: 6.220E-05 | global batch size: 512 | lm loss: 4.394578E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.827 | TFLOPs: 70.87 | +[default7]: iteration 2386/ 3814 | consumed samples: 1221632 | consumed tokens: 2501902336 | elapsed time per iteration (s): 5.45 | learning rate: 6.213E-05 | global batch size: 512 | lm loss: 4.369350E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 2387/ 3814 | consumed samples: 1222144 | consumed tokens: 2502950912 | elapsed time per iteration (s): 5.45 | learning rate: 6.205E-05 | global batch size: 512 | lm loss: 4.397634E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.881 | TFLOPs: 70.91 | +[default7]: iteration 2388/ 3814 | consumed samples: 1222656 | consumed tokens: 2503999488 | elapsed time per iteration (s): 5.46 | learning rate: 6.198E-05 | global batch size: 512 | lm loss: 4.408592E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.786 | TFLOPs: 70.84 | +[default7]: iteration 2389/ 3814 | consumed samples: 1223168 | consumed tokens: 2505048064 | elapsed time per iteration (s): 5.46 | learning rate: 6.190E-05 | global batch size: 512 | lm loss: 4.413433E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.721 | TFLOPs: 70.79 | +[default7]: iteration 2390/ 3814 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 5.44 | learning rate: 6.183E-05 | global batch size: 512 | lm loss: 4.410100E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 2391/ 3814 | consumed samples: 1224192 | consumed tokens: 2507145216 | elapsed time per iteration (s): 5.43 | learning rate: 6.175E-05 | global batch size: 512 | lm loss: 4.401358E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.264 | TFLOPs: 71.20 | +[default7]: iteration 2392/ 3814 | consumed samples: 1224704 | consumed tokens: 2508193792 | elapsed time per iteration (s): 5.46 | learning rate: 6.168E-05 | global batch size: 512 | lm loss: 4.395029E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.758 | TFLOPs: 70.82 | +[default7]: iteration 2393/ 3814 | consumed samples: 1225216 | consumed tokens: 2509242368 | elapsed time per iteration (s): 5.44 | learning rate: 6.160E-05 | global batch size: 512 | lm loss: 4.372561E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.114 | TFLOPs: 71.09 | +[default7]: iteration 2394/ 3814 | consumed samples: 1225728 | consumed tokens: 2510290944 | elapsed time per iteration (s): 5.45 | learning rate: 6.153E-05 | global batch size: 512 | lm loss: 4.395027E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.004 | TFLOPs: 71.00 | +[default7]: iteration 2395/ 3814 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 5.45 | learning rate: 6.146E-05 | global batch size: 512 | lm loss: 4.377159E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.001 | TFLOPs: 71.00 | +[default7]: iteration 2396/ 3814 | consumed samples: 1226752 | consumed tokens: 2512388096 | elapsed time per iteration (s): 5.46 | learning rate: 6.138E-05 | global batch size: 512 | lm loss: 4.433140E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.806 | TFLOPs: 70.85 | +[default7]: iteration 2397/ 3814 | consumed samples: 1227264 | consumed tokens: 2513436672 | elapsed time per iteration (s): 5.45 | learning rate: 6.131E-05 | global batch size: 512 | lm loss: 4.394764E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 2398/ 3814 | consumed samples: 1227776 | consumed tokens: 2514485248 | elapsed time per iteration (s): 5.45 | learning rate: 6.123E-05 | global batch size: 512 | lm loss: 4.389671E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.895 | TFLOPs: 70.92 | +[default7]: iteration 2399/ 3814 | consumed samples: 1228288 | consumed tokens: 2515533824 | elapsed time per iteration (s): 5.46 | learning rate: 6.116E-05 | global batch size: 512 | lm loss: 4.395956E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.806 | TFLOPs: 70.85 | +[default7]: iteration 2400/ 3814 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 5.45 | learning rate: 6.109E-05 | global batch size: 512 | lm loss: 4.379807E+00 | loss scale: 65536.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.889 | TFLOPs: 70.92 | +[default7]: iteration 2401/ 3814 | consumed samples: 1229312 | consumed tokens: 2517630976 | elapsed time per iteration (s): 5.43 | learning rate: 6.101E-05 | global batch size: 512 | lm loss: 4.393792E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.222 | TFLOPs: 71.17 | +[default7]: iteration 2402/ 3814 | consumed samples: 1229824 | consumed tokens: 2518679552 | elapsed time per iteration (s): 5.46 | learning rate: 6.094E-05 | global batch size: 512 | lm loss: 4.400998E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.845 | TFLOPs: 70.88 | +[default7]: iteration 2403/ 3814 | consumed samples: 1230336 | consumed tokens: 2519728128 | elapsed time per iteration (s): 5.43 | learning rate: 6.086E-05 | global batch size: 512 | lm loss: 4.400741E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 2404/ 3814 | consumed samples: 1230848 | consumed tokens: 2520776704 | elapsed time per iteration (s): 5.44 | learning rate: 6.079E-05 | global batch size: 512 | lm loss: 4.389729E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.148 | TFLOPs: 71.11 | +[default7]: iteration 2405/ 3814 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 5.46 | learning rate: 6.072E-05 | global batch size: 512 | lm loss: 4.384816E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.832 | TFLOPs: 70.87 | +[default7]: iteration 2406/ 3814 | consumed samples: 1231872 | consumed tokens: 2522873856 | elapsed time per iteration (s): 5.45 | learning rate: 6.064E-05 | global batch size: 512 | lm loss: 4.374277E+00 | loss scale: 65536.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.895 | TFLOPs: 70.92 | +[default7]: iteration 2407/ 3814 | consumed samples: 1232384 | consumed tokens: 2523922432 | elapsed time per iteration (s): 5.46 | learning rate: 6.057E-05 | global batch size: 512 | lm loss: 4.381961E+00 | loss scale: 65536.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.845 | TFLOPs: 70.88 | +[default7]: iteration 2408/ 3814 | consumed samples: 1232896 | consumed tokens: 2524971008 | elapsed time per iteration (s): 5.45 | learning rate: 6.049E-05 | global batch size: 512 | lm loss: 4.374673E+00 | loss scale: 65536.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.028 | TFLOPs: 71.02 | +[default7]: iteration 2409/ 3814 | consumed samples: 1233408 | consumed tokens: 2526019584 | elapsed time per iteration (s): 5.46 | learning rate: 6.042E-05 | global batch size: 512 | lm loss: 4.366673E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.801 | TFLOPs: 70.85 | +[default7]: iteration 2410/ 3814 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 5.46 | learning rate: 6.035E-05 | global batch size: 512 | lm loss: 4.367687E+00 | loss scale: 65536.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.836 | TFLOPs: 70.88 | +[default7]: iteration 2411/ 3814 | consumed samples: 1234432 | consumed tokens: 2528116736 | elapsed time per iteration (s): 5.48 | learning rate: 6.027E-05 | global batch size: 512 | lm loss: 4.405081E+00 | loss scale: 65536.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.378 | TFLOPs: 70.53 | +[default7]: iteration 2412/ 3814 | consumed samples: 1234944 | consumed tokens: 2529165312 | elapsed time per iteration (s): 5.46 | learning rate: 6.020E-05 | global batch size: 512 | lm loss: 4.373200E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.690 | TFLOPs: 70.77 | +[default7]: iteration 2413/ 3814 | consumed samples: 1235456 | consumed tokens: 2530213888 | elapsed time per iteration (s): 5.48 | learning rate: 6.012E-05 | global batch size: 512 | lm loss: 4.384049E+00 | loss scale: 65536.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.483 | TFLOPs: 70.61 | +[default7]: iteration 2414/ 3814 | consumed samples: 1235968 | consumed tokens: 2531262464 | elapsed time per iteration (s): 5.46 | learning rate: 6.005E-05 | global batch size: 512 | lm loss: 4.399224E+00 | loss scale: 65536.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.716 | TFLOPs: 70.78 | +[default7]: iteration 2415/ 3814 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 5.46 | learning rate: 5.998E-05 | global batch size: 512 | lm loss: 4.397635E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.791 | TFLOPs: 70.84 | +[default7]: iteration 2416/ 3814 | consumed samples: 1236992 | consumed tokens: 2533359616 | elapsed time per iteration (s): 5.46 | learning rate: 5.990E-05 | global batch size: 512 | lm loss: 4.379107E+00 | loss scale: 65536.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 2417/ 3814 | consumed samples: 1237504 | consumed tokens: 2534408192 | elapsed time per iteration (s): 5.47 | learning rate: 5.983E-05 | global batch size: 512 | lm loss: 4.409456E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.535 | TFLOPs: 70.65 | +[default7]: iteration 2418/ 3814 | consumed samples: 1238016 | consumed tokens: 2535456768 | elapsed time per iteration (s): 5.50 | learning rate: 5.975E-05 | global batch size: 512 | lm loss: 4.368721E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.136 | TFLOPs: 70.35 | +[default7]: iteration 2419/ 3814 | consumed samples: 1238528 | consumed tokens: 2536505344 | elapsed time per iteration (s): 5.49 | learning rate: 5.968E-05 | global batch size: 512 | lm loss: 4.361211E+00 | loss scale: 65536.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.316 | TFLOPs: 70.48 | +[default7]: iteration 2420/ 3814 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 5.47 | learning rate: 5.961E-05 | global batch size: 512 | lm loss: 4.381299E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.662 | TFLOPs: 70.74 | +[default7]: iteration 2421/ 3814 | consumed samples: 1239552 | consumed tokens: 2538602496 | elapsed time per iteration (s): 5.46 | learning rate: 5.953E-05 | global batch size: 512 | lm loss: 4.361976E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.831 | TFLOPs: 70.87 | +[default7]: iteration 2422/ 3814 | consumed samples: 1240064 | consumed tokens: 2539651072 | elapsed time per iteration (s): 5.47 | learning rate: 5.946E-05 | global batch size: 512 | lm loss: 4.384013E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.622 | TFLOPs: 70.71 | +[default7]: iteration 2423/ 3814 | consumed samples: 1240576 | consumed tokens: 2540699648 | elapsed time per iteration (s): 5.48 | learning rate: 5.939E-05 | global batch size: 512 | lm loss: 4.370985E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.455 | TFLOPs: 70.59 | +[default7]: iteration 2424/ 3814 | consumed samples: 1241088 | consumed tokens: 2541748224 | elapsed time per iteration (s): 5.46 | learning rate: 5.931E-05 | global batch size: 512 | lm loss: 4.369524E+00 | loss scale: 65536.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.714 | TFLOPs: 70.78 | +[default7]: iteration 2425/ 3814 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 5.47 | learning rate: 5.924E-05 | global batch size: 512 | lm loss: 4.377018E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.683 | TFLOPs: 70.76 | +[default7]: iteration 2426/ 3814 | consumed samples: 1242112 | consumed tokens: 2543845376 | elapsed time per iteration (s): 5.48 | learning rate: 5.917E-05 | global batch size: 512 | lm loss: 4.378062E+00 | loss scale: 65536.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.474 | TFLOPs: 70.60 | +[default7]: iteration 2427/ 3814 | consumed samples: 1242624 | consumed tokens: 2544893952 | elapsed time per iteration (s): 5.48 | learning rate: 5.909E-05 | global batch size: 512 | lm loss: 4.372139E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.384 | TFLOPs: 70.53 | +[default7]: iteration 2428/ 3814 | consumed samples: 1243136 | consumed tokens: 2545942528 | elapsed time per iteration (s): 5.48 | learning rate: 5.902E-05 | global batch size: 512 | lm loss: 4.383878E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.501 | TFLOPs: 70.62 | +[default7]: iteration 2429/ 3814 | consumed samples: 1243648 | consumed tokens: 2546991104 | elapsed time per iteration (s): 5.45 | learning rate: 5.894E-05 | global batch size: 512 | lm loss: 4.382334E+00 | loss scale: 65536.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.905 | TFLOPs: 70.93 | +[default7]: iteration 2430/ 3814 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 5.44 | learning rate: 5.887E-05 | global batch size: 512 | lm loss: 4.345153E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 2431/ 3814 | consumed samples: 1244672 | consumed tokens: 2549088256 | elapsed time per iteration (s): 5.48 | learning rate: 5.880E-05 | global batch size: 512 | lm loss: 4.382175E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.515 | TFLOPs: 70.63 | +[default7]: iteration 2432/ 3814 | consumed samples: 1245184 | consumed tokens: 2550136832 | elapsed time per iteration (s): 5.45 | learning rate: 5.872E-05 | global batch size: 512 | lm loss: 4.390405E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.948 | TFLOPs: 70.96 | +[default7]: iteration 2433/ 3814 | consumed samples: 1245696 | consumed tokens: 2551185408 | elapsed time per iteration (s): 5.44 | learning rate: 5.865E-05 | global batch size: 512 | lm loss: 4.369647E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.182 | TFLOPs: 71.14 | +[default7]: iteration 2434/ 3814 | consumed samples: 1246208 | consumed tokens: 2552233984 | elapsed time per iteration (s): 5.44 | learning rate: 5.858E-05 | global batch size: 512 | lm loss: 4.373761E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.036 | TFLOPs: 71.03 | +[default7]: iteration 2435/ 3814 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 5.45 | learning rate: 5.850E-05 | global batch size: 512 | lm loss: 4.383073E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.898 | TFLOPs: 70.92 | +[default7]: iteration 2436/ 3814 | consumed samples: 1247232 | consumed tokens: 2554331136 | elapsed time per iteration (s): 5.47 | learning rate: 5.843E-05 | global batch size: 512 | lm loss: 4.384555E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.677 | TFLOPs: 70.76 | +[default7]: iteration 2437/ 3814 | consumed samples: 1247744 | consumed tokens: 2555379712 | elapsed time per iteration (s): 5.45 | learning rate: 5.836E-05 | global batch size: 512 | lm loss: 4.373347E+00 | loss scale: 65536.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 2438/ 3814 | consumed samples: 1248256 | consumed tokens: 2556428288 | elapsed time per iteration (s): 5.47 | learning rate: 5.828E-05 | global batch size: 512 | lm loss: 4.382707E+00 | loss scale: 65536.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.606 | TFLOPs: 70.70 | +[default7]: iteration 2439/ 3814 | consumed samples: 1248768 | consumed tokens: 2557476864 | elapsed time per iteration (s): 5.47 | learning rate: 5.821E-05 | global batch size: 512 | lm loss: 4.383512E+00 | loss scale: 65536.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.673 | TFLOPs: 70.75 | +[default7]: iteration 2440/ 3814 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 5.46 | learning rate: 5.814E-05 | global batch size: 512 | lm loss: 4.344664E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.709 | TFLOPs: 70.78 | +[default7]: iteration 2441/ 3814 | consumed samples: 1249792 | consumed tokens: 2559574016 | elapsed time per iteration (s): 5.47 | learning rate: 5.806E-05 | global batch size: 512 | lm loss: 4.377522E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.605 | TFLOPs: 70.70 | +[default7]: iteration 2442/ 3814 | consumed samples: 1250304 | consumed tokens: 2560622592 | elapsed time per iteration (s): 5.46 | learning rate: 5.799E-05 | global batch size: 512 | lm loss: 4.365440E+00 | loss scale: 65536.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.808 | TFLOPs: 70.85 | +[default7]: iteration 2443/ 3814 | consumed samples: 1250816 | consumed tokens: 2561671168 | elapsed time per iteration (s): 5.47 | learning rate: 5.792E-05 | global batch size: 512 | lm loss: 4.387230E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.678 | TFLOPs: 70.76 | +[default7]: iteration 2444/ 3814 | consumed samples: 1251328 | consumed tokens: 2562719744 | elapsed time per iteration (s): 5.47 | learning rate: 5.784E-05 | global batch size: 512 | lm loss: 4.345769E+00 | loss scale: 65536.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.579 | TFLOPs: 70.68 | +[default7]: iteration 2445/ 3814 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 5.47 | learning rate: 5.777E-05 | global batch size: 512 | lm loss: 4.377368E+00 | loss scale: 65536.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.606 | TFLOPs: 70.70 | +[default7]: iteration 2446/ 3814 | consumed samples: 1252352 | consumed tokens: 2564816896 | elapsed time per iteration (s): 5.46 | learning rate: 5.770E-05 | global batch size: 512 | lm loss: 4.373597E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.761 | TFLOPs: 70.82 | +[default7]: iteration 2447/ 3814 | consumed samples: 1252864 | consumed tokens: 2565865472 | elapsed time per iteration (s): 5.45 | learning rate: 5.762E-05 | global batch size: 512 | lm loss: 4.344882E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.874 | TFLOPs: 70.90 | +[default7]: iteration 2448/ 3814 | consumed samples: 1253376 | consumed tokens: 2566914048 | elapsed time per iteration (s): 5.46 | learning rate: 5.755E-05 | global batch size: 512 | lm loss: 4.382827E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.720 | TFLOPs: 70.79 | +[default7]: iteration 2449/ 3814 | consumed samples: 1253888 | consumed tokens: 2567962624 | elapsed time per iteration (s): 5.48 | learning rate: 5.748E-05 | global batch size: 512 | lm loss: 4.372172E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.476 | TFLOPs: 70.60 | +[default7]: iteration 2450/ 3814 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 5.48 | learning rate: 5.741E-05 | global batch size: 512 | lm loss: 4.374059E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.472 | TFLOPs: 70.60 | +[default7]: iteration 2451/ 3814 | consumed samples: 1254912 | consumed tokens: 2570059776 | elapsed time per iteration (s): 5.46 | learning rate: 5.733E-05 | global batch size: 512 | lm loss: 4.344956E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.753 | TFLOPs: 70.81 | +[default7]: iteration 2452/ 3814 | consumed samples: 1255424 | consumed tokens: 2571108352 | elapsed time per iteration (s): 5.46 | learning rate: 5.726E-05 | global batch size: 512 | lm loss: 4.387355E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.705 | TFLOPs: 70.78 | +[default7]: iteration 2453/ 3814 | consumed samples: 1255936 | consumed tokens: 2572156928 | elapsed time per iteration (s): 5.45 | learning rate: 5.719E-05 | global batch size: 512 | lm loss: 4.390632E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.008 | TFLOPs: 71.00 | +[default7]: iteration 2454/ 3814 | consumed samples: 1256448 | consumed tokens: 2573205504 | elapsed time per iteration (s): 5.47 | learning rate: 5.711E-05 | global batch size: 512 | lm loss: 4.380019E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.623 | TFLOPs: 70.71 | +[default7]: iteration 2455/ 3814 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 5.47 | learning rate: 5.704E-05 | global batch size: 512 | lm loss: 4.400203E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.674 | TFLOPs: 70.75 | +[default7]: iteration 2456/ 3814 | consumed samples: 1257472 | consumed tokens: 2575302656 | elapsed time per iteration (s): 5.45 | learning rate: 5.697E-05 | global batch size: 512 | lm loss: 4.368955E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.912 | TFLOPs: 70.93 | +[default7]: iteration 2457/ 3814 | consumed samples: 1257984 | consumed tokens: 2576351232 | elapsed time per iteration (s): 5.45 | learning rate: 5.689E-05 | global batch size: 512 | lm loss: 4.392937E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 2458/ 3814 | consumed samples: 1258496 | consumed tokens: 2577399808 | elapsed time per iteration (s): 5.47 | learning rate: 5.682E-05 | global batch size: 512 | lm loss: 4.352684E+00 | loss scale: 65536.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.682 | TFLOPs: 70.76 | +[default7]: iteration 2459/ 3814 | consumed samples: 1259008 | consumed tokens: 2578448384 | elapsed time per iteration (s): 5.45 | learning rate: 5.675E-05 | global batch size: 512 | lm loss: 4.374725E+00 | loss scale: 65536.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.025 | TFLOPs: 71.02 | +[default7]: iteration 2460/ 3814 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 5.45 | learning rate: 5.668E-05 | global batch size: 512 | lm loss: 4.354004E+00 | loss scale: 65536.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.994 | TFLOPs: 70.99 | +[default7]: iteration 2461/ 3814 | consumed samples: 1260032 | consumed tokens: 2580545536 | elapsed time per iteration (s): 5.46 | learning rate: 5.660E-05 | global batch size: 512 | lm loss: 4.370974E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.720 | TFLOPs: 70.79 | +[default7]: iteration 2462/ 3814 | consumed samples: 1260544 | consumed tokens: 2581594112 | elapsed time per iteration (s): 5.47 | learning rate: 5.653E-05 | global batch size: 512 | lm loss: 4.373721E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.592 | TFLOPs: 70.69 | +[default7]: iteration 2463/ 3814 | consumed samples: 1261056 | consumed tokens: 2582642688 | elapsed time per iteration (s): 5.44 | learning rate: 5.646E-05 | global batch size: 512 | lm loss: 4.359496E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 2464/ 3814 | consumed samples: 1261568 | consumed tokens: 2583691264 | elapsed time per iteration (s): 5.46 | learning rate: 5.638E-05 | global batch size: 512 | lm loss: 4.370336E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.698 | TFLOPs: 70.77 | +[default7]: iteration 2465/ 3814 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 5.49 | learning rate: 5.631E-05 | global batch size: 512 | lm loss: 4.387849E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.338 | TFLOPs: 70.50 | +[default7]: iteration 2466/ 3814 | consumed samples: 1262592 | consumed tokens: 2585788416 | elapsed time per iteration (s): 5.49 | learning rate: 5.624E-05 | global batch size: 512 | lm loss: 4.366631E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.340 | TFLOPs: 70.50 | +[default7]: iteration 2467/ 3814 | consumed samples: 1263104 | consumed tokens: 2586836992 | elapsed time per iteration (s): 5.49 | learning rate: 5.617E-05 | global batch size: 512 | lm loss: 4.360034E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.319 | TFLOPs: 70.49 | +[default7]: iteration 2468/ 3814 | consumed samples: 1263616 | consumed tokens: 2587885568 | elapsed time per iteration (s): 5.48 | learning rate: 5.609E-05 | global batch size: 512 | lm loss: 4.367626E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.368 | TFLOPs: 70.52 | +[default7]: iteration 2469/ 3814 | consumed samples: 1264128 | consumed tokens: 2588934144 | elapsed time per iteration (s): 5.47 | learning rate: 5.602E-05 | global batch size: 512 | lm loss: 4.362346E+00 | loss scale: 65536.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.677 | TFLOPs: 70.76 | +[default7]: iteration 2470/ 3814 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 5.47 | learning rate: 5.595E-05 | global batch size: 512 | lm loss: 4.399450E+00 | loss scale: 65536.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.686 | TFLOPs: 70.76 | +[default7]: iteration 2471/ 3814 | consumed samples: 1265152 | consumed tokens: 2591031296 | elapsed time per iteration (s): 5.48 | learning rate: 5.588E-05 | global batch size: 512 | lm loss: 4.369140E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.502 | TFLOPs: 70.62 | +[default7]: iteration 2472/ 3814 | consumed samples: 1265664 | consumed tokens: 2592079872 | elapsed time per iteration (s): 5.45 | learning rate: 5.580E-05 | global batch size: 512 | lm loss: 4.376030E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 2473/ 3814 | consumed samples: 1266176 | consumed tokens: 2593128448 | elapsed time per iteration (s): 5.46 | learning rate: 5.573E-05 | global batch size: 512 | lm loss: 4.360450E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.776 | TFLOPs: 70.83 | +[default7]: iteration 2474/ 3814 | consumed samples: 1266688 | consumed tokens: 2594177024 | elapsed time per iteration (s): 5.45 | learning rate: 5.566E-05 | global batch size: 512 | lm loss: 4.351602E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.889 | TFLOPs: 70.92 | +[default7]: iteration 2475/ 3814 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 5.47 | learning rate: 5.559E-05 | global batch size: 512 | lm loss: 4.362988E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.660 | TFLOPs: 70.74 | +[default7]: iteration 2476/ 3814 | consumed samples: 1267712 | consumed tokens: 2596274176 | elapsed time per iteration (s): 5.46 | learning rate: 5.551E-05 | global batch size: 512 | lm loss: 4.364606E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.812 | TFLOPs: 70.86 | +[default7]: iteration 2477/ 3814 | consumed samples: 1268224 | consumed tokens: 2597322752 | elapsed time per iteration (s): 5.47 | learning rate: 5.544E-05 | global batch size: 512 | lm loss: 4.373061E+00 | loss scale: 65536.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.643 | TFLOPs: 70.73 | +[default7]: iteration 2478/ 3814 | consumed samples: 1268736 | consumed tokens: 2598371328 | elapsed time per iteration (s): 5.45 | learning rate: 5.537E-05 | global batch size: 512 | lm loss: 4.370859E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.007 | TFLOPs: 71.00 | +[default7]: iteration 2479/ 3814 | consumed samples: 1269248 | consumed tokens: 2599419904 | elapsed time per iteration (s): 5.46 | learning rate: 5.530E-05 | global batch size: 512 | lm loss: 4.365326E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.709 | TFLOPs: 70.78 | +[default7]: iteration 2480/ 3814 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 5.47 | learning rate: 5.522E-05 | global batch size: 512 | lm loss: 4.368435E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.668 | TFLOPs: 70.75 | +[default7]: iteration 2481/ 3814 | consumed samples: 1270272 | consumed tokens: 2601517056 | elapsed time per iteration (s): 5.45 | learning rate: 5.515E-05 | global batch size: 512 | lm loss: 4.346859E+00 | loss scale: 65536.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.921 | TFLOPs: 70.94 | +[default7]: iteration 2482/ 3814 | consumed samples: 1270784 | consumed tokens: 2602565632 | elapsed time per iteration (s): 5.45 | learning rate: 5.508E-05 | global batch size: 512 | lm loss: 4.329252E+00 | loss scale: 65536.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.980 | TFLOPs: 70.98 | +[default7]: iteration 2483/ 3814 | consumed samples: 1271296 | consumed tokens: 2603614208 | elapsed time per iteration (s): 5.44 | learning rate: 5.501E-05 | global batch size: 512 | lm loss: 4.367475E+00 | loss scale: 65536.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.203 | TFLOPs: 71.15 | +[default7]: iteration 2484/ 3814 | consumed samples: 1271808 | consumed tokens: 2604662784 | elapsed time per iteration (s): 5.45 | learning rate: 5.493E-05 | global batch size: 512 | lm loss: 4.377689E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.962 | TFLOPs: 70.97 | +[default7]: iteration 2485/ 3814 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 5.44 | learning rate: 5.486E-05 | global batch size: 512 | lm loss: 4.359710E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.159 | TFLOPs: 71.12 | +[default7]: iteration 2486/ 3814 | consumed samples: 1272832 | consumed tokens: 2606759936 | elapsed time per iteration (s): 5.45 | learning rate: 5.479E-05 | global batch size: 512 | lm loss: 4.357003E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.862 | TFLOPs: 70.89 | +[default7]: iteration 2487/ 3814 | consumed samples: 1273344 | consumed tokens: 2607808512 | elapsed time per iteration (s): 5.46 | learning rate: 5.472E-05 | global batch size: 512 | lm loss: 4.352922E+00 | loss scale: 65536.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.835 | TFLOPs: 70.87 | +[default7]: iteration 2488/ 3814 | consumed samples: 1273856 | consumed tokens: 2608857088 | elapsed time per iteration (s): 5.45 | learning rate: 5.465E-05 | global batch size: 512 | lm loss: 4.363176E+00 | loss scale: 65536.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.868 | TFLOPs: 70.90 | +[default7]: iteration 2489/ 3814 | consumed samples: 1274368 | consumed tokens: 2609905664 | elapsed time per iteration (s): 5.46 | learning rate: 5.457E-05 | global batch size: 512 | lm loss: 4.348749E+00 | loss scale: 65536.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.788 | TFLOPs: 70.84 | +[default7]: iteration 2490/ 3814 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 5.45 | learning rate: 5.450E-05 | global batch size: 512 | lm loss: 4.370903E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.903 | TFLOPs: 70.93 | +[default7]: iteration 2491/ 3814 | consumed samples: 1275392 | consumed tokens: 2612002816 | elapsed time per iteration (s): 5.46 | learning rate: 5.443E-05 | global batch size: 512 | lm loss: 4.327559E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.813 | TFLOPs: 70.86 | +[default7]: iteration 2492/ 3814 | consumed samples: 1275904 | consumed tokens: 2613051392 | elapsed time per iteration (s): 5.44 | learning rate: 5.436E-05 | global batch size: 512 | lm loss: 4.366795E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.176 | TFLOPs: 71.13 | +[default7]: iteration 2493/ 3814 | consumed samples: 1276416 | consumed tokens: 2614099968 | elapsed time per iteration (s): 5.44 | learning rate: 5.429E-05 | global batch size: 512 | lm loss: 4.392258E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.06 | +[default7]: iteration 2494/ 3814 | consumed samples: 1276928 | consumed tokens: 2615148544 | elapsed time per iteration (s): 5.45 | learning rate: 5.421E-05 | global batch size: 512 | lm loss: 4.367138E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 2495/ 3814 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 5.46 | learning rate: 5.414E-05 | global batch size: 512 | lm loss: 4.377059E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.775 | TFLOPs: 70.83 | +[default7]: iteration 2496/ 3814 | consumed samples: 1277952 | consumed tokens: 2617245696 | elapsed time per iteration (s): 5.46 | learning rate: 5.407E-05 | global batch size: 512 | lm loss: 4.370331E+00 | loss scale: 65536.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.762 | TFLOPs: 70.82 | +[default7]: iteration 2497/ 3814 | consumed samples: 1278464 | consumed tokens: 2618294272 | elapsed time per iteration (s): 5.45 | learning rate: 5.400E-05 | global batch size: 512 | lm loss: 4.354804E+00 | loss scale: 65536.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.880 | TFLOPs: 70.91 | +[default7]: iteration 2498/ 3814 | consumed samples: 1278976 | consumed tokens: 2619342848 | elapsed time per iteration (s): 5.44 | learning rate: 5.393E-05 | global batch size: 512 | lm loss: 4.364949E+00 | loss scale: 65536.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.042 | TFLOPs: 71.03 | +[default7]: iteration 2499/ 3814 | consumed samples: 1279488 | consumed tokens: 2620391424 | elapsed time per iteration (s): 5.46 | learning rate: 5.385E-05 | global batch size: 512 | lm loss: 4.357806E+00 | loss scale: 65536.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.844 | TFLOPs: 70.88 | +[default7]: iteration 2500/ 3814 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 5.45 | learning rate: 5.378E-05 | global batch size: 512 | lm loss: 4.351935E+00 | loss scale: 131072.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.939 | TFLOPs: 70.95 | +[default1]:[2023-02-16 15:06:57,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 2500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 15:06:57,984] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2500 is begin to save! +[default0]:[2023-02-16 15:06:57,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,164] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,171] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,225] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,276] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,279] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,331] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,437] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,596] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,656] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,651] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,705] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,766] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,819] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:58,920] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:58,928] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:58,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:58,974] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,026] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:58,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:58,981] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,080] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,135] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,240] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,248] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,295] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,303] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,356] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,401] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,409] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,409] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,506] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,566] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,736] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,674] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 15:06:59,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,791] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,845] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 15:06:59,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_00-model_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:06:59,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:06:59,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,905] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 15:06:59,906] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 15:06:59,907] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 15:06:59,907] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 15:06:59,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:06:59,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:06:59,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 15:06:59,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 15:06:59,891] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 15:06:59,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 15:06:59,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:06:59,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:06:59,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:06:59,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:07:00,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,397] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,433] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,440] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,440] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,419] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,466] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,465] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,506] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,477] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,467] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,497] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,507] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,571] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,517] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,596] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,557] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,550] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,518] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,580] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,523] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,529] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,520] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,521] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,593] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,579] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,537] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,622] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,612] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,592] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,559] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,592] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,619] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,627] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,587] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,627] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,659] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,679] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 15:07:00,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,664] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,707] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,642] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,675] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,685] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,656] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,700] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,676] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,736] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,684] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,760] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 15:07:00,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:07:00,740] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:07:00,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,715] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,771] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,717] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,744] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,742] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 15:07:00,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:07:00,724] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:07:00,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 15:07:00,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:07:00,743] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:07:00,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 15:07:00,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:07:00,778] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:07:00,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 15:07:00,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:07:00,732] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:07:00,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:time (ms) | save-checkpoint: 2795.88 +[default2]:[2023-02-16 15:07:00,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:07:00,729] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:07:00,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 15:07:00,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:07:00,776] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:07:00,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 15:07:00,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:07:00,763] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:07:00,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]: successfully saved checkpoint at iteration 2500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 2501/ 3814 | consumed samples: 1280512 | consumed tokens: 2622488576 | elapsed time per iteration (s): 8.26 | learning rate: 5.371E-05 | global batch size: 512 | lm loss: 4.371264E+00 | loss scale: 131072.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 61.991 | TFLOPs: 46.82 | +[default7]: iteration 2502/ 3814 | consumed samples: 1281024 | consumed tokens: 2623537152 | elapsed time per iteration (s): 5.46 | learning rate: 5.364E-05 | global batch size: 512 | lm loss: 4.353359E+00 | loss scale: 131072.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.734 | TFLOPs: 70.80 | +[default7]: iteration 2503/ 3814 | consumed samples: 1281536 | consumed tokens: 2624585728 | elapsed time per iteration (s): 5.45 | learning rate: 5.357E-05 | global batch size: 512 | lm loss: 4.366185E+00 | loss scale: 131072.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.929 | TFLOPs: 70.95 | +[default7]: iteration 2504/ 3814 | consumed samples: 1282048 | consumed tokens: 2625634304 | elapsed time per iteration (s): 5.48 | learning rate: 5.349E-05 | global batch size: 512 | lm loss: 4.344825E+00 | loss scale: 131072.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.417 | TFLOPs: 70.56 | +[default7]: iteration 2505/ 3814 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 5.46 | learning rate: 5.342E-05 | global batch size: 512 | lm loss: 4.360113E+00 | loss scale: 131072.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.760 | TFLOPs: 70.82 | +[default7]: iteration 2506/ 3814 | consumed samples: 1283072 | consumed tokens: 2627731456 | elapsed time per iteration (s): 5.45 | learning rate: 5.335E-05 | global batch size: 512 | lm loss: 4.360265E+00 | loss scale: 131072.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.984 | TFLOPs: 70.99 | +[default7]: iteration 2507/ 3814 | consumed samples: 1283584 | consumed tokens: 2628780032 | elapsed time per iteration (s): 5.48 | learning rate: 5.328E-05 | global batch size: 512 | lm loss: 4.339787E+00 | loss scale: 131072.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.410 | TFLOPs: 70.55 | +[default7]: iteration 2508/ 3814 | consumed samples: 1284096 | consumed tokens: 2629828608 | elapsed time per iteration (s): 5.47 | learning rate: 5.321E-05 | global batch size: 512 | lm loss: 4.371634E+00 | loss scale: 131072.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.644 | TFLOPs: 70.73 | +[default7]: iteration 2509/ 3814 | consumed samples: 1284608 | consumed tokens: 2630877184 | elapsed time per iteration (s): 5.46 | learning rate: 5.314E-05 | global batch size: 512 | lm loss: 4.357670E+00 | loss scale: 131072.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.814 | TFLOPs: 70.86 | +[default7]: iteration 2510/ 3814 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 5.45 | learning rate: 5.306E-05 | global batch size: 512 | lm loss: 4.321858E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.910 | TFLOPs: 70.93 | +[default7]: iteration 2511/ 3814 | consumed samples: 1285632 | consumed tokens: 2632974336 | elapsed time per iteration (s): 5.47 | learning rate: 5.299E-05 | global batch size: 512 | lm loss: 4.367831E+00 | loss scale: 131072.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.537 | TFLOPs: 70.65 | +[default7]: iteration 2512/ 3814 | consumed samples: 1286144 | consumed tokens: 2634022912 | elapsed time per iteration (s): 5.46 | learning rate: 5.292E-05 | global batch size: 512 | lm loss: 4.353232E+00 | loss scale: 131072.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.731 | TFLOPs: 70.80 | +[default7]: iteration 2513/ 3814 | consumed samples: 1286656 | consumed tokens: 2635071488 | elapsed time per iteration (s): 5.46 | learning rate: 5.285E-05 | global batch size: 512 | lm loss: 4.377919E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.721 | TFLOPs: 70.79 | +[default7]: iteration 2514/ 3814 | consumed samples: 1287168 | consumed tokens: 2636120064 | elapsed time per iteration (s): 5.47 | learning rate: 5.278E-05 | global batch size: 512 | lm loss: 4.361230E+00 | loss scale: 131072.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.598 | TFLOPs: 70.70 | +[default7]: iteration 2515/ 3814 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 5.46 | learning rate: 5.271E-05 | global batch size: 512 | lm loss: 4.371551E+00 | loss scale: 131072.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.767 | TFLOPs: 70.82 | +[default7]: iteration 2516/ 3814 | consumed samples: 1288192 | consumed tokens: 2638217216 | elapsed time per iteration (s): 5.45 | learning rate: 5.264E-05 | global batch size: 512 | lm loss: 4.359939E+00 | loss scale: 131072.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.868 | TFLOPs: 70.90 | +[default7]: iteration 2517/ 3814 | consumed samples: 1288704 | consumed tokens: 2639265792 | elapsed time per iteration (s): 5.46 | learning rate: 5.256E-05 | global batch size: 512 | lm loss: 4.331656E+00 | loss scale: 131072.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.707 | TFLOPs: 70.78 | +[default7]: iteration 2518/ 3814 | consumed samples: 1289216 | consumed tokens: 2640314368 | elapsed time per iteration (s): 5.46 | learning rate: 5.249E-05 | global batch size: 512 | lm loss: 4.365445E+00 | loss scale: 131072.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.740 | TFLOPs: 70.80 | +[default7]: iteration 2519/ 3814 | consumed samples: 1289728 | consumed tokens: 2641362944 | elapsed time per iteration (s): 5.46 | learning rate: 5.242E-05 | global batch size: 512 | lm loss: 4.342895E+00 | loss scale: 131072.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.847 | TFLOPs: 70.88 | +[default7]: iteration 2520/ 3814 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 5.45 | learning rate: 5.235E-05 | global batch size: 512 | lm loss: 4.373384E+00 | loss scale: 131072.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.864 | TFLOPs: 70.90 | +[default7]: iteration 2521/ 3814 | consumed samples: 1290752 | consumed tokens: 2643460096 | elapsed time per iteration (s): 5.47 | learning rate: 5.228E-05 | global batch size: 512 | lm loss: 4.340891E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.623 | TFLOPs: 70.71 | +[default7]: iteration 2522/ 3814 | consumed samples: 1291264 | consumed tokens: 2644508672 | elapsed time per iteration (s): 5.46 | learning rate: 5.221E-05 | global batch size: 512 | lm loss: 4.364008E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.720 | TFLOPs: 70.79 | +[default7]: iteration 2523/ 3814 | consumed samples: 1291776 | consumed tokens: 2645557248 | elapsed time per iteration (s): 5.47 | learning rate: 5.214E-05 | global batch size: 512 | lm loss: 4.379059E+00 | loss scale: 131072.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.671 | TFLOPs: 70.75 | +[default7]: iteration 2524/ 3814 | consumed samples: 1292288 | consumed tokens: 2646605824 | elapsed time per iteration (s): 5.45 | learning rate: 5.207E-05 | global batch size: 512 | lm loss: 4.362563E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.980 | TFLOPs: 70.98 | +[default7]: iteration 2525/ 3814 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 5.46 | learning rate: 5.199E-05 | global batch size: 512 | lm loss: 4.351849E+00 | loss scale: 131072.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.689 | TFLOPs: 70.76 | +[default7]: iteration 2526/ 3814 | consumed samples: 1293312 | consumed tokens: 2648702976 | elapsed time per iteration (s): 5.45 | learning rate: 5.192E-05 | global batch size: 512 | lm loss: 4.364927E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.863 | TFLOPs: 70.90 | +[default7]: iteration 2527/ 3814 | consumed samples: 1293824 | consumed tokens: 2649751552 | elapsed time per iteration (s): 5.45 | learning rate: 5.185E-05 | global batch size: 512 | lm loss: 4.348009E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.957 | TFLOPs: 70.97 | +[default7]: iteration 2528/ 3814 | consumed samples: 1294336 | consumed tokens: 2650800128 | elapsed time per iteration (s): 5.44 | learning rate: 5.178E-05 | global batch size: 512 | lm loss: 4.348742E+00 | loss scale: 131072.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.049 | TFLOPs: 71.04 | +[default7]: iteration 2529/ 3814 | consumed samples: 1294848 | consumed tokens: 2651848704 | elapsed time per iteration (s): 5.45 | learning rate: 5.171E-05 | global batch size: 512 | lm loss: 4.366364E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.955 | TFLOPs: 70.97 | +[default7]: iteration 2530/ 3814 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 5.44 | learning rate: 5.164E-05 | global batch size: 512 | lm loss: 4.354900E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.171 | TFLOPs: 71.13 | +[default7]: iteration 2531/ 3814 | consumed samples: 1295872 | consumed tokens: 2653945856 | elapsed time per iteration (s): 5.44 | learning rate: 5.157E-05 | global batch size: 512 | lm loss: 4.342245E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.166 | TFLOPs: 71.12 | +[default7]: iteration 2532/ 3814 | consumed samples: 1296384 | consumed tokens: 2654994432 | elapsed time per iteration (s): 5.44 | learning rate: 5.150E-05 | global batch size: 512 | lm loss: 4.351997E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.046 | TFLOPs: 71.03 | +[default7]: iteration 2533/ 3814 | consumed samples: 1296896 | consumed tokens: 2656043008 | elapsed time per iteration (s): 5.45 | learning rate: 5.143E-05 | global batch size: 512 | lm loss: 4.340396E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.978 | TFLOPs: 70.98 | +[default7]: iteration 2534/ 3814 | consumed samples: 1297408 | consumed tokens: 2657091584 | elapsed time per iteration (s): 5.45 | learning rate: 5.135E-05 | global batch size: 512 | lm loss: 4.363808E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.984 | TFLOPs: 70.99 | +[default7]: iteration 2535/ 3814 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 5.45 | learning rate: 5.128E-05 | global batch size: 512 | lm loss: 4.380110E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.906 | TFLOPs: 70.93 | +[default7]: iteration 2536/ 3814 | consumed samples: 1298432 | consumed tokens: 2659188736 | elapsed time per iteration (s): 5.45 | learning rate: 5.121E-05 | global batch size: 512 | lm loss: 4.355454E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.997 | TFLOPs: 71.00 | +[default7]: iteration 2537/ 3814 | consumed samples: 1298944 | consumed tokens: 2660237312 | elapsed time per iteration (s): 5.46 | learning rate: 5.114E-05 | global batch size: 512 | lm loss: 4.336874E+00 | loss scale: 131072.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.834 | TFLOPs: 70.87 | +[default7]: iteration 2538/ 3814 | consumed samples: 1299456 | consumed tokens: 2661285888 | elapsed time per iteration (s): 5.44 | learning rate: 5.107E-05 | global batch size: 512 | lm loss: 4.344586E+00 | loss scale: 131072.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.068 | TFLOPs: 71.05 | +[default7]: iteration 2539/ 3814 | consumed samples: 1299968 | consumed tokens: 2662334464 | elapsed time per iteration (s): 5.44 | learning rate: 5.100E-05 | global batch size: 512 | lm loss: 4.355806E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 2540/ 3814 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 5.45 | learning rate: 5.093E-05 | global batch size: 512 | lm loss: 4.362216E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.929 | TFLOPs: 70.95 | +[default7]: iteration 2541/ 3814 | consumed samples: 1300992 | consumed tokens: 2664431616 | elapsed time per iteration (s): 5.45 | learning rate: 5.086E-05 | global batch size: 512 | lm loss: 4.335752E+00 | loss scale: 131072.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.990 | TFLOPs: 70.99 | +[default7]: iteration 2542/ 3814 | consumed samples: 1301504 | consumed tokens: 2665480192 | elapsed time per iteration (s): 5.44 | learning rate: 5.079E-05 | global batch size: 512 | lm loss: 4.364627E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.057 | TFLOPs: 71.04 | +[default7]: iteration 2543/ 3814 | consumed samples: 1302016 | consumed tokens: 2666528768 | elapsed time per iteration (s): 5.44 | learning rate: 5.072E-05 | global batch size: 512 | lm loss: 4.346757E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.133 | TFLOPs: 71.10 | +[default7]: iteration 2544/ 3814 | consumed samples: 1302528 | consumed tokens: 2667577344 | elapsed time per iteration (s): 5.44 | learning rate: 5.065E-05 | global batch size: 512 | lm loss: 4.334450E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.058 | TFLOPs: 71.04 | +[default7]: iteration 2545/ 3814 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 5.43 | learning rate: 5.058E-05 | global batch size: 512 | lm loss: 4.367045E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.232 | TFLOPs: 71.17 | +[default7]: iteration 2546/ 3814 | consumed samples: 1303552 | consumed tokens: 2669674496 | elapsed time per iteration (s): 5.46 | learning rate: 5.051E-05 | global batch size: 512 | lm loss: 4.329138E+00 | loss scale: 131072.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.847 | TFLOPs: 70.88 | +[default7]: iteration 2547/ 3814 | consumed samples: 1304064 | consumed tokens: 2670723072 | elapsed time per iteration (s): 5.47 | learning rate: 5.043E-05 | global batch size: 512 | lm loss: 4.356115E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.644 | TFLOPs: 70.73 | +[default7]: iteration 2548/ 3814 | consumed samples: 1304576 | consumed tokens: 2671771648 | elapsed time per iteration (s): 5.46 | learning rate: 5.036E-05 | global batch size: 512 | lm loss: 4.362108E+00 | loss scale: 131072.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.698 | TFLOPs: 70.77 | +[default7]: iteration 2549/ 3814 | consumed samples: 1305088 | consumed tokens: 2672820224 | elapsed time per iteration (s): 5.46 | learning rate: 5.029E-05 | global batch size: 512 | lm loss: 4.343196E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.833 | TFLOPs: 70.87 | +[default7]: iteration 2550/ 3814 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 5.44 | learning rate: 5.022E-05 | global batch size: 512 | lm loss: 4.351226E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.045 | TFLOPs: 71.03 | +[default7]: iteration 2551/ 3814 | consumed samples: 1306112 | consumed tokens: 2674917376 | elapsed time per iteration (s): 5.45 | learning rate: 5.015E-05 | global batch size: 512 | lm loss: 4.338223E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.001 | TFLOPs: 71.00 | +[default7]: iteration 2552/ 3814 | consumed samples: 1306624 | consumed tokens: 2675965952 | elapsed time per iteration (s): 5.44 | learning rate: 5.008E-05 | global batch size: 512 | lm loss: 4.342094E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.078 | TFLOPs: 71.06 | +[default7]: iteration 2553/ 3814 | consumed samples: 1307136 | consumed tokens: 2677014528 | elapsed time per iteration (s): 5.46 | learning rate: 5.001E-05 | global batch size: 512 | lm loss: 4.335836E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.769 | TFLOPs: 70.82 | +[default7]: iteration 2554/ 3814 | consumed samples: 1307648 | consumed tokens: 2678063104 | elapsed time per iteration (s): 5.44 | learning rate: 4.994E-05 | global batch size: 512 | lm loss: 4.331849E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.070 | TFLOPs: 71.05 | +[default7]: iteration 2555/ 3814 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 5.46 | learning rate: 4.987E-05 | global batch size: 512 | lm loss: 4.333837E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.747 | TFLOPs: 70.81 | +[default7]: iteration 2556/ 3814 | consumed samples: 1308672 | consumed tokens: 2680160256 | elapsed time per iteration (s): 5.44 | learning rate: 4.980E-05 | global batch size: 512 | lm loss: 4.355989E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.154 | TFLOPs: 71.12 | +[default7]: iteration 2557/ 3814 | consumed samples: 1309184 | consumed tokens: 2681208832 | elapsed time per iteration (s): 5.45 | learning rate: 4.973E-05 | global batch size: 512 | lm loss: 4.339284E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.904 | TFLOPs: 70.93 | +[default7]: iteration 2558/ 3814 | consumed samples: 1309696 | consumed tokens: 2682257408 | elapsed time per iteration (s): 5.46 | learning rate: 4.966E-05 | global batch size: 512 | lm loss: 4.339801E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.775 | TFLOPs: 70.83 | +[default7]: iteration 2559/ 3814 | consumed samples: 1310208 | consumed tokens: 2683305984 | elapsed time per iteration (s): 5.43 | learning rate: 4.959E-05 | global batch size: 512 | lm loss: 4.306396E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.256 | TFLOPs: 71.19 | +[default7]: iteration 2560/ 3814 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 5.45 | learning rate: 4.952E-05 | global batch size: 512 | lm loss: 4.341623E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.963 | TFLOPs: 70.97 | +[default7]: iteration 2561/ 3814 | consumed samples: 1311232 | consumed tokens: 2685403136 | elapsed time per iteration (s): 5.42 | learning rate: 4.945E-05 | global batch size: 512 | lm loss: 4.348144E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.396 | TFLOPs: 71.30 | +[default7]: iteration 2562/ 3814 | consumed samples: 1311744 | consumed tokens: 2686451712 | elapsed time per iteration (s): 5.42 | learning rate: 4.938E-05 | global batch size: 512 | lm loss: 4.318213E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.517 | TFLOPs: 71.39 | +[default7]: iteration 2563/ 3814 | consumed samples: 1312256 | consumed tokens: 2687500288 | elapsed time per iteration (s): 5.44 | learning rate: 4.931E-05 | global batch size: 512 | lm loss: 4.326573E+00 | loss scale: 131072.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.081 | TFLOPs: 71.06 | +[default7]: iteration 2564/ 3814 | consumed samples: 1312768 | consumed tokens: 2688548864 | elapsed time per iteration (s): 5.44 | learning rate: 4.924E-05 | global batch size: 512 | lm loss: 4.333785E+00 | loss scale: 131072.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.195 | TFLOPs: 71.15 | +[default7]: iteration 2565/ 3814 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 5.43 | learning rate: 4.917E-05 | global batch size: 512 | lm loss: 4.332517E+00 | loss scale: 131072.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.209 | TFLOPs: 71.16 | +[default7]: iteration 2566/ 3814 | consumed samples: 1313792 | consumed tokens: 2690646016 | elapsed time per iteration (s): 5.43 | learning rate: 4.910E-05 | global batch size: 512 | lm loss: 4.364997E+00 | loss scale: 131072.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.301 | TFLOPs: 71.23 | +[default7]: iteration 2567/ 3814 | consumed samples: 1314304 | consumed tokens: 2691694592 | elapsed time per iteration (s): 5.48 | learning rate: 4.903E-05 | global batch size: 512 | lm loss: 4.353397E+00 | loss scale: 131072.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.421 | TFLOPs: 70.56 | +[default7]: iteration 2568/ 3814 | consumed samples: 1314816 | consumed tokens: 2692743168 | elapsed time per iteration (s): 5.47 | learning rate: 4.896E-05 | global batch size: 512 | lm loss: 4.352827E+00 | loss scale: 131072.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.672 | TFLOPs: 70.75 | +[default7]: iteration 2569/ 3814 | consumed samples: 1315328 | consumed tokens: 2693791744 | elapsed time per iteration (s): 5.44 | learning rate: 4.889E-05 | global batch size: 512 | lm loss: 4.342396E+00 | loss scale: 131072.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.098 | TFLOPs: 71.07 | +[default7]: iteration 2570/ 3814 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 5.43 | learning rate: 4.882E-05 | global batch size: 512 | lm loss: 4.348863E+00 | loss scale: 131072.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 2571/ 3814 | consumed samples: 1316352 | consumed tokens: 2695888896 | elapsed time per iteration (s): 5.44 | learning rate: 4.875E-05 | global batch size: 512 | lm loss: 4.350410E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.157 | TFLOPs: 71.12 | +[default7]: iteration 2572/ 3814 | consumed samples: 1316864 | consumed tokens: 2696937472 | elapsed time per iteration (s): 5.44 | learning rate: 4.868E-05 | global batch size: 512 | lm loss: 4.350709E+00 | loss scale: 131072.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.056 | TFLOPs: 71.04 | +[default7]: iteration 2573/ 3814 | consumed samples: 1317376 | consumed tokens: 2697986048 | elapsed time per iteration (s): 5.45 | learning rate: 4.861E-05 | global batch size: 512 | lm loss: 4.334457E+00 | loss scale: 131072.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.967 | TFLOPs: 70.97 | +[default7]: iteration 2574/ 3814 | consumed samples: 1317888 | consumed tokens: 2699034624 | elapsed time per iteration (s): 5.45 | learning rate: 4.854E-05 | global batch size: 512 | lm loss: 4.365003E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.013 | TFLOPs: 71.01 | +[default7]: iteration 2575/ 3814 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 5.46 | learning rate: 4.847E-05 | global batch size: 512 | lm loss: 4.317165E+00 | loss scale: 131072.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.820 | TFLOPs: 70.86 | +[default7]: iteration 2576/ 3814 | consumed samples: 1318912 | consumed tokens: 2701131776 | elapsed time per iteration (s): 5.44 | learning rate: 4.840E-05 | global batch size: 512 | lm loss: 4.340417E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.070 | TFLOPs: 71.05 | +[default7]: iteration 2577/ 3814 | consumed samples: 1319424 | consumed tokens: 2702180352 | elapsed time per iteration (s): 5.43 | learning rate: 4.833E-05 | global batch size: 512 | lm loss: 4.352428E+00 | loss scale: 131072.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.243 | TFLOPs: 71.18 | +[default7]: iteration 2578/ 3814 | consumed samples: 1319936 | consumed tokens: 2703228928 | elapsed time per iteration (s): 5.43 | learning rate: 4.826E-05 | global batch size: 512 | lm loss: 4.372121E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.293 | TFLOPs: 71.22 | +[default7]: iteration 2579/ 3814 | consumed samples: 1320448 | consumed tokens: 2704277504 | elapsed time per iteration (s): 5.44 | learning rate: 4.819E-05 | global batch size: 512 | lm loss: 4.361848E+00 | loss scale: 131072.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.139 | TFLOPs: 71.10 | +[default7]: iteration 2580/ 3814 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 5.50 | learning rate: 4.812E-05 | global batch size: 512 | lm loss: 4.331644E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.143 | TFLOPs: 70.35 | +[default7]: iteration 2581/ 3814 | consumed samples: 1321472 | consumed tokens: 2706374656 | elapsed time per iteration (s): 5.45 | learning rate: 4.805E-05 | global batch size: 512 | lm loss: 4.320878E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.927 | TFLOPs: 70.94 | +[default7]: iteration 2582/ 3814 | consumed samples: 1321984 | consumed tokens: 2707423232 | elapsed time per iteration (s): 5.46 | learning rate: 4.798E-05 | global batch size: 512 | lm loss: 4.350171E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.687 | TFLOPs: 70.76 | +[default7]: iteration 2583/ 3814 | consumed samples: 1322496 | consumed tokens: 2708471808 | elapsed time per iteration (s): 5.47 | learning rate: 4.791E-05 | global batch size: 512 | lm loss: 4.324698E+00 | loss scale: 131072.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.604 | TFLOPs: 70.70 | +[default7]: iteration 2584/ 3814 | consumed samples: 1323008 | consumed tokens: 2709520384 | elapsed time per iteration (s): 5.49 | learning rate: 4.784E-05 | global batch size: 512 | lm loss: 4.322150E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.211 | TFLOPs: 70.40 | +[default7]: iteration 2585/ 3814 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 5.46 | learning rate: 4.777E-05 | global batch size: 512 | lm loss: 4.330132E+00 | loss scale: 131072.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.766 | TFLOPs: 70.82 | +[default7]: iteration 2586/ 3814 | consumed samples: 1324032 | consumed tokens: 2711617536 | elapsed time per iteration (s): 5.47 | learning rate: 4.770E-05 | global batch size: 512 | lm loss: 4.322893E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.658 | TFLOPs: 70.74 | +[default7]: iteration 2587/ 3814 | consumed samples: 1324544 | consumed tokens: 2712666112 | elapsed time per iteration (s): 5.49 | learning rate: 4.764E-05 | global batch size: 512 | lm loss: 4.321023E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.241 | TFLOPs: 70.43 | +[default7]: iteration 2588/ 3814 | consumed samples: 1325056 | consumed tokens: 2713714688 | elapsed time per iteration (s): 5.46 | learning rate: 4.757E-05 | global batch size: 512 | lm loss: 4.346792E+00 | loss scale: 131072.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.774 | TFLOPs: 70.83 | +[default7]: iteration 2589/ 3814 | consumed samples: 1325568 | consumed tokens: 2714763264 | elapsed time per iteration (s): 5.44 | learning rate: 4.750E-05 | global batch size: 512 | lm loss: 4.322217E+00 | loss scale: 131072.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.057 | TFLOPs: 71.04 | +[default7]: iteration 2590/ 3814 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 5.41 | learning rate: 4.743E-05 | global batch size: 512 | lm loss: 4.346608E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.674 | TFLOPs: 71.51 | +[default7]: iteration 2591/ 3814 | consumed samples: 1326592 | consumed tokens: 2716860416 | elapsed time per iteration (s): 5.39 | learning rate: 4.736E-05 | global batch size: 512 | lm loss: 4.337993E+00 | loss scale: 131072.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.950 | TFLOPs: 71.72 | +[default7]: iteration 2592/ 3814 | consumed samples: 1327104 | consumed tokens: 2717908992 | elapsed time per iteration (s): 5.42 | learning rate: 4.729E-05 | global batch size: 512 | lm loss: 4.339030E+00 | loss scale: 131072.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.509 | TFLOPs: 71.38 | +[default7]: iteration 2593/ 3814 | consumed samples: 1327616 | consumed tokens: 2718957568 | elapsed time per iteration (s): 5.42 | learning rate: 4.722E-05 | global batch size: 512 | lm loss: 4.331451E+00 | loss scale: 131072.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.480 | TFLOPs: 71.36 | +[default7]: iteration 2594/ 3814 | consumed samples: 1328128 | consumed tokens: 2720006144 | elapsed time per iteration (s): 5.41 | learning rate: 4.715E-05 | global batch size: 512 | lm loss: 4.349327E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.596 | TFLOPs: 71.45 | +[default7]: iteration 2595/ 3814 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 5.43 | learning rate: 4.708E-05 | global batch size: 512 | lm loss: 4.361297E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.211 | TFLOPs: 71.16 | +[default7]: iteration 2596/ 3814 | consumed samples: 1329152 | consumed tokens: 2722103296 | elapsed time per iteration (s): 5.41 | learning rate: 4.701E-05 | global batch size: 512 | lm loss: 4.317369E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.665 | TFLOPs: 71.50 | +[default7]: iteration 2597/ 3814 | consumed samples: 1329664 | consumed tokens: 2723151872 | elapsed time per iteration (s): 5.41 | learning rate: 4.694E-05 | global batch size: 512 | lm loss: 4.341680E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.674 | TFLOPs: 71.51 | +[default7]: iteration 2598/ 3814 | consumed samples: 1330176 | consumed tokens: 2724200448 | elapsed time per iteration (s): 5.42 | learning rate: 4.687E-05 | global batch size: 512 | lm loss: 4.336831E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.467 | TFLOPs: 71.35 | +[default7]: iteration 2599/ 3814 | consumed samples: 1330688 | consumed tokens: 2725249024 | elapsed time per iteration (s): 5.43 | learning rate: 4.681E-05 | global batch size: 512 | lm loss: 4.351107E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.276 | TFLOPs: 71.21 | +[default7]: iteration 2600/ 3814 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 5.43 | learning rate: 4.674E-05 | global batch size: 512 | lm loss: 4.312409E+00 | loss scale: 131072.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.320 | TFLOPs: 71.24 | +[default7]: iteration 2601/ 3814 | consumed samples: 1331712 | consumed tokens: 2727346176 | elapsed time per iteration (s): 5.43 | learning rate: 4.667E-05 | global batch size: 512 | lm loss: 4.338802E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.304 | TFLOPs: 71.23 | +[default7]: iteration 2602/ 3814 | consumed samples: 1332224 | consumed tokens: 2728394752 | elapsed time per iteration (s): 5.42 | learning rate: 4.660E-05 | global batch size: 512 | lm loss: 4.334571E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.488 | TFLOPs: 71.37 | +[default7]: iteration 2603/ 3814 | consumed samples: 1332736 | consumed tokens: 2729443328 | elapsed time per iteration (s): 5.42 | learning rate: 4.653E-05 | global batch size: 512 | lm loss: 4.339299E+00 | loss scale: 131072.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.386 | TFLOPs: 71.29 | +[default7]: iteration 2604/ 3814 | consumed samples: 1333248 | consumed tokens: 2730491904 | elapsed time per iteration (s): 5.44 | learning rate: 4.646E-05 | global batch size: 512 | lm loss: 4.317187E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.092 | TFLOPs: 71.07 | +[default7]: iteration 2605/ 3814 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 5.44 | learning rate: 4.639E-05 | global batch size: 512 | lm loss: 4.309396E+00 | loss scale: 131072.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.091 | TFLOPs: 71.07 | +[default7]: iteration 2606/ 3814 | consumed samples: 1334272 | consumed tokens: 2732589056 | elapsed time per iteration (s): 5.44 | learning rate: 4.632E-05 | global batch size: 512 | lm loss: 4.327542E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.107 | TFLOPs: 71.08 | +[default7]: iteration 2607/ 3814 | consumed samples: 1334784 | consumed tokens: 2733637632 | elapsed time per iteration (s): 5.43 | learning rate: 4.625E-05 | global batch size: 512 | lm loss: 4.348459E+00 | loss scale: 131072.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.349 | TFLOPs: 71.26 | +[default7]: iteration 2608/ 3814 | consumed samples: 1335296 | consumed tokens: 2734686208 | elapsed time per iteration (s): 5.43 | learning rate: 4.619E-05 | global batch size: 512 | lm loss: 4.295058E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.208 | TFLOPs: 71.16 | +[default7]: iteration 2609/ 3814 | consumed samples: 1335808 | consumed tokens: 2735734784 | elapsed time per iteration (s): 5.45 | learning rate: 4.612E-05 | global batch size: 512 | lm loss: 4.345945E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.986 | TFLOPs: 70.99 | +[default7]: iteration 2610/ 3814 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 5.46 | learning rate: 4.605E-05 | global batch size: 512 | lm loss: 4.334542E+00 | loss scale: 131072.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.768 | TFLOPs: 70.82 | +[default7]: iteration 2611/ 3814 | consumed samples: 1336832 | consumed tokens: 2737831936 | elapsed time per iteration (s): 5.45 | learning rate: 4.598E-05 | global batch size: 512 | lm loss: 4.334908E+00 | loss scale: 131072.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.899 | TFLOPs: 70.92 | +[default7]: iteration 2612/ 3814 | consumed samples: 1337344 | consumed tokens: 2738880512 | elapsed time per iteration (s): 5.44 | learning rate: 4.591E-05 | global batch size: 512 | lm loss: 4.342258E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 2613/ 3814 | consumed samples: 1337856 | consumed tokens: 2739929088 | elapsed time per iteration (s): 5.47 | learning rate: 4.584E-05 | global batch size: 512 | lm loss: 4.314288E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.670 | TFLOPs: 70.75 | +[default7]: iteration 2614/ 3814 | consumed samples: 1338368 | consumed tokens: 2740977664 | elapsed time per iteration (s): 5.45 | learning rate: 4.577E-05 | global batch size: 512 | lm loss: 4.312479E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.989 | TFLOPs: 70.99 | +[default7]: iteration 2615/ 3814 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 5.43 | learning rate: 4.571E-05 | global batch size: 512 | lm loss: 4.334808E+00 | loss scale: 131072.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.284 | TFLOPs: 71.21 | +[default7]: iteration 2616/ 3814 | consumed samples: 1339392 | consumed tokens: 2743074816 | elapsed time per iteration (s): 5.42 | learning rate: 4.564E-05 | global batch size: 512 | lm loss: 4.328606E+00 | loss scale: 131072.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.462 | TFLOPs: 71.35 | +[default7]: iteration 2617/ 3814 | consumed samples: 1339904 | consumed tokens: 2744123392 | elapsed time per iteration (s): 5.43 | learning rate: 4.557E-05 | global batch size: 512 | lm loss: 4.343260E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.321 | TFLOPs: 71.24 | +[default7]: iteration 2618/ 3814 | consumed samples: 1340416 | consumed tokens: 2745171968 | elapsed time per iteration (s): 5.43 | learning rate: 4.550E-05 | global batch size: 512 | lm loss: 4.331403E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.231 | TFLOPs: 71.17 | +[default7]: iteration 2619/ 3814 | consumed samples: 1340928 | consumed tokens: 2746220544 | elapsed time per iteration (s): 5.42 | learning rate: 4.543E-05 | global batch size: 512 | lm loss: 4.322745E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.527 | TFLOPs: 71.40 | +[default7]: iteration 2620/ 3814 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 5.42 | learning rate: 4.536E-05 | global batch size: 512 | lm loss: 4.308495E+00 | loss scale: 131072.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.406 | TFLOPs: 71.31 | +[default7]: iteration 2621/ 3814 | consumed samples: 1341952 | consumed tokens: 2748317696 | elapsed time per iteration (s): 5.47 | learning rate: 4.529E-05 | global batch size: 512 | lm loss: 4.340656E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.589 | TFLOPs: 70.69 | +[default7]: iteration 2622/ 3814 | consumed samples: 1342464 | consumed tokens: 2749366272 | elapsed time per iteration (s): 5.43 | learning rate: 4.523E-05 | global batch size: 512 | lm loss: 4.295642E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.214 | TFLOPs: 71.16 | +[default7]: iteration 2623/ 3814 | consumed samples: 1342976 | consumed tokens: 2750414848 | elapsed time per iteration (s): 5.44 | learning rate: 4.516E-05 | global batch size: 512 | lm loss: 4.333856E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.037 | TFLOPs: 71.03 | +[default7]: iteration 2624/ 3814 | consumed samples: 1343488 | consumed tokens: 2751463424 | elapsed time per iteration (s): 5.43 | learning rate: 4.509E-05 | global batch size: 512 | lm loss: 4.327712E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.330 | TFLOPs: 71.25 | +[default7]: iteration 2625/ 3814 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 5.43 | learning rate: 4.502E-05 | global batch size: 512 | lm loss: 4.316317E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.375 | TFLOPs: 71.28 | +[default7]: iteration 2626/ 3814 | consumed samples: 1344512 | consumed tokens: 2753560576 | elapsed time per iteration (s): 5.43 | learning rate: 4.495E-05 | global batch size: 512 | lm loss: 4.325695E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.295 | TFLOPs: 71.22 | +[default7]: iteration 2627/ 3814 | consumed samples: 1345024 | consumed tokens: 2754609152 | elapsed time per iteration (s): 5.42 | learning rate: 4.489E-05 | global batch size: 512 | lm loss: 4.320629E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.403 | TFLOPs: 71.30 | +[default7]: iteration 2628/ 3814 | consumed samples: 1345536 | consumed tokens: 2755657728 | elapsed time per iteration (s): 5.43 | learning rate: 4.482E-05 | global batch size: 512 | lm loss: 4.342032E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.302 | TFLOPs: 71.23 | +[default7]: iteration 2629/ 3814 | consumed samples: 1346048 | consumed tokens: 2756706304 | elapsed time per iteration (s): 5.42 | learning rate: 4.475E-05 | global batch size: 512 | lm loss: 4.299590E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.472 | TFLOPs: 71.36 | +[default7]: iteration 2630/ 3814 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 5.42 | learning rate: 4.468E-05 | global batch size: 512 | lm loss: 4.334504E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.462 | TFLOPs: 71.35 | +[default7]: iteration 2631/ 3814 | consumed samples: 1347072 | consumed tokens: 2758803456 | elapsed time per iteration (s): 5.41 | learning rate: 4.461E-05 | global batch size: 512 | lm loss: 4.334439E+00 | loss scale: 131072.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.578 | TFLOPs: 71.44 | +[default7]: iteration 2632/ 3814 | consumed samples: 1347584 | consumed tokens: 2759852032 | elapsed time per iteration (s): 5.43 | learning rate: 4.455E-05 | global batch size: 512 | lm loss: 4.355612E+00 | loss scale: 131072.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.377 | TFLOPs: 71.28 | +[default7]: iteration 2633/ 3814 | consumed samples: 1348096 | consumed tokens: 2760900608 | elapsed time per iteration (s): 5.42 | learning rate: 4.448E-05 | global batch size: 512 | lm loss: 4.321245E+00 | loss scale: 131072.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.528 | TFLOPs: 71.40 | +[default7]: iteration 2634/ 3814 | consumed samples: 1348608 | consumed tokens: 2761949184 | elapsed time per iteration (s): 5.42 | learning rate: 4.441E-05 | global batch size: 512 | lm loss: 4.307152E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.547 | TFLOPs: 71.41 | +[default7]: iteration 2635/ 3814 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 5.43 | learning rate: 4.434E-05 | global batch size: 512 | lm loss: 4.333857E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.236 | TFLOPs: 71.18 | +[default7]: iteration 2636/ 3814 | consumed samples: 1349632 | consumed tokens: 2764046336 | elapsed time per iteration (s): 5.43 | learning rate: 4.427E-05 | global batch size: 512 | lm loss: 4.299744E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.253 | TFLOPs: 71.19 | +[default7]: iteration 2637/ 3814 | consumed samples: 1350144 | consumed tokens: 2765094912 | elapsed time per iteration (s): 5.43 | learning rate: 4.421E-05 | global batch size: 512 | lm loss: 4.330354E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.253 | TFLOPs: 71.19 | +[default7]: iteration 2638/ 3814 | consumed samples: 1350656 | consumed tokens: 2766143488 | elapsed time per iteration (s): 5.43 | learning rate: 4.414E-05 | global batch size: 512 | lm loss: 4.329280E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.327 | TFLOPs: 71.25 | +[default7]: iteration 2639/ 3814 | consumed samples: 1351168 | consumed tokens: 2767192064 | elapsed time per iteration (s): 5.43 | learning rate: 4.407E-05 | global batch size: 512 | lm loss: 4.323013E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 2640/ 3814 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 5.42 | learning rate: 4.400E-05 | global batch size: 512 | lm loss: 4.323956E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.540 | TFLOPs: 71.41 | +[default7]: iteration 2641/ 3814 | consumed samples: 1352192 | consumed tokens: 2769289216 | elapsed time per iteration (s): 5.44 | learning rate: 4.394E-05 | global batch size: 512 | lm loss: 4.298998E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.108 | TFLOPs: 71.08 | +[default7]: iteration 2642/ 3814 | consumed samples: 1352704 | consumed tokens: 2770337792 | elapsed time per iteration (s): 5.43 | learning rate: 4.387E-05 | global batch size: 512 | lm loss: 4.327886E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.270 | TFLOPs: 71.20 | +[default7]: iteration 2643/ 3814 | consumed samples: 1353216 | consumed tokens: 2771386368 | elapsed time per iteration (s): 5.42 | learning rate: 4.380E-05 | global batch size: 512 | lm loss: 4.314148E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.499 | TFLOPs: 71.38 | +[default7]: iteration 2644/ 3814 | consumed samples: 1353728 | consumed tokens: 2772434944 | elapsed time per iteration (s): 5.43 | learning rate: 4.373E-05 | global batch size: 512 | lm loss: 4.310820E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.277 | TFLOPs: 71.21 | +[default7]: iteration 2645/ 3814 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 5.43 | learning rate: 4.367E-05 | global batch size: 512 | lm loss: 4.312728E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.275 | TFLOPs: 71.21 | +[default7]: iteration 2646/ 3814 | consumed samples: 1354752 | consumed tokens: 2774532096 | elapsed time per iteration (s): 5.45 | learning rate: 4.360E-05 | global batch size: 512 | lm loss: 4.304853E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.969 | TFLOPs: 70.98 | +[default7]: iteration 2647/ 3814 | consumed samples: 1355264 | consumed tokens: 2775580672 | elapsed time per iteration (s): 5.42 | learning rate: 4.353E-05 | global batch size: 512 | lm loss: 4.324083E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.408 | TFLOPs: 71.31 | +[default7]: iteration 2648/ 3814 | consumed samples: 1355776 | consumed tokens: 2776629248 | elapsed time per iteration (s): 5.43 | learning rate: 4.346E-05 | global batch size: 512 | lm loss: 4.301730E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.306 | TFLOPs: 71.23 | +[default7]: iteration 2649/ 3814 | consumed samples: 1356288 | consumed tokens: 2777677824 | elapsed time per iteration (s): 5.43 | learning rate: 4.340E-05 | global batch size: 512 | lm loss: 4.318017E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.236 | TFLOPs: 71.18 | +[default7]: iteration 2650/ 3814 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 5.42 | learning rate: 4.333E-05 | global batch size: 512 | lm loss: 4.306138E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.444 | TFLOPs: 71.33 | +[default7]: iteration 2651/ 3814 | consumed samples: 1357312 | consumed tokens: 2779774976 | elapsed time per iteration (s): 5.44 | learning rate: 4.326E-05 | global batch size: 512 | lm loss: 4.286202E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.056 | TFLOPs: 71.04 | +[default7]: iteration 2652/ 3814 | consumed samples: 1357824 | consumed tokens: 2780823552 | elapsed time per iteration (s): 5.42 | learning rate: 4.319E-05 | global batch size: 512 | lm loss: 4.322713E+00 | loss scale: 131072.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 2653/ 3814 | consumed samples: 1358336 | consumed tokens: 2781872128 | elapsed time per iteration (s): 5.41 | learning rate: 4.313E-05 | global batch size: 512 | lm loss: 4.337001E+00 | loss scale: 131072.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.654 | TFLOPs: 71.49 | +[default7]: iteration 2654/ 3814 | consumed samples: 1358848 | consumed tokens: 2782920704 | elapsed time per iteration (s): 5.42 | learning rate: 4.306E-05 | global batch size: 512 | lm loss: 4.329000E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.456 | TFLOPs: 71.34 | +[default7]: iteration 2655/ 3814 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 5.44 | learning rate: 4.299E-05 | global batch size: 512 | lm loss: 4.320436E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.174 | TFLOPs: 71.13 | +[default7]: iteration 2656/ 3814 | consumed samples: 1359872 | consumed tokens: 2785017856 | elapsed time per iteration (s): 5.44 | learning rate: 4.292E-05 | global batch size: 512 | lm loss: 4.328115E+00 | loss scale: 131072.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.112 | TFLOPs: 71.08 | +[default7]: iteration 2657/ 3814 | consumed samples: 1360384 | consumed tokens: 2786066432 | elapsed time per iteration (s): 5.43 | learning rate: 4.286E-05 | global batch size: 512 | lm loss: 4.327755E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.358 | TFLOPs: 71.27 | +[default7]: iteration 2658/ 3814 | consumed samples: 1360896 | consumed tokens: 2787115008 | elapsed time per iteration (s): 5.45 | learning rate: 4.279E-05 | global batch size: 512 | lm loss: 4.332089E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.909 | TFLOPs: 70.93 | +[default7]: iteration 2659/ 3814 | consumed samples: 1361408 | consumed tokens: 2788163584 | elapsed time per iteration (s): 5.46 | learning rate: 4.272E-05 | global batch size: 512 | lm loss: 4.329191E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.727 | TFLOPs: 70.79 | +[default7]: iteration 2660/ 3814 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 5.43 | learning rate: 4.266E-05 | global batch size: 512 | lm loss: 4.328513E+00 | loss scale: 131072.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.210 | TFLOPs: 71.16 | +[default7]: iteration 2661/ 3814 | consumed samples: 1362432 | consumed tokens: 2790260736 | elapsed time per iteration (s): 5.44 | learning rate: 4.259E-05 | global batch size: 512 | lm loss: 4.335409E+00 | loss scale: 131072.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.077 | TFLOPs: 71.06 | +[default7]: iteration 2662/ 3814 | consumed samples: 1362944 | consumed tokens: 2791309312 | elapsed time per iteration (s): 5.43 | learning rate: 4.252E-05 | global batch size: 512 | lm loss: 4.320680E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.321 | TFLOPs: 71.24 | +[default7]: iteration 2663/ 3814 | consumed samples: 1363456 | consumed tokens: 2792357888 | elapsed time per iteration (s): 5.44 | learning rate: 4.246E-05 | global batch size: 512 | lm loss: 4.296611E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.184 | TFLOPs: 71.14 | +[default7]: iteration 2664/ 3814 | consumed samples: 1363968 | consumed tokens: 2793406464 | elapsed time per iteration (s): 5.42 | learning rate: 4.239E-05 | global batch size: 512 | lm loss: 4.281665E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.387 | TFLOPs: 71.29 | +[default7]: iteration 2665/ 3814 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 5.42 | learning rate: 4.232E-05 | global batch size: 512 | lm loss: 4.305022E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.487 | TFLOPs: 71.37 | +[default7]: iteration 2666/ 3814 | consumed samples: 1364992 | consumed tokens: 2795503616 | elapsed time per iteration (s): 5.43 | learning rate: 4.226E-05 | global batch size: 512 | lm loss: 4.310004E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.337 | TFLOPs: 71.25 | +[default7]: iteration 2667/ 3814 | consumed samples: 1365504 | consumed tokens: 2796552192 | elapsed time per iteration (s): 5.43 | learning rate: 4.219E-05 | global batch size: 512 | lm loss: 4.317684E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.297 | TFLOPs: 71.22 | +[default7]: iteration 2668/ 3814 | consumed samples: 1366016 | consumed tokens: 2797600768 | elapsed time per iteration (s): 5.44 | learning rate: 4.212E-05 | global batch size: 512 | lm loss: 4.328364E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.128 | TFLOPs: 71.10 | +[default7]: iteration 2669/ 3814 | consumed samples: 1366528 | consumed tokens: 2798649344 | elapsed time per iteration (s): 5.42 | learning rate: 4.206E-05 | global batch size: 512 | lm loss: 4.316431E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.500 | TFLOPs: 71.38 | +[default7]: iteration 2670/ 3814 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 5.42 | learning rate: 4.199E-05 | global batch size: 512 | lm loss: 4.302675E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.432 | TFLOPs: 71.33 | +[default7]: iteration 2671/ 3814 | consumed samples: 1367552 | consumed tokens: 2800746496 | elapsed time per iteration (s): 5.44 | learning rate: 4.192E-05 | global batch size: 512 | lm loss: 4.315454E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.184 | TFLOPs: 71.14 | +[default7]: iteration 2672/ 3814 | consumed samples: 1368064 | consumed tokens: 2801795072 | elapsed time per iteration (s): 5.42 | learning rate: 4.186E-05 | global batch size: 512 | lm loss: 4.310308E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.437 | TFLOPs: 71.33 | +[default7]: iteration 2673/ 3814 | consumed samples: 1368576 | consumed tokens: 2802843648 | elapsed time per iteration (s): 5.44 | learning rate: 4.179E-05 | global batch size: 512 | lm loss: 4.331181E+00 | loss scale: 131072.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.034 | TFLOPs: 71.02 | +[default7]: iteration 2674/ 3814 | consumed samples: 1369088 | consumed tokens: 2803892224 | elapsed time per iteration (s): 5.48 | learning rate: 4.172E-05 | global batch size: 512 | lm loss: 4.305829E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.374 | TFLOPs: 70.53 | +[default7]: iteration 2675/ 3814 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 5.44 | learning rate: 4.166E-05 | global batch size: 512 | lm loss: 4.296199E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.138 | TFLOPs: 71.10 | +[default7]: iteration 2676/ 3814 | consumed samples: 1370112 | consumed tokens: 2805989376 | elapsed time per iteration (s): 5.44 | learning rate: 4.159E-05 | global batch size: 512 | lm loss: 4.316828E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 2677/ 3814 | consumed samples: 1370624 | consumed tokens: 2807037952 | elapsed time per iteration (s): 5.44 | learning rate: 4.152E-05 | global batch size: 512 | lm loss: 4.326693E+00 | loss scale: 131072.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.141 | TFLOPs: 71.11 | +[default7]: iteration 2678/ 3814 | consumed samples: 1371136 | consumed tokens: 2808086528 | elapsed time per iteration (s): 5.44 | learning rate: 4.146E-05 | global batch size: 512 | lm loss: 4.347304E+00 | loss scale: 131072.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.039 | TFLOPs: 71.03 | +[default7]: iteration 2679/ 3814 | consumed samples: 1371648 | consumed tokens: 2809135104 | elapsed time per iteration (s): 5.44 | learning rate: 4.139E-05 | global batch size: 512 | lm loss: 4.310624E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 2680/ 3814 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 5.48 | learning rate: 4.132E-05 | global batch size: 512 | lm loss: 4.316818E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.405 | TFLOPs: 70.55 | +[default7]: iteration 2681/ 3814 | consumed samples: 1372672 | consumed tokens: 2811232256 | elapsed time per iteration (s): 5.44 | learning rate: 4.126E-05 | global batch size: 512 | lm loss: 4.291220E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.160 | TFLOPs: 71.12 | +[default7]: iteration 2682/ 3814 | consumed samples: 1373184 | consumed tokens: 2812280832 | elapsed time per iteration (s): 5.44 | learning rate: 4.119E-05 | global batch size: 512 | lm loss: 4.330418E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.107 | TFLOPs: 71.08 | +[default7]: iteration 2683/ 3814 | consumed samples: 1373696 | consumed tokens: 2813329408 | elapsed time per iteration (s): 5.42 | learning rate: 4.113E-05 | global batch size: 512 | lm loss: 4.304154E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.492 | TFLOPs: 71.37 | +[default7]: iteration 2684/ 3814 | consumed samples: 1374208 | consumed tokens: 2814377984 | elapsed time per iteration (s): 5.42 | learning rate: 4.106E-05 | global batch size: 512 | lm loss: 4.281180E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.547 | TFLOPs: 71.41 | +[default7]: iteration 2685/ 3814 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 5.43 | learning rate: 4.099E-05 | global batch size: 512 | lm loss: 4.295395E+00 | loss scale: 131072.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.248 | TFLOPs: 71.19 | +[default7]: iteration 2686/ 3814 | consumed samples: 1375232 | consumed tokens: 2816475136 | elapsed time per iteration (s): 5.42 | learning rate: 4.093E-05 | global batch size: 512 | lm loss: 4.315187E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.409 | TFLOPs: 71.31 | +[default7]: iteration 2687/ 3814 | consumed samples: 1375744 | consumed tokens: 2817523712 | elapsed time per iteration (s): 5.44 | learning rate: 4.086E-05 | global batch size: 512 | lm loss: 4.304327E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 2688/ 3814 | consumed samples: 1376256 | consumed tokens: 2818572288 | elapsed time per iteration (s): 5.45 | learning rate: 4.080E-05 | global batch size: 512 | lm loss: 4.307171E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.966 | TFLOPs: 70.97 | +[default7]: iteration 2689/ 3814 | consumed samples: 1376768 | consumed tokens: 2819620864 | elapsed time per iteration (s): 5.43 | learning rate: 4.073E-05 | global batch size: 512 | lm loss: 4.305687E+00 | loss scale: 131072.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.219 | TFLOPs: 71.16 | +[default7]: iteration 2690/ 3814 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 5.44 | learning rate: 4.066E-05 | global batch size: 512 | lm loss: 4.302915E+00 | loss scale: 131072.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.047 | TFLOPs: 71.03 | +[default7]: iteration 2691/ 3814 | consumed samples: 1377792 | consumed tokens: 2821718016 | elapsed time per iteration (s): 5.44 | learning rate: 4.060E-05 | global batch size: 512 | lm loss: 4.311848E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.055 | TFLOPs: 71.04 | +[default7]: iteration 2692/ 3814 | consumed samples: 1378304 | consumed tokens: 2822766592 | elapsed time per iteration (s): 5.40 | learning rate: 4.053E-05 | global batch size: 512 | lm loss: 4.311669E+00 | loss scale: 131072.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.802 | TFLOPs: 71.61 | +[default7]: iteration 2693/ 3814 | consumed samples: 1378816 | consumed tokens: 2823815168 | elapsed time per iteration (s): 5.41 | learning rate: 4.047E-05 | global batch size: 512 | lm loss: 4.316111E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.702 | TFLOPs: 71.53 | +[default7]: iteration 2694/ 3814 | consumed samples: 1379328 | consumed tokens: 2824863744 | elapsed time per iteration (s): 5.42 | learning rate: 4.040E-05 | global batch size: 512 | lm loss: 4.320184E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.520 | TFLOPs: 71.39 | +[default7]: iteration 2695/ 3814 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 5.42 | learning rate: 4.033E-05 | global batch size: 512 | lm loss: 4.318590E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.415 | TFLOPs: 71.31 | +[default7]: iteration 2696/ 3814 | consumed samples: 1380352 | consumed tokens: 2826960896 | elapsed time per iteration (s): 5.42 | learning rate: 4.027E-05 | global batch size: 512 | lm loss: 4.339879E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.526 | TFLOPs: 71.40 | +[default7]: iteration 2697/ 3814 | consumed samples: 1380864 | consumed tokens: 2828009472 | elapsed time per iteration (s): 5.43 | learning rate: 4.020E-05 | global batch size: 512 | lm loss: 4.294349E+00 | loss scale: 131072.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.316 | TFLOPs: 71.24 | +[default7]: iteration 2698/ 3814 | consumed samples: 1381376 | consumed tokens: 2829058048 | elapsed time per iteration (s): 5.43 | learning rate: 4.014E-05 | global batch size: 512 | lm loss: 4.355727E+00 | loss scale: 131072.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.346 | TFLOPs: 71.26 | +[default7]: iteration 2699/ 3814 | consumed samples: 1381888 | consumed tokens: 2830106624 | elapsed time per iteration (s): 5.42 | learning rate: 4.007E-05 | global batch size: 512 | lm loss: 4.316529E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.390 | TFLOPs: 71.29 | +[default7]: iteration 2700/ 3814 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 5.43 | learning rate: 4.001E-05 | global batch size: 512 | lm loss: 4.307576E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.282 | TFLOPs: 71.21 | +[default7]: iteration 2701/ 3814 | consumed samples: 1382912 | consumed tokens: 2832203776 | elapsed time per iteration (s): 5.44 | learning rate: 3.994E-05 | global batch size: 512 | lm loss: 4.308453E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.086 | TFLOPs: 71.06 | +[default7]: iteration 2702/ 3814 | consumed samples: 1383424 | consumed tokens: 2833252352 | elapsed time per iteration (s): 5.43 | learning rate: 3.988E-05 | global batch size: 512 | lm loss: 4.313663E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.348 | TFLOPs: 71.26 | +[default7]: iteration 2703/ 3814 | consumed samples: 1383936 | consumed tokens: 2834300928 | elapsed time per iteration (s): 5.43 | learning rate: 3.981E-05 | global batch size: 512 | lm loss: 4.331056E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.243 | TFLOPs: 71.18 | +[default7]: iteration 2704/ 3814 | consumed samples: 1384448 | consumed tokens: 2835349504 | elapsed time per iteration (s): 5.44 | learning rate: 3.974E-05 | global batch size: 512 | lm loss: 4.300025E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.151 | TFLOPs: 71.11 | +[default7]: iteration 2705/ 3814 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 5.45 | learning rate: 3.968E-05 | global batch size: 512 | lm loss: 4.301252E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.923 | TFLOPs: 70.94 | +[default7]: iteration 2706/ 3814 | consumed samples: 1385472 | consumed tokens: 2837446656 | elapsed time per iteration (s): 5.43 | learning rate: 3.961E-05 | global batch size: 512 | lm loss: 4.320740E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.228 | TFLOPs: 71.17 | +[default7]: iteration 2707/ 3814 | consumed samples: 1385984 | consumed tokens: 2838495232 | elapsed time per iteration (s): 5.43 | learning rate: 3.955E-05 | global batch size: 512 | lm loss: 4.300203E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.205 | TFLOPs: 71.15 | +[default7]: iteration 2708/ 3814 | consumed samples: 1386496 | consumed tokens: 2839543808 | elapsed time per iteration (s): 5.45 | learning rate: 3.948E-05 | global batch size: 512 | lm loss: 4.302763E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.024 | TFLOPs: 71.02 | +[default7]: iteration 2709/ 3814 | consumed samples: 1387008 | consumed tokens: 2840592384 | elapsed time per iteration (s): 5.46 | learning rate: 3.942E-05 | global batch size: 512 | lm loss: 4.327864E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.777 | TFLOPs: 70.83 | +[default7]: iteration 2710/ 3814 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 5.43 | learning rate: 3.935E-05 | global batch size: 512 | lm loss: 4.301909E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.258 | TFLOPs: 71.19 | +[default7]: iteration 2711/ 3814 | consumed samples: 1388032 | consumed tokens: 2842689536 | elapsed time per iteration (s): 5.44 | learning rate: 3.929E-05 | global batch size: 512 | lm loss: 4.314760E+00 | loss scale: 131072.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.188 | TFLOPs: 71.14 | +[default7]: iteration 2712/ 3814 | consumed samples: 1388544 | consumed tokens: 2843738112 | elapsed time per iteration (s): 5.45 | learning rate: 3.922E-05 | global batch size: 512 | lm loss: 4.316148E+00 | loss scale: 131072.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.982 | TFLOPs: 70.99 | +[default7]: iteration 2713/ 3814 | consumed samples: 1389056 | consumed tokens: 2844786688 | elapsed time per iteration (s): 5.46 | learning rate: 3.916E-05 | global batch size: 512 | lm loss: 4.310252E+00 | loss scale: 131072.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.702 | TFLOPs: 70.77 | +[default7]: iteration 2714/ 3814 | consumed samples: 1389568 | consumed tokens: 2845835264 | elapsed time per iteration (s): 5.44 | learning rate: 3.909E-05 | global batch size: 512 | lm loss: 4.349387E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.097 | TFLOPs: 71.07 | +[default7]: iteration 2715/ 3814 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 5.44 | learning rate: 3.903E-05 | global batch size: 512 | lm loss: 4.306402E+00 | loss scale: 131072.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.072 | TFLOPs: 71.05 | +[default7]: iteration 2716/ 3814 | consumed samples: 1390592 | consumed tokens: 2847932416 | elapsed time per iteration (s): 5.44 | learning rate: 3.896E-05 | global batch size: 512 | lm loss: 4.316306E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.186 | TFLOPs: 71.14 | +[default7]: iteration 2717/ 3814 | consumed samples: 1391104 | consumed tokens: 2848980992 | elapsed time per iteration (s): 5.43 | learning rate: 3.890E-05 | global batch size: 512 | lm loss: 4.271944E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.215 | TFLOPs: 71.16 | +[default7]: iteration 2718/ 3814 | consumed samples: 1391616 | consumed tokens: 2850029568 | elapsed time per iteration (s): 5.43 | learning rate: 3.883E-05 | global batch size: 512 | lm loss: 4.295407E+00 | loss scale: 131072.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.210 | TFLOPs: 71.16 | +[default7]: iteration 2719/ 3814 | consumed samples: 1392128 | consumed tokens: 2851078144 | elapsed time per iteration (s): 5.44 | learning rate: 3.877E-05 | global batch size: 512 | lm loss: 4.305358E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.104 | TFLOPs: 71.08 | +[default7]: iteration 2720/ 3814 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 5.47 | learning rate: 3.870E-05 | global batch size: 512 | lm loss: 4.310882E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.576 | TFLOPs: 70.68 | +[default7]: iteration 2721/ 3814 | consumed samples: 1393152 | consumed tokens: 2853175296 | elapsed time per iteration (s): 5.44 | learning rate: 3.864E-05 | global batch size: 512 | lm loss: 4.321494E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.041 | TFLOPs: 71.03 | +[default7]: iteration 2722/ 3814 | consumed samples: 1393664 | consumed tokens: 2854223872 | elapsed time per iteration (s): 5.45 | learning rate: 3.857E-05 | global batch size: 512 | lm loss: 4.296024E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.967 | TFLOPs: 70.97 | +[default7]: iteration 2723/ 3814 | consumed samples: 1394176 | consumed tokens: 2855272448 | elapsed time per iteration (s): 5.45 | learning rate: 3.851E-05 | global batch size: 512 | lm loss: 4.323666E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.966 | TFLOPs: 70.97 | +[default7]: iteration 2724/ 3814 | consumed samples: 1394688 | consumed tokens: 2856321024 | elapsed time per iteration (s): 5.42 | learning rate: 3.844E-05 | global batch size: 512 | lm loss: 4.279381E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.387 | TFLOPs: 71.29 | +[default7]: iteration 2725/ 3814 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 5.44 | learning rate: 3.838E-05 | global batch size: 512 | lm loss: 4.287966E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.189 | TFLOPs: 71.14 | +[default7]: iteration 2726/ 3814 | consumed samples: 1395712 | consumed tokens: 2858418176 | elapsed time per iteration (s): 5.43 | learning rate: 3.831E-05 | global batch size: 512 | lm loss: 4.310906E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.16 | +[default7]: iteration 2727/ 3814 | consumed samples: 1396224 | consumed tokens: 2859466752 | elapsed time per iteration (s): 5.44 | learning rate: 3.825E-05 | global batch size: 512 | lm loss: 4.312801E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.056 | TFLOPs: 71.04 | +[default7]: iteration 2728/ 3814 | consumed samples: 1396736 | consumed tokens: 2860515328 | elapsed time per iteration (s): 5.44 | learning rate: 3.819E-05 | global batch size: 512 | lm loss: 4.300783E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.204 | TFLOPs: 71.15 | +[default7]: iteration 2729/ 3814 | consumed samples: 1397248 | consumed tokens: 2861563904 | elapsed time per iteration (s): 5.43 | learning rate: 3.812E-05 | global batch size: 512 | lm loss: 4.312462E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.339 | TFLOPs: 71.26 | +[default7]: iteration 2730/ 3814 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 5.43 | learning rate: 3.806E-05 | global batch size: 512 | lm loss: 4.314348E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 2731/ 3814 | consumed samples: 1398272 | consumed tokens: 2863661056 | elapsed time per iteration (s): 5.43 | learning rate: 3.799E-05 | global batch size: 512 | lm loss: 4.307550E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 2732/ 3814 | consumed samples: 1398784 | consumed tokens: 2864709632 | elapsed time per iteration (s): 5.43 | learning rate: 3.793E-05 | global batch size: 512 | lm loss: 4.294220E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.256 | TFLOPs: 71.19 | +[default7]: iteration 2733/ 3814 | consumed samples: 1399296 | consumed tokens: 2865758208 | elapsed time per iteration (s): 5.44 | learning rate: 3.786E-05 | global batch size: 512 | lm loss: 4.302170E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.147 | TFLOPs: 71.11 | +[default7]: iteration 2734/ 3814 | consumed samples: 1399808 | consumed tokens: 2866806784 | elapsed time per iteration (s): 5.43 | learning rate: 3.780E-05 | global batch size: 512 | lm loss: 4.292727E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.213 | TFLOPs: 71.16 | +[default7]: iteration 2735/ 3814 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 5.45 | learning rate: 3.774E-05 | global batch size: 512 | lm loss: 4.284249E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.019 | TFLOPs: 71.01 | +[default7]: iteration 2736/ 3814 | consumed samples: 1400832 | consumed tokens: 2868903936 | elapsed time per iteration (s): 5.45 | learning rate: 3.767E-05 | global batch size: 512 | lm loss: 4.322751E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.021 | TFLOPs: 71.02 | +[default7]: iteration 2737/ 3814 | consumed samples: 1401344 | consumed tokens: 2869952512 | elapsed time per iteration (s): 5.45 | learning rate: 3.761E-05 | global batch size: 512 | lm loss: 4.287860E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.014 | TFLOPs: 71.01 | +[default7]: iteration 2738/ 3814 | consumed samples: 1401856 | consumed tokens: 2871001088 | elapsed time per iteration (s): 5.44 | learning rate: 3.754E-05 | global batch size: 512 | lm loss: 4.295834E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.085 | TFLOPs: 71.06 | +[default7]: iteration 2739/ 3814 | consumed samples: 1402368 | consumed tokens: 2872049664 | elapsed time per iteration (s): 5.45 | learning rate: 3.748E-05 | global batch size: 512 | lm loss: 4.314578E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.990 | TFLOPs: 70.99 | +[default7]: iteration 2740/ 3814 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 5.44 | learning rate: 3.742E-05 | global batch size: 512 | lm loss: 4.304594E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.111 | TFLOPs: 71.08 | +[default7]: iteration 2741/ 3814 | consumed samples: 1403392 | consumed tokens: 2874146816 | elapsed time per iteration (s): 5.44 | learning rate: 3.735E-05 | global batch size: 512 | lm loss: 4.286507E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.158 | TFLOPs: 71.12 | +[default7]: iteration 2742/ 3814 | consumed samples: 1403904 | consumed tokens: 2875195392 | elapsed time per iteration (s): 5.44 | learning rate: 3.729E-05 | global batch size: 512 | lm loss: 4.295920E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.163 | TFLOPs: 71.12 | +[default7]: iteration 2743/ 3814 | consumed samples: 1404416 | consumed tokens: 2876243968 | elapsed time per iteration (s): 5.42 | learning rate: 3.722E-05 | global batch size: 512 | lm loss: 4.262067E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.435 | TFLOPs: 71.33 | +[default7]: iteration 2744/ 3814 | consumed samples: 1404928 | consumed tokens: 2877292544 | elapsed time per iteration (s): 5.44 | learning rate: 3.716E-05 | global batch size: 512 | lm loss: 4.285487E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.138 | TFLOPs: 71.10 | +[default7]: iteration 2745/ 3814 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 5.45 | learning rate: 3.710E-05 | global batch size: 512 | lm loss: 4.302623E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.864 | TFLOPs: 70.90 | +[default7]: iteration 2746/ 3814 | consumed samples: 1405952 | consumed tokens: 2879389696 | elapsed time per iteration (s): 5.45 | learning rate: 3.703E-05 | global batch size: 512 | lm loss: 4.301231E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.877 | TFLOPs: 70.91 | +[default7]: iteration 2747/ 3814 | consumed samples: 1406464 | consumed tokens: 2880438272 | elapsed time per iteration (s): 5.45 | learning rate: 3.697E-05 | global batch size: 512 | lm loss: 4.320372E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.002 | TFLOPs: 71.00 | +[default7]: iteration 2748/ 3814 | consumed samples: 1406976 | consumed tokens: 2881486848 | elapsed time per iteration (s): 5.43 | learning rate: 3.690E-05 | global batch size: 512 | lm loss: 4.315245E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.274 | TFLOPs: 71.21 | +[default7]: iteration 2749/ 3814 | consumed samples: 1407488 | consumed tokens: 2882535424 | elapsed time per iteration (s): 5.43 | learning rate: 3.684E-05 | global batch size: 512 | lm loss: 4.303829E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.337 | TFLOPs: 71.25 | +[default0]:saving checkpoint at iteration 2750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 15:29:40,937] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2750 is begin to save! +[default0]:[2023-02-16 15:29:40,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:40,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_01-model_states.pt... +[default7]: iteration 2750/ 3814 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 5.43 | learning rate: 3.678E-05 | global batch size: 512 | lm loss: 4.288713E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.251 | TFLOPs: 71.19 | +[default0]:[2023-02-16 15:29:41,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,112] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,231] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,294] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,398] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,455] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,519] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,677] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,685] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,793] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,839] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:41,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,893] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:41,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:41,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,905] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:41,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:41,946] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_01-model_states.pt. +[default0]:[2023-02-16 15:29:41,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:41,958] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,140] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,174] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,195] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,227] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,285] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,306] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,394] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,424] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,425] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,486] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_00-model_states.pt. +[default1]:[2023-02-16 15:29:42,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,533] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,660] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,714] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,768] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,825] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 15:29:42,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 15:29:42,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,888] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 15:29:42,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 15:29:42,943] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 15:29:42,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 15:29:42,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt. +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,925] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 15:29:42,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 15:29:42,928] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 15:29:42,928] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 15:29:42,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:29:42,972] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:29:43,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,446] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,437] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,504] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,504] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,514] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,501] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,511] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,519] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,516] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,488] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,544] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,555] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,503] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,589] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,551] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,537] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,547] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,602] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,547] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,575] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,622] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,562] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,585] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,608] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,576] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,620] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,628] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,650] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,620] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,652] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,620] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,640] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,635] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,571] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,589] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,655] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,626] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,601] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,682] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,666] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,638] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,627] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,697] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,713] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,630] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,631] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,688] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 15:29:43,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:29:43,656] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:29:43,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,721] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,672] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 15:29:43,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:29:43,684] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:29:43,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,707] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,751] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 15:29:43,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:29:43,718] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:29:43,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 15:29:43,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:29:43,665] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:29:43,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,735] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,710] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 15:29:43,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,742] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 15:29:43,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:29:43,746] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:29:43,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:time (ms) | save-checkpoint: 2880.37 +[default4]:[2023-02-16 15:29:43,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,720] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 15:29:43,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:29:43,725] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:29:43,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 15:29:43,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:29:43,799] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:29:43,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]: successfully saved checkpoint at iteration 2750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default4]:[2023-02-16 15:29:43,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:29:43,816] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:29:43,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]: iteration 2751/ 3814 | consumed samples: 1408512 | consumed tokens: 2884632576 | elapsed time per iteration (s): 8.32 | learning rate: 3.671E-05 | global batch size: 512 | lm loss: 4.294137E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 61.555 | TFLOPs: 46.49 | +[default7]: iteration 2752/ 3814 | consumed samples: 1409024 | consumed tokens: 2885681152 | elapsed time per iteration (s): 5.43 | learning rate: 3.665E-05 | global batch size: 512 | lm loss: 4.302911E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 2753/ 3814 | consumed samples: 1409536 | consumed tokens: 2886729728 | elapsed time per iteration (s): 5.41 | learning rate: 3.659E-05 | global batch size: 512 | lm loss: 4.290793E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.567 | TFLOPs: 71.43 | +[default7]: iteration 2754/ 3814 | consumed samples: 1410048 | consumed tokens: 2887778304 | elapsed time per iteration (s): 5.41 | learning rate: 3.652E-05 | global batch size: 512 | lm loss: 4.308618E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.566 | TFLOPs: 71.43 | +[default7]: iteration 2755/ 3814 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 5.42 | learning rate: 3.646E-05 | global batch size: 512 | lm loss: 4.280190E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.408 | TFLOPs: 71.31 | +[default7]: iteration 2756/ 3814 | consumed samples: 1411072 | consumed tokens: 2889875456 | elapsed time per iteration (s): 5.44 | learning rate: 3.640E-05 | global batch size: 512 | lm loss: 4.277869E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.186 | TFLOPs: 71.14 | +[default7]: iteration 2757/ 3814 | consumed samples: 1411584 | consumed tokens: 2890924032 | elapsed time per iteration (s): 5.42 | learning rate: 3.633E-05 | global batch size: 512 | lm loss: 4.289749E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.472 | TFLOPs: 71.36 | +[default7]: iteration 2758/ 3814 | consumed samples: 1412096 | consumed tokens: 2891972608 | elapsed time per iteration (s): 5.45 | learning rate: 3.627E-05 | global batch size: 512 | lm loss: 4.264739E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.952 | TFLOPs: 70.96 | +[default7]: iteration 2759/ 3814 | consumed samples: 1412608 | consumed tokens: 2893021184 | elapsed time per iteration (s): 5.44 | learning rate: 3.621E-05 | global batch size: 512 | lm loss: 4.322101E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.080 | TFLOPs: 71.06 | +[default7]: iteration 2760/ 3814 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 5.42 | learning rate: 3.614E-05 | global batch size: 512 | lm loss: 4.276719E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.416 | TFLOPs: 71.31 | +[default7]: iteration 2761/ 3814 | consumed samples: 1413632 | consumed tokens: 2895118336 | elapsed time per iteration (s): 5.44 | learning rate: 3.608E-05 | global batch size: 512 | lm loss: 4.310340E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.177 | TFLOPs: 71.13 | +[default7]: iteration 2762/ 3814 | consumed samples: 1414144 | consumed tokens: 2896166912 | elapsed time per iteration (s): 5.44 | learning rate: 3.602E-05 | global batch size: 512 | lm loss: 4.308682E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 2763/ 3814 | consumed samples: 1414656 | consumed tokens: 2897215488 | elapsed time per iteration (s): 5.41 | learning rate: 3.595E-05 | global batch size: 512 | lm loss: 4.267792E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.697 | TFLOPs: 71.53 | +[default7]: iteration 2764/ 3814 | consumed samples: 1415168 | consumed tokens: 2898264064 | elapsed time per iteration (s): 5.40 | learning rate: 3.589E-05 | global batch size: 512 | lm loss: 4.304419E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.824 | TFLOPs: 71.62 | +[default7]: iteration 2765/ 3814 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 5.44 | learning rate: 3.583E-05 | global batch size: 512 | lm loss: 4.297857E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.197 | TFLOPs: 71.15 | +[default7]: iteration 2766/ 3814 | consumed samples: 1416192 | consumed tokens: 2900361216 | elapsed time per iteration (s): 5.40 | learning rate: 3.576E-05 | global batch size: 512 | lm loss: 4.280975E+00 | loss scale: 131072.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.883 | TFLOPs: 71.67 | +[default7]: iteration 2767/ 3814 | consumed samples: 1416704 | consumed tokens: 2901409792 | elapsed time per iteration (s): 5.42 | learning rate: 3.570E-05 | global batch size: 512 | lm loss: 4.299049E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.419 | TFLOPs: 71.32 | +[default7]: iteration 2768/ 3814 | consumed samples: 1417216 | consumed tokens: 2902458368 | elapsed time per iteration (s): 5.41 | learning rate: 3.564E-05 | global batch size: 512 | lm loss: 4.309487E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.587 | TFLOPs: 71.44 | +[default7]: iteration 2769/ 3814 | consumed samples: 1417728 | consumed tokens: 2903506944 | elapsed time per iteration (s): 5.40 | learning rate: 3.558E-05 | global batch size: 512 | lm loss: 4.276049E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.813 | TFLOPs: 71.61 | +[default7]: iteration 2770/ 3814 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 5.41 | learning rate: 3.551E-05 | global batch size: 512 | lm loss: 4.286477E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.677 | TFLOPs: 71.51 | +[default7]: iteration 2771/ 3814 | consumed samples: 1418752 | consumed tokens: 2905604096 | elapsed time per iteration (s): 5.42 | learning rate: 3.545E-05 | global batch size: 512 | lm loss: 4.310502E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.530 | TFLOPs: 71.40 | +[default7]: iteration 2772/ 3814 | consumed samples: 1419264 | consumed tokens: 2906652672 | elapsed time per iteration (s): 5.41 | learning rate: 3.539E-05 | global batch size: 512 | lm loss: 4.288520E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.716 | TFLOPs: 71.54 | +[default7]: iteration 2773/ 3814 | consumed samples: 1419776 | consumed tokens: 2907701248 | elapsed time per iteration (s): 5.40 | learning rate: 3.532E-05 | global batch size: 512 | lm loss: 4.315956E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.827 | TFLOPs: 71.62 | +[default7]: iteration 2774/ 3814 | consumed samples: 1420288 | consumed tokens: 2908749824 | elapsed time per iteration (s): 5.41 | learning rate: 3.526E-05 | global batch size: 512 | lm loss: 4.311539E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.602 | TFLOPs: 71.45 | +[default7]: iteration 2775/ 3814 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 5.42 | learning rate: 3.520E-05 | global batch size: 512 | lm loss: 4.276530E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.495 | TFLOPs: 71.37 | +[default7]: iteration 2776/ 3814 | consumed samples: 1421312 | consumed tokens: 2910846976 | elapsed time per iteration (s): 5.41 | learning rate: 3.514E-05 | global batch size: 512 | lm loss: 4.298565E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.622 | TFLOPs: 71.47 | +[default7]: iteration 2777/ 3814 | consumed samples: 1421824 | consumed tokens: 2911895552 | elapsed time per iteration (s): 5.41 | learning rate: 3.507E-05 | global batch size: 512 | lm loss: 4.303431E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.716 | TFLOPs: 71.54 | +[default7]: iteration 2778/ 3814 | consumed samples: 1422336 | consumed tokens: 2912944128 | elapsed time per iteration (s): 5.39 | learning rate: 3.501E-05 | global batch size: 512 | lm loss: 4.318236E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.964 | TFLOPs: 71.73 | +[default7]: iteration 2779/ 3814 | consumed samples: 1422848 | consumed tokens: 2913992704 | elapsed time per iteration (s): 5.42 | learning rate: 3.495E-05 | global batch size: 512 | lm loss: 4.284740E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.536 | TFLOPs: 71.40 | +[default7]: iteration 2780/ 3814 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 5.43 | learning rate: 3.489E-05 | global batch size: 512 | lm loss: 4.297196E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.377 | TFLOPs: 71.28 | +[default7]: iteration 2781/ 3814 | consumed samples: 1423872 | consumed tokens: 2916089856 | elapsed time per iteration (s): 5.38 | learning rate: 3.482E-05 | global batch size: 512 | lm loss: 4.306341E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.102 | TFLOPs: 71.83 | +[default7]: iteration 2782/ 3814 | consumed samples: 1424384 | consumed tokens: 2917138432 | elapsed time per iteration (s): 5.42 | learning rate: 3.476E-05 | global batch size: 512 | lm loss: 4.274189E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.447 | TFLOPs: 71.34 | +[default7]: iteration 2783/ 3814 | consumed samples: 1424896 | consumed tokens: 2918187008 | elapsed time per iteration (s): 5.45 | learning rate: 3.470E-05 | global batch size: 512 | lm loss: 4.255661E+00 | loss scale: 131072.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.973 | TFLOPs: 70.98 | +[default7]: iteration 2784/ 3814 | consumed samples: 1425408 | consumed tokens: 2919235584 | elapsed time per iteration (s): 5.41 | learning rate: 3.464E-05 | global batch size: 512 | lm loss: 4.305099E+00 | loss scale: 131072.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.575 | TFLOPs: 71.43 | +[default7]: iteration 2785/ 3814 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 5.42 | learning rate: 3.458E-05 | global batch size: 512 | lm loss: 4.300199E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.393 | TFLOPs: 71.30 | +[default7]: iteration 2786/ 3814 | consumed samples: 1426432 | consumed tokens: 2921332736 | elapsed time per iteration (s): 5.43 | learning rate: 3.451E-05 | global batch size: 512 | lm loss: 4.290411E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.323 | TFLOPs: 71.24 | +[default7]: iteration 2787/ 3814 | consumed samples: 1426944 | consumed tokens: 2922381312 | elapsed time per iteration (s): 5.44 | learning rate: 3.445E-05 | global batch size: 512 | lm loss: 4.287711E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.039 | TFLOPs: 71.03 | +[default7]: iteration 2788/ 3814 | consumed samples: 1427456 | consumed tokens: 2923429888 | elapsed time per iteration (s): 5.43 | learning rate: 3.439E-05 | global batch size: 512 | lm loss: 4.285310E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.275 | TFLOPs: 71.21 | +[default7]: iteration 2789/ 3814 | consumed samples: 1427968 | consumed tokens: 2924478464 | elapsed time per iteration (s): 5.42 | learning rate: 3.433E-05 | global batch size: 512 | lm loss: 4.306675E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.438 | TFLOPs: 71.33 | +[default7]: iteration 2790/ 3814 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 5.43 | learning rate: 3.427E-05 | global batch size: 512 | lm loss: 4.297623E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.310 | TFLOPs: 71.23 | +[default7]: iteration 2791/ 3814 | consumed samples: 1428992 | consumed tokens: 2926575616 | elapsed time per iteration (s): 5.43 | learning rate: 3.420E-05 | global batch size: 512 | lm loss: 4.315260E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.210 | TFLOPs: 71.16 | +[default7]: iteration 2792/ 3814 | consumed samples: 1429504 | consumed tokens: 2927624192 | elapsed time per iteration (s): 5.44 | learning rate: 3.414E-05 | global batch size: 512 | lm loss: 4.278610E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.083 | TFLOPs: 71.06 | +[default7]: iteration 2793/ 3814 | consumed samples: 1430016 | consumed tokens: 2928672768 | elapsed time per iteration (s): 5.43 | learning rate: 3.408E-05 | global batch size: 512 | lm loss: 4.290851E+00 | loss scale: 131072.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 2794/ 3814 | consumed samples: 1430528 | consumed tokens: 2929721344 | elapsed time per iteration (s): 5.45 | learning rate: 3.402E-05 | global batch size: 512 | lm loss: 4.327928E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.023 | TFLOPs: 71.02 | +[default7]: iteration 2795/ 3814 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 5.42 | learning rate: 3.396E-05 | global batch size: 512 | lm loss: 4.277533E+00 | loss scale: 131072.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.538 | TFLOPs: 71.41 | +[default7]: iteration 2796/ 3814 | consumed samples: 1431552 | consumed tokens: 2931818496 | elapsed time per iteration (s): 5.42 | learning rate: 3.389E-05 | global batch size: 512 | lm loss: 4.262504E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 2797/ 3814 | consumed samples: 1432064 | consumed tokens: 2932867072 | elapsed time per iteration (s): 5.42 | learning rate: 3.383E-05 | global batch size: 512 | lm loss: 4.285645E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.390 | TFLOPs: 71.29 | +[default7]: iteration 2798/ 3814 | consumed samples: 1432576 | consumed tokens: 2933915648 | elapsed time per iteration (s): 5.41 | learning rate: 3.377E-05 | global batch size: 512 | lm loss: 4.274577E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.656 | TFLOPs: 71.49 | +[default7]: iteration 2799/ 3814 | consumed samples: 1433088 | consumed tokens: 2934964224 | elapsed time per iteration (s): 5.41 | learning rate: 3.371E-05 | global batch size: 512 | lm loss: 4.299656E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.590 | TFLOPs: 71.44 | +[default7]: iteration 2800/ 3814 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 5.40 | learning rate: 3.365E-05 | global batch size: 512 | lm loss: 4.308341E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.892 | TFLOPs: 71.67 | +[default7]: iteration 2801/ 3814 | consumed samples: 1434112 | consumed tokens: 2937061376 | elapsed time per iteration (s): 5.41 | learning rate: 3.359E-05 | global batch size: 512 | lm loss: 4.266888E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.593 | TFLOPs: 71.45 | +[default7]: iteration 2802/ 3814 | consumed samples: 1434624 | consumed tokens: 2938109952 | elapsed time per iteration (s): 5.40 | learning rate: 3.352E-05 | global batch size: 512 | lm loss: 4.292533E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.867 | TFLOPs: 71.65 | +[default7]: iteration 2803/ 3814 | consumed samples: 1435136 | consumed tokens: 2939158528 | elapsed time per iteration (s): 5.43 | learning rate: 3.346E-05 | global batch size: 512 | lm loss: 4.312403E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.206 | TFLOPs: 71.15 | +[default7]: iteration 2804/ 3814 | consumed samples: 1435648 | consumed tokens: 2940207104 | elapsed time per iteration (s): 5.43 | learning rate: 3.340E-05 | global batch size: 512 | lm loss: 4.289742E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.377 | TFLOPs: 71.28 | +[default7]: iteration 2805/ 3814 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 5.46 | learning rate: 3.334E-05 | global batch size: 512 | lm loss: 4.273314E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 2806/ 3814 | consumed samples: 1436672 | consumed tokens: 2942304256 | elapsed time per iteration (s): 5.44 | learning rate: 3.328E-05 | global batch size: 512 | lm loss: 4.272683E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.050 | TFLOPs: 71.04 | +[default7]: iteration 2807/ 3814 | consumed samples: 1437184 | consumed tokens: 2943352832 | elapsed time per iteration (s): 5.49 | learning rate: 3.322E-05 | global batch size: 512 | lm loss: 4.297998E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.176 | TFLOPs: 70.38 | +[default7]: iteration 2808/ 3814 | consumed samples: 1437696 | consumed tokens: 2944401408 | elapsed time per iteration (s): 5.47 | learning rate: 3.316E-05 | global batch size: 512 | lm loss: 4.290239E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.666 | TFLOPs: 70.75 | +[default7]: iteration 2809/ 3814 | consumed samples: 1438208 | consumed tokens: 2945449984 | elapsed time per iteration (s): 5.46 | learning rate: 3.310E-05 | global batch size: 512 | lm loss: 4.283582E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.730 | TFLOPs: 70.79 | +[default7]: iteration 2810/ 3814 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 5.48 | learning rate: 3.303E-05 | global batch size: 512 | lm loss: 4.279614E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.358 | TFLOPs: 70.51 | +[default7]: iteration 2811/ 3814 | consumed samples: 1439232 | consumed tokens: 2947547136 | elapsed time per iteration (s): 5.49 | learning rate: 3.297E-05 | global batch size: 512 | lm loss: 4.289997E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.311 | TFLOPs: 70.48 | +[default7]: iteration 2812/ 3814 | consumed samples: 1439744 | consumed tokens: 2948595712 | elapsed time per iteration (s): 5.49 | learning rate: 3.291E-05 | global batch size: 512 | lm loss: 4.301793E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.206 | TFLOPs: 70.40 | +[default7]: iteration 2813/ 3814 | consumed samples: 1440256 | consumed tokens: 2949644288 | elapsed time per iteration (s): 5.47 | learning rate: 3.285E-05 | global batch size: 512 | lm loss: 4.303016E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.674 | TFLOPs: 70.75 | +[default7]: iteration 2814/ 3814 | consumed samples: 1440768 | consumed tokens: 2950692864 | elapsed time per iteration (s): 5.45 | learning rate: 3.279E-05 | global batch size: 512 | lm loss: 4.299335E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.951 | TFLOPs: 70.96 | +[default7]: iteration 2815/ 3814 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 5.45 | learning rate: 3.273E-05 | global batch size: 512 | lm loss: 4.311325E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.001 | TFLOPs: 71.00 | +[default7]: iteration 2816/ 3814 | consumed samples: 1441792 | consumed tokens: 2952790016 | elapsed time per iteration (s): 5.43 | learning rate: 3.267E-05 | global batch size: 512 | lm loss: 4.276783E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.265 | TFLOPs: 71.20 | +[default7]: iteration 2817/ 3814 | consumed samples: 1442304 | consumed tokens: 2953838592 | elapsed time per iteration (s): 5.45 | learning rate: 3.261E-05 | global batch size: 512 | lm loss: 4.283970E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.983 | TFLOPs: 70.99 | +[default7]: iteration 2818/ 3814 | consumed samples: 1442816 | consumed tokens: 2954887168 | elapsed time per iteration (s): 5.44 | learning rate: 3.255E-05 | global batch size: 512 | lm loss: 4.292104E+00 | loss scale: 131072.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.183 | TFLOPs: 71.14 | +[default7]: iteration 2819/ 3814 | consumed samples: 1443328 | consumed tokens: 2955935744 | elapsed time per iteration (s): 5.44 | learning rate: 3.249E-05 | global batch size: 512 | lm loss: 4.283960E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.035 | TFLOPs: 71.03 | +[default7]: iteration 2820/ 3814 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 5.44 | learning rate: 3.242E-05 | global batch size: 512 | lm loss: 4.283696E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.068 | TFLOPs: 71.05 | +[default7]: iteration 2821/ 3814 | consumed samples: 1444352 | consumed tokens: 2958032896 | elapsed time per iteration (s): 5.45 | learning rate: 3.236E-05 | global batch size: 512 | lm loss: 4.293045E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.917 | TFLOPs: 70.94 | +[default7]: iteration 2822/ 3814 | consumed samples: 1444864 | consumed tokens: 2959081472 | elapsed time per iteration (s): 5.43 | learning rate: 3.230E-05 | global batch size: 512 | lm loss: 4.299261E+00 | loss scale: 131072.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 2823/ 3814 | consumed samples: 1445376 | consumed tokens: 2960130048 | elapsed time per iteration (s): 5.42 | learning rate: 3.224E-05 | global batch size: 512 | lm loss: 4.282902E+00 | loss scale: 131072.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.411 | TFLOPs: 71.31 | +[default7]: iteration 2824/ 3814 | consumed samples: 1445888 | consumed tokens: 2961178624 | elapsed time per iteration (s): 5.43 | learning rate: 3.218E-05 | global batch size: 512 | lm loss: 4.277958E+00 | loss scale: 131072.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.343 | TFLOPs: 71.26 | +[default7]: iteration 2825/ 3814 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 5.43 | learning rate: 3.212E-05 | global batch size: 512 | lm loss: 4.284268E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.376 | TFLOPs: 71.28 | +[default7]: iteration 2826/ 3814 | consumed samples: 1446912 | consumed tokens: 2963275776 | elapsed time per iteration (s): 5.42 | learning rate: 3.206E-05 | global batch size: 512 | lm loss: 4.284396E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.512 | TFLOPs: 71.39 | +[default7]: iteration 2827/ 3814 | consumed samples: 1447424 | consumed tokens: 2964324352 | elapsed time per iteration (s): 5.42 | learning rate: 3.200E-05 | global batch size: 512 | lm loss: 4.308878E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.450 | TFLOPs: 71.34 | +[default7]: iteration 2828/ 3814 | consumed samples: 1447936 | consumed tokens: 2965372928 | elapsed time per iteration (s): 5.41 | learning rate: 3.194E-05 | global batch size: 512 | lm loss: 4.278141E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.648 | TFLOPs: 71.49 | +[default7]: iteration 2829/ 3814 | consumed samples: 1448448 | consumed tokens: 2966421504 | elapsed time per iteration (s): 5.42 | learning rate: 3.188E-05 | global batch size: 512 | lm loss: 4.300227E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.405 | TFLOPs: 71.31 | +[default7]: iteration 2830/ 3814 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 5.43 | learning rate: 3.182E-05 | global batch size: 512 | lm loss: 4.285076E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.339 | TFLOPs: 71.26 | +[default7]: iteration 2831/ 3814 | consumed samples: 1449472 | consumed tokens: 2968518656 | elapsed time per iteration (s): 5.46 | learning rate: 3.176E-05 | global batch size: 512 | lm loss: 4.277987E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.820 | TFLOPs: 70.86 | +[default7]: iteration 2832/ 3814 | consumed samples: 1449984 | consumed tokens: 2969567232 | elapsed time per iteration (s): 5.44 | learning rate: 3.170E-05 | global batch size: 512 | lm loss: 4.284087E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.173 | TFLOPs: 71.13 | +[default7]: iteration 2833/ 3814 | consumed samples: 1450496 | consumed tokens: 2970615808 | elapsed time per iteration (s): 5.42 | learning rate: 3.164E-05 | global batch size: 512 | lm loss: 4.280537E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.525 | TFLOPs: 71.40 | +[default7]: iteration 2834/ 3814 | consumed samples: 1451008 | consumed tokens: 2971664384 | elapsed time per iteration (s): 5.42 | learning rate: 3.158E-05 | global batch size: 512 | lm loss: 4.321456E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.444 | TFLOPs: 71.33 | +[default7]: iteration 2835/ 3814 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 5.42 | learning rate: 3.152E-05 | global batch size: 512 | lm loss: 4.259799E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.404 | TFLOPs: 71.30 | +[default7]: iteration 2836/ 3814 | consumed samples: 1452032 | consumed tokens: 2973761536 | elapsed time per iteration (s): 5.42 | learning rate: 3.146E-05 | global batch size: 512 | lm loss: 4.281490E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.517 | TFLOPs: 71.39 | +[default7]: iteration 2837/ 3814 | consumed samples: 1452544 | consumed tokens: 2974810112 | elapsed time per iteration (s): 5.44 | learning rate: 3.140E-05 | global batch size: 512 | lm loss: 4.307121E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.102 | TFLOPs: 71.08 | +[default7]: iteration 2838/ 3814 | consumed samples: 1453056 | consumed tokens: 2975858688 | elapsed time per iteration (s): 5.42 | learning rate: 3.134E-05 | global batch size: 512 | lm loss: 4.244246E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.421 | TFLOPs: 71.32 | +[default7]: iteration 2839/ 3814 | consumed samples: 1453568 | consumed tokens: 2976907264 | elapsed time per iteration (s): 5.41 | learning rate: 3.128E-05 | global batch size: 512 | lm loss: 4.279039E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.573 | TFLOPs: 71.43 | +[default7]: iteration 2840/ 3814 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 5.43 | learning rate: 3.122E-05 | global batch size: 512 | lm loss: 4.268611E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.249 | TFLOPs: 71.19 | +[default7]: iteration 2841/ 3814 | consumed samples: 1454592 | consumed tokens: 2979004416 | elapsed time per iteration (s): 5.42 | learning rate: 3.116E-05 | global batch size: 512 | lm loss: 4.299666E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.517 | TFLOPs: 71.39 | +[default7]: iteration 2842/ 3814 | consumed samples: 1455104 | consumed tokens: 2980052992 | elapsed time per iteration (s): 5.41 | learning rate: 3.110E-05 | global batch size: 512 | lm loss: 4.315009E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.725 | TFLOPs: 71.55 | +[default7]: iteration 2843/ 3814 | consumed samples: 1455616 | consumed tokens: 2981101568 | elapsed time per iteration (s): 5.41 | learning rate: 3.104E-05 | global batch size: 512 | lm loss: 4.276014E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.648 | TFLOPs: 71.49 | +[default7]: iteration 2844/ 3814 | consumed samples: 1456128 | consumed tokens: 2982150144 | elapsed time per iteration (s): 5.42 | learning rate: 3.098E-05 | global batch size: 512 | lm loss: 4.272998E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.536 | TFLOPs: 71.40 | +[default7]: iteration 2845/ 3814 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 5.42 | learning rate: 3.092E-05 | global batch size: 512 | lm loss: 4.284266E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.540 | TFLOPs: 71.41 | +[default7]: iteration 2846/ 3814 | consumed samples: 1457152 | consumed tokens: 2984247296 | elapsed time per iteration (s): 5.42 | learning rate: 3.086E-05 | global batch size: 512 | lm loss: 4.259070E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.466 | TFLOPs: 71.35 | +[default7]: iteration 2847/ 3814 | consumed samples: 1457664 | consumed tokens: 2985295872 | elapsed time per iteration (s): 5.43 | learning rate: 3.080E-05 | global batch size: 512 | lm loss: 4.305408E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.276 | TFLOPs: 71.21 | +[default7]: iteration 2848/ 3814 | consumed samples: 1458176 | consumed tokens: 2986344448 | elapsed time per iteration (s): 5.41 | learning rate: 3.074E-05 | global batch size: 512 | lm loss: 4.303590E+00 | loss scale: 131072.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.578 | TFLOPs: 71.44 | +[default7]: iteration 2849/ 3814 | consumed samples: 1458688 | consumed tokens: 2987393024 | elapsed time per iteration (s): 5.41 | learning rate: 3.068E-05 | global batch size: 512 | lm loss: 4.269724E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.599 | TFLOPs: 71.45 | +[default7]: iteration 2850/ 3814 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 5.39 | learning rate: 3.062E-05 | global batch size: 512 | lm loss: 4.285622E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.908 | TFLOPs: 71.68 | +[default7]: iteration 2851/ 3814 | consumed samples: 1459712 | consumed tokens: 2989490176 | elapsed time per iteration (s): 5.40 | learning rate: 3.056E-05 | global batch size: 512 | lm loss: 4.289734E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.884 | TFLOPs: 71.67 | +[default7]: iteration 2852/ 3814 | consumed samples: 1460224 | consumed tokens: 2990538752 | elapsed time per iteration (s): 5.41 | learning rate: 3.051E-05 | global batch size: 512 | lm loss: 4.306976E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.714 | TFLOPs: 71.54 | +[default7]: iteration 2853/ 3814 | consumed samples: 1460736 | consumed tokens: 2991587328 | elapsed time per iteration (s): 5.40 | learning rate: 3.045E-05 | global batch size: 512 | lm loss: 4.272614E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.891 | TFLOPs: 71.67 | +[default7]: iteration 2854/ 3814 | consumed samples: 1461248 | consumed tokens: 2992635904 | elapsed time per iteration (s): 5.40 | learning rate: 3.039E-05 | global batch size: 512 | lm loss: 4.264388E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.790 | TFLOPs: 71.60 | +[default7]: iteration 2855/ 3814 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 5.40 | learning rate: 3.033E-05 | global batch size: 512 | lm loss: 4.288914E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.827 | TFLOPs: 71.62 | +[default7]: iteration 2856/ 3814 | consumed samples: 1462272 | consumed tokens: 2994733056 | elapsed time per iteration (s): 5.42 | learning rate: 3.027E-05 | global batch size: 512 | lm loss: 4.288289E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.390 | TFLOPs: 71.29 | +[default7]: iteration 2857/ 3814 | consumed samples: 1462784 | consumed tokens: 2995781632 | elapsed time per iteration (s): 5.41 | learning rate: 3.021E-05 | global batch size: 512 | lm loss: 4.280921E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.596 | TFLOPs: 71.45 | +[default7]: iteration 2858/ 3814 | consumed samples: 1463296 | consumed tokens: 2996830208 | elapsed time per iteration (s): 5.43 | learning rate: 3.015E-05 | global batch size: 512 | lm loss: 4.289187E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.298 | TFLOPs: 71.22 | +[default7]: iteration 2859/ 3814 | consumed samples: 1463808 | consumed tokens: 2997878784 | elapsed time per iteration (s): 5.42 | learning rate: 3.009E-05 | global batch size: 512 | lm loss: 4.306704E+00 | loss scale: 131072.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 2860/ 3814 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 5.42 | learning rate: 3.003E-05 | global batch size: 512 | lm loss: 4.300392E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.415 | TFLOPs: 71.31 | +[default7]: iteration 2861/ 3814 | consumed samples: 1464832 | consumed tokens: 2999975936 | elapsed time per iteration (s): 5.41 | learning rate: 2.997E-05 | global batch size: 512 | lm loss: 4.303450E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.601 | TFLOPs: 71.45 | +[default7]: iteration 2862/ 3814 | consumed samples: 1465344 | consumed tokens: 3001024512 | elapsed time per iteration (s): 5.45 | learning rate: 2.991E-05 | global batch size: 512 | lm loss: 4.238159E+00 | loss scale: 131072.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.999 | TFLOPs: 71.00 | +[default7]: iteration 2863/ 3814 | consumed samples: 1465856 | consumed tokens: 3002073088 | elapsed time per iteration (s): 5.43 | learning rate: 2.986E-05 | global batch size: 512 | lm loss: 4.292925E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.361 | TFLOPs: 71.27 | +[default7]: iteration 2864/ 3814 | consumed samples: 1466368 | consumed tokens: 3003121664 | elapsed time per iteration (s): 5.43 | learning rate: 2.980E-05 | global batch size: 512 | lm loss: 4.274695E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.232 | TFLOPs: 71.17 | +[default7]: iteration 2865/ 3814 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 5.45 | learning rate: 2.974E-05 | global batch size: 512 | lm loss: 4.302177E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.024 | TFLOPs: 71.02 | +[default7]: iteration 2866/ 3814 | consumed samples: 1467392 | consumed tokens: 3005218816 | elapsed time per iteration (s): 5.44 | learning rate: 2.968E-05 | global batch size: 512 | lm loss: 4.277898E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.110 | TFLOPs: 71.08 | +[default7]: iteration 2867/ 3814 | consumed samples: 1467904 | consumed tokens: 3006267392 | elapsed time per iteration (s): 5.44 | learning rate: 2.962E-05 | global batch size: 512 | lm loss: 4.300302E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.093 | TFLOPs: 71.07 | +[default7]: iteration 2868/ 3814 | consumed samples: 1468416 | consumed tokens: 3007315968 | elapsed time per iteration (s): 5.43 | learning rate: 2.956E-05 | global batch size: 512 | lm loss: 4.260608E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.331 | TFLOPs: 71.25 | +[default7]: iteration 2869/ 3814 | consumed samples: 1468928 | consumed tokens: 3008364544 | elapsed time per iteration (s): 5.41 | learning rate: 2.950E-05 | global batch size: 512 | lm loss: 4.268040E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.622 | TFLOPs: 71.47 | +[default7]: iteration 2870/ 3814 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 5.43 | learning rate: 2.945E-05 | global batch size: 512 | lm loss: 4.266588E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.251 | TFLOPs: 71.19 | +[default7]: iteration 2871/ 3814 | consumed samples: 1469952 | consumed tokens: 3010461696 | elapsed time per iteration (s): 5.45 | learning rate: 2.939E-05 | global batch size: 512 | lm loss: 4.278053E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.948 | TFLOPs: 70.96 | +[default7]: iteration 2872/ 3814 | consumed samples: 1470464 | consumed tokens: 3011510272 | elapsed time per iteration (s): 5.44 | learning rate: 2.933E-05 | global batch size: 512 | lm loss: 4.274462E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.131 | TFLOPs: 71.10 | +[default7]: iteration 2873/ 3814 | consumed samples: 1470976 | consumed tokens: 3012558848 | elapsed time per iteration (s): 5.44 | learning rate: 2.927E-05 | global batch size: 512 | lm loss: 4.305414E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.090 | TFLOPs: 71.07 | +[default7]: iteration 2874/ 3814 | consumed samples: 1471488 | consumed tokens: 3013607424 | elapsed time per iteration (s): 5.43 | learning rate: 2.921E-05 | global batch size: 512 | lm loss: 4.293534E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.215 | TFLOPs: 71.16 | +[default7]: iteration 2875/ 3814 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 5.44 | learning rate: 2.915E-05 | global batch size: 512 | lm loss: 4.291139E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.180 | TFLOPs: 71.14 | +[default7]: iteration 2876/ 3814 | consumed samples: 1472512 | consumed tokens: 3015704576 | elapsed time per iteration (s): 5.44 | learning rate: 2.910E-05 | global batch size: 512 | lm loss: 4.300611E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 2877/ 3814 | consumed samples: 1473024 | consumed tokens: 3016753152 | elapsed time per iteration (s): 5.44 | learning rate: 2.904E-05 | global batch size: 512 | lm loss: 4.287813E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.156 | TFLOPs: 71.12 | +[default7]: iteration 2878/ 3814 | consumed samples: 1473536 | consumed tokens: 3017801728 | elapsed time per iteration (s): 5.43 | learning rate: 2.898E-05 | global batch size: 512 | lm loss: 4.287005E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.234 | TFLOPs: 71.18 | +[default7]: iteration 2879/ 3814 | consumed samples: 1474048 | consumed tokens: 3018850304 | elapsed time per iteration (s): 5.44 | learning rate: 2.892E-05 | global batch size: 512 | lm loss: 4.253746E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.163 | TFLOPs: 71.12 | +[default7]: iteration 2880/ 3814 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 5.44 | learning rate: 2.886E-05 | global batch size: 512 | lm loss: 4.284550E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.108 | TFLOPs: 71.08 | +[default7]: iteration 2881/ 3814 | consumed samples: 1475072 | consumed tokens: 3020947456 | elapsed time per iteration (s): 5.42 | learning rate: 2.881E-05 | global batch size: 512 | lm loss: 4.297827E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 2882/ 3814 | consumed samples: 1475584 | consumed tokens: 3021996032 | elapsed time per iteration (s): 5.43 | learning rate: 2.875E-05 | global batch size: 512 | lm loss: 4.275794E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.240 | TFLOPs: 71.18 | +[default7]: iteration 2883/ 3814 | consumed samples: 1476096 | consumed tokens: 3023044608 | elapsed time per iteration (s): 5.44 | learning rate: 2.869E-05 | global batch size: 512 | lm loss: 4.286555E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.143 | TFLOPs: 71.11 | +[default7]: iteration 2884/ 3814 | consumed samples: 1476608 | consumed tokens: 3024093184 | elapsed time per iteration (s): 5.45 | learning rate: 2.863E-05 | global batch size: 512 | lm loss: 4.283647E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.875 | TFLOPs: 70.90 | +[default7]: iteration 2885/ 3814 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 5.45 | learning rate: 2.857E-05 | global batch size: 512 | lm loss: 4.268642E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.958 | TFLOPs: 70.97 | +[default7]: iteration 2886/ 3814 | consumed samples: 1477632 | consumed tokens: 3026190336 | elapsed time per iteration (s): 5.44 | learning rate: 2.852E-05 | global batch size: 512 | lm loss: 4.239190E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.158 | TFLOPs: 71.12 | +[default7]: iteration 2887/ 3814 | consumed samples: 1478144 | consumed tokens: 3027238912 | elapsed time per iteration (s): 5.45 | learning rate: 2.846E-05 | global batch size: 512 | lm loss: 4.298935E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.006 | TFLOPs: 71.00 | +[default7]: iteration 2888/ 3814 | consumed samples: 1478656 | consumed tokens: 3028287488 | elapsed time per iteration (s): 5.43 | learning rate: 2.840E-05 | global batch size: 512 | lm loss: 4.279217E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.245 | TFLOPs: 71.18 | +[default7]: iteration 2889/ 3814 | consumed samples: 1479168 | consumed tokens: 3029336064 | elapsed time per iteration (s): 5.43 | learning rate: 2.834E-05 | global batch size: 512 | lm loss: 4.275589E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.229 | TFLOPs: 71.17 | +[default7]: iteration 2890/ 3814 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 5.42 | learning rate: 2.829E-05 | global batch size: 512 | lm loss: 4.272220E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.400 | TFLOPs: 71.30 | +[default7]: iteration 2891/ 3814 | consumed samples: 1480192 | consumed tokens: 3031433216 | elapsed time per iteration (s): 5.43 | learning rate: 2.823E-05 | global batch size: 512 | lm loss: 4.271278E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.223 | TFLOPs: 71.17 | +[default7]: iteration 2892/ 3814 | consumed samples: 1480704 | consumed tokens: 3032481792 | elapsed time per iteration (s): 5.43 | learning rate: 2.817E-05 | global batch size: 512 | lm loss: 4.286632E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 2893/ 3814 | consumed samples: 1481216 | consumed tokens: 3033530368 | elapsed time per iteration (s): 5.45 | learning rate: 2.811E-05 | global batch size: 512 | lm loss: 4.244622E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.974 | TFLOPs: 70.98 | +[default7]: iteration 2894/ 3814 | consumed samples: 1481728 | consumed tokens: 3034578944 | elapsed time per iteration (s): 5.44 | learning rate: 2.806E-05 | global batch size: 512 | lm loss: 4.324296E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.151 | TFLOPs: 71.11 | +[default7]: iteration 2895/ 3814 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 5.44 | learning rate: 2.800E-05 | global batch size: 512 | lm loss: 4.287010E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.116 | TFLOPs: 71.09 | +[default7]: iteration 2896/ 3814 | consumed samples: 1482752 | consumed tokens: 3036676096 | elapsed time per iteration (s): 5.44 | learning rate: 2.794E-05 | global batch size: 512 | lm loss: 4.286391E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.083 | TFLOPs: 71.06 | +[default7]: iteration 2897/ 3814 | consumed samples: 1483264 | consumed tokens: 3037724672 | elapsed time per iteration (s): 5.43 | learning rate: 2.788E-05 | global batch size: 512 | lm loss: 4.298704E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.243 | TFLOPs: 71.18 | +[default7]: iteration 2898/ 3814 | consumed samples: 1483776 | consumed tokens: 3038773248 | elapsed time per iteration (s): 5.45 | learning rate: 2.783E-05 | global batch size: 512 | lm loss: 4.264181E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.965 | TFLOPs: 70.97 | +[default7]: iteration 2899/ 3814 | consumed samples: 1484288 | consumed tokens: 3039821824 | elapsed time per iteration (s): 5.44 | learning rate: 2.777E-05 | global batch size: 512 | lm loss: 4.293204E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.095 | TFLOPs: 71.07 | +[default7]: iteration 2900/ 3814 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 5.46 | learning rate: 2.771E-05 | global batch size: 512 | lm loss: 4.261909E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.803 | TFLOPs: 70.85 | +[default7]: iteration 2901/ 3814 | consumed samples: 1485312 | consumed tokens: 3041918976 | elapsed time per iteration (s): 5.43 | learning rate: 2.766E-05 | global batch size: 512 | lm loss: 4.281861E+00 | loss scale: 131072.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.294 | TFLOPs: 71.22 | +[default7]: iteration 2902/ 3814 | consumed samples: 1485824 | consumed tokens: 3042967552 | elapsed time per iteration (s): 5.44 | learning rate: 2.760E-05 | global batch size: 512 | lm loss: 4.280797E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.160 | TFLOPs: 71.12 | +[default7]: iteration 2903/ 3814 | consumed samples: 1486336 | consumed tokens: 3044016128 | elapsed time per iteration (s): 5.44 | learning rate: 2.754E-05 | global batch size: 512 | lm loss: 4.272460E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.056 | TFLOPs: 71.04 | +[default7]: iteration 2904/ 3814 | consumed samples: 1486848 | consumed tokens: 3045064704 | elapsed time per iteration (s): 5.44 | learning rate: 2.748E-05 | global batch size: 512 | lm loss: 4.275703E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.084 | TFLOPs: 71.06 | +[default7]: iteration 2905/ 3814 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 5.43 | learning rate: 2.743E-05 | global batch size: 512 | lm loss: 4.281317E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.321 | TFLOPs: 71.24 | +[default7]: iteration 2906/ 3814 | consumed samples: 1487872 | consumed tokens: 3047161856 | elapsed time per iteration (s): 5.44 | learning rate: 2.737E-05 | global batch size: 512 | lm loss: 4.264316E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.169 | TFLOPs: 71.13 | +[default7]: iteration 2907/ 3814 | consumed samples: 1488384 | consumed tokens: 3048210432 | elapsed time per iteration (s): 5.44 | learning rate: 2.731E-05 | global batch size: 512 | lm loss: 4.301914E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.119 | TFLOPs: 71.09 | +[default7]: iteration 2908/ 3814 | consumed samples: 1488896 | consumed tokens: 3049259008 | elapsed time per iteration (s): 5.44 | learning rate: 2.726E-05 | global batch size: 512 | lm loss: 4.313475E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.166 | TFLOPs: 71.12 | +[default7]: iteration 2909/ 3814 | consumed samples: 1489408 | consumed tokens: 3050307584 | elapsed time per iteration (s): 5.43 | learning rate: 2.720E-05 | global batch size: 512 | lm loss: 4.280178E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.257 | TFLOPs: 71.19 | +[default7]: iteration 2910/ 3814 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 5.43 | learning rate: 2.714E-05 | global batch size: 512 | lm loss: 4.266877E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.259 | TFLOPs: 71.19 | +[default7]: iteration 2911/ 3814 | consumed samples: 1490432 | consumed tokens: 3052404736 | elapsed time per iteration (s): 5.43 | learning rate: 2.709E-05 | global batch size: 512 | lm loss: 4.269889E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.334 | TFLOPs: 71.25 | +[default7]: iteration 2912/ 3814 | consumed samples: 1490944 | consumed tokens: 3053453312 | elapsed time per iteration (s): 5.42 | learning rate: 2.703E-05 | global batch size: 512 | lm loss: 4.282136E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.460 | TFLOPs: 71.35 | +[default7]: iteration 2913/ 3814 | consumed samples: 1491456 | consumed tokens: 3054501888 | elapsed time per iteration (s): 5.45 | learning rate: 2.697E-05 | global batch size: 512 | lm loss: 4.289632E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.991 | TFLOPs: 70.99 | +[default7]: iteration 2914/ 3814 | consumed samples: 1491968 | consumed tokens: 3055550464 | elapsed time per iteration (s): 5.44 | learning rate: 2.692E-05 | global batch size: 512 | lm loss: 4.264623E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.202 | TFLOPs: 71.15 | +[default7]: iteration 2915/ 3814 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 5.46 | learning rate: 2.686E-05 | global batch size: 512 | lm loss: 4.262367E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.758 | TFLOPs: 70.82 | +[default7]: iteration 2916/ 3814 | consumed samples: 1492992 | consumed tokens: 3057647616 | elapsed time per iteration (s): 5.49 | learning rate: 2.681E-05 | global batch size: 512 | lm loss: 4.272111E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.232 | TFLOPs: 70.42 | +[default7]: iteration 2917/ 3814 | consumed samples: 1493504 | consumed tokens: 3058696192 | elapsed time per iteration (s): 5.44 | learning rate: 2.675E-05 | global batch size: 512 | lm loss: 4.281574E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.175 | TFLOPs: 71.13 | +[default7]: iteration 2918/ 3814 | consumed samples: 1494016 | consumed tokens: 3059744768 | elapsed time per iteration (s): 5.42 | learning rate: 2.669E-05 | global batch size: 512 | lm loss: 4.266261E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.460 | TFLOPs: 71.35 | +[default7]: iteration 2919/ 3814 | consumed samples: 1494528 | consumed tokens: 3060793344 | elapsed time per iteration (s): 5.43 | learning rate: 2.664E-05 | global batch size: 512 | lm loss: 4.280309E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.213 | TFLOPs: 71.16 | +[default7]: iteration 2920/ 3814 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 5.44 | learning rate: 2.658E-05 | global batch size: 512 | lm loss: 4.254167E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 2921/ 3814 | consumed samples: 1495552 | consumed tokens: 3062890496 | elapsed time per iteration (s): 5.43 | learning rate: 2.652E-05 | global batch size: 512 | lm loss: 4.304318E+00 | loss scale: 131072.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.263 | TFLOPs: 71.20 | +[default7]: iteration 2922/ 3814 | consumed samples: 1496064 | consumed tokens: 3063939072 | elapsed time per iteration (s): 5.44 | learning rate: 2.647E-05 | global batch size: 512 | lm loss: 4.287164E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.157 | TFLOPs: 71.12 | +[default7]: iteration 2923/ 3814 | consumed samples: 1496576 | consumed tokens: 3064987648 | elapsed time per iteration (s): 5.43 | learning rate: 2.641E-05 | global batch size: 512 | lm loss: 4.290808E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.234 | TFLOPs: 71.18 | +[default7]: iteration 2924/ 3814 | consumed samples: 1497088 | consumed tokens: 3066036224 | elapsed time per iteration (s): 5.44 | learning rate: 2.636E-05 | global batch size: 512 | lm loss: 4.284307E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.184 | TFLOPs: 71.14 | +[default7]: iteration 2925/ 3814 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 5.45 | learning rate: 2.630E-05 | global batch size: 512 | lm loss: 4.258744E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.031 | TFLOPs: 71.02 | +[default7]: iteration 2926/ 3814 | consumed samples: 1498112 | consumed tokens: 3068133376 | elapsed time per iteration (s): 5.43 | learning rate: 2.624E-05 | global batch size: 512 | lm loss: 4.246668E+00 | loss scale: 131072.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.318 | TFLOPs: 71.24 | +[default7]: iteration 2927/ 3814 | consumed samples: 1498624 | consumed tokens: 3069181952 | elapsed time per iteration (s): 5.44 | learning rate: 2.619E-05 | global batch size: 512 | lm loss: 4.281431E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.074 | TFLOPs: 71.05 | +[default7]: iteration 2928/ 3814 | consumed samples: 1499136 | consumed tokens: 3070230528 | elapsed time per iteration (s): 5.44 | learning rate: 2.613E-05 | global batch size: 512 | lm loss: 4.245584E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.113 | TFLOPs: 71.08 | +[default7]: iteration 2929/ 3814 | consumed samples: 1499648 | consumed tokens: 3071279104 | elapsed time per iteration (s): 5.42 | learning rate: 2.608E-05 | global batch size: 512 | lm loss: 4.284946E+00 | loss scale: 131072.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.482 | TFLOPs: 71.36 | +[default7]: iteration 2930/ 3814 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 5.44 | learning rate: 2.602E-05 | global batch size: 512 | lm loss: 4.266030E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default7]: iteration 2931/ 3814 | consumed samples: 1500672 | consumed tokens: 3073376256 | elapsed time per iteration (s): 5.44 | learning rate: 2.597E-05 | global batch size: 512 | lm loss: 4.244349E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.059 | TFLOPs: 71.04 | +[default7]: iteration 2932/ 3814 | consumed samples: 1501184 | consumed tokens: 3074424832 | elapsed time per iteration (s): 5.42 | learning rate: 2.591E-05 | global batch size: 512 | lm loss: 4.306656E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.440 | TFLOPs: 71.33 | +[default7]: iteration 2933/ 3814 | consumed samples: 1501696 | consumed tokens: 3075473408 | elapsed time per iteration (s): 5.42 | learning rate: 2.586E-05 | global batch size: 512 | lm loss: 4.261182E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.399 | TFLOPs: 71.30 | +[default7]: iteration 2934/ 3814 | consumed samples: 1502208 | consumed tokens: 3076521984 | elapsed time per iteration (s): 5.43 | learning rate: 2.580E-05 | global batch size: 512 | lm loss: 4.264377E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.228 | TFLOPs: 71.17 | +[default7]: iteration 2935/ 3814 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 5.42 | learning rate: 2.574E-05 | global batch size: 512 | lm loss: 4.283895E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.499 | TFLOPs: 71.38 | +[default7]: iteration 2936/ 3814 | consumed samples: 1503232 | consumed tokens: 3078619136 | elapsed time per iteration (s): 5.45 | learning rate: 2.569E-05 | global batch size: 512 | lm loss: 4.252832E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.989 | TFLOPs: 70.99 | +[default7]: iteration 2937/ 3814 | consumed samples: 1503744 | consumed tokens: 3079667712 | elapsed time per iteration (s): 5.43 | learning rate: 2.563E-05 | global batch size: 512 | lm loss: 4.248567E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.219 | TFLOPs: 71.16 | +[default7]: iteration 2938/ 3814 | consumed samples: 1504256 | consumed tokens: 3080716288 | elapsed time per iteration (s): 5.43 | learning rate: 2.558E-05 | global batch size: 512 | lm loss: 4.277197E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.231 | TFLOPs: 71.17 | +[default7]: iteration 2939/ 3814 | consumed samples: 1504768 | consumed tokens: 3081764864 | elapsed time per iteration (s): 5.46 | learning rate: 2.552E-05 | global batch size: 512 | lm loss: 4.278872E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.800 | TFLOPs: 70.85 | +[default7]: iteration 2940/ 3814 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 5.45 | learning rate: 2.547E-05 | global batch size: 512 | lm loss: 4.273686E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.946 | TFLOPs: 70.96 | +[default7]: iteration 2941/ 3814 | consumed samples: 1505792 | consumed tokens: 3083862016 | elapsed time per iteration (s): 5.45 | learning rate: 2.541E-05 | global batch size: 512 | lm loss: 4.254651E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.987 | TFLOPs: 70.99 | +[default7]: iteration 2942/ 3814 | consumed samples: 1506304 | consumed tokens: 3084910592 | elapsed time per iteration (s): 5.44 | learning rate: 2.536E-05 | global batch size: 512 | lm loss: 4.251768E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 2943/ 3814 | consumed samples: 1506816 | consumed tokens: 3085959168 | elapsed time per iteration (s): 5.43 | learning rate: 2.530E-05 | global batch size: 512 | lm loss: 4.285837E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.238 | TFLOPs: 71.18 | +[default7]: iteration 2944/ 3814 | consumed samples: 1507328 | consumed tokens: 3087007744 | elapsed time per iteration (s): 5.45 | learning rate: 2.525E-05 | global batch size: 512 | lm loss: 4.248358E+00 | loss scale: 131072.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.944 | TFLOPs: 70.96 | +[default7]: iteration 2945/ 3814 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 5.45 | learning rate: 2.519E-05 | global batch size: 512 | lm loss: 4.265453E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.884 | TFLOPs: 70.91 | +[default7]: iteration 2946/ 3814 | consumed samples: 1508352 | consumed tokens: 3089104896 | elapsed time per iteration (s): 5.46 | learning rate: 2.514E-05 | global batch size: 512 | lm loss: 4.246735E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.838 | TFLOPs: 70.88 | +[default7]: iteration 2947/ 3814 | consumed samples: 1508864 | consumed tokens: 3090153472 | elapsed time per iteration (s): 5.47 | learning rate: 2.508E-05 | global batch size: 512 | lm loss: 4.268039E+00 | loss scale: 131072.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.536 | TFLOPs: 70.65 | +[default7]: iteration 2948/ 3814 | consumed samples: 1509376 | consumed tokens: 3091202048 | elapsed time per iteration (s): 5.45 | learning rate: 2.503E-05 | global batch size: 512 | lm loss: 4.302335E+00 | loss scale: 131072.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.886 | TFLOPs: 70.91 | +[default7]: iteration 2949/ 3814 | consumed samples: 1509888 | consumed tokens: 3092250624 | elapsed time per iteration (s): 5.47 | learning rate: 2.497E-05 | global batch size: 512 | lm loss: 4.255189E+00 | loss scale: 131072.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.655 | TFLOPs: 70.74 | +[default7]: iteration 2950/ 3814 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 5.45 | learning rate: 2.492E-05 | global batch size: 512 | lm loss: 4.282394E+00 | loss scale: 131072.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.867 | TFLOPs: 70.90 | +[default7]: iteration 2951/ 3814 | consumed samples: 1510912 | consumed tokens: 3094347776 | elapsed time per iteration (s): 5.46 | learning rate: 2.486E-05 | global batch size: 512 | lm loss: 4.272745E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.855 | TFLOPs: 70.89 | +[default7]: iteration 2952/ 3814 | consumed samples: 1511424 | consumed tokens: 3095396352 | elapsed time per iteration (s): 5.42 | learning rate: 2.481E-05 | global batch size: 512 | lm loss: 4.276521E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.434 | TFLOPs: 71.33 | +[default7]: iteration 2953/ 3814 | consumed samples: 1511936 | consumed tokens: 3096444928 | elapsed time per iteration (s): 5.43 | learning rate: 2.476E-05 | global batch size: 512 | lm loss: 4.314520E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.261 | TFLOPs: 71.20 | +[default7]: iteration 2954/ 3814 | consumed samples: 1512448 | consumed tokens: 3097493504 | elapsed time per iteration (s): 5.43 | learning rate: 2.470E-05 | global batch size: 512 | lm loss: 4.256653E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.327 | TFLOPs: 71.25 | +[default7]: iteration 2955/ 3814 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 5.43 | learning rate: 2.465E-05 | global batch size: 512 | lm loss: 4.285296E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.294 | TFLOPs: 71.22 | +[default7]: iteration 2956/ 3814 | consumed samples: 1513472 | consumed tokens: 3099590656 | elapsed time per iteration (s): 5.43 | learning rate: 2.459E-05 | global batch size: 512 | lm loss: 4.262030E+00 | loss scale: 131072.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.352 | TFLOPs: 71.26 | +[default7]: iteration 2957/ 3814 | consumed samples: 1513984 | consumed tokens: 3100639232 | elapsed time per iteration (s): 5.43 | learning rate: 2.454E-05 | global batch size: 512 | lm loss: 4.243955E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 2958/ 3814 | consumed samples: 1514496 | consumed tokens: 3101687808 | elapsed time per iteration (s): 5.43 | learning rate: 2.448E-05 | global batch size: 512 | lm loss: 4.267852E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 2959/ 3814 | consumed samples: 1515008 | consumed tokens: 3102736384 | elapsed time per iteration (s): 5.45 | learning rate: 2.443E-05 | global batch size: 512 | lm loss: 4.282774E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.870 | TFLOPs: 70.90 | +[default7]: iteration 2960/ 3814 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 5.43 | learning rate: 2.438E-05 | global batch size: 512 | lm loss: 4.279905E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.301 | TFLOPs: 71.23 | +[default7]: iteration 2961/ 3814 | consumed samples: 1516032 | consumed tokens: 3104833536 | elapsed time per iteration (s): 5.48 | learning rate: 2.432E-05 | global batch size: 512 | lm loss: 4.243757E+00 | loss scale: 131072.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.502 | TFLOPs: 70.62 | +[default7]: iteration 2962/ 3814 | consumed samples: 1516544 | consumed tokens: 3105882112 | elapsed time per iteration (s): 5.44 | learning rate: 2.427E-05 | global batch size: 512 | lm loss: 4.263619E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.071 | TFLOPs: 71.05 | +[default7]: iteration 2963/ 3814 | consumed samples: 1517056 | consumed tokens: 3106930688 | elapsed time per iteration (s): 5.44 | learning rate: 2.421E-05 | global batch size: 512 | lm loss: 4.263507E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.096 | TFLOPs: 71.07 | +[default7]: iteration 2964/ 3814 | consumed samples: 1517568 | consumed tokens: 3107979264 | elapsed time per iteration (s): 5.42 | learning rate: 2.416E-05 | global batch size: 512 | lm loss: 4.285243E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.457 | TFLOPs: 71.34 | +[default7]: iteration 2965/ 3814 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 5.43 | learning rate: 2.411E-05 | global batch size: 512 | lm loss: 4.256511E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.212 | TFLOPs: 71.16 | +[default7]: iteration 2966/ 3814 | consumed samples: 1518592 | consumed tokens: 3110076416 | elapsed time per iteration (s): 5.44 | learning rate: 2.405E-05 | global batch size: 512 | lm loss: 4.302902E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.147 | TFLOPs: 71.11 | +[default7]: iteration 2967/ 3814 | consumed samples: 1519104 | consumed tokens: 3111124992 | elapsed time per iteration (s): 5.44 | learning rate: 2.400E-05 | global batch size: 512 | lm loss: 4.275831E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.195 | TFLOPs: 71.15 | +[default7]: iteration 2968/ 3814 | consumed samples: 1519616 | consumed tokens: 3112173568 | elapsed time per iteration (s): 5.43 | learning rate: 2.394E-05 | global batch size: 512 | lm loss: 4.282134E+00 | loss scale: 131072.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.357 | TFLOPs: 71.27 | +[default7]: iteration 2969/ 3814 | consumed samples: 1520128 | consumed tokens: 3113222144 | elapsed time per iteration (s): 5.43 | learning rate: 2.389E-05 | global batch size: 512 | lm loss: 4.273302E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.341 | TFLOPs: 71.26 | +[default7]: iteration 2970/ 3814 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 5.42 | learning rate: 2.384E-05 | global batch size: 512 | lm loss: 4.246861E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.426 | TFLOPs: 71.32 | +[default7]: iteration 2971/ 3814 | consumed samples: 1521152 | consumed tokens: 3115319296 | elapsed time per iteration (s): 5.41 | learning rate: 2.378E-05 | global batch size: 512 | lm loss: 4.265827E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.613 | TFLOPs: 71.46 | +[default7]: iteration 2972/ 3814 | consumed samples: 1521664 | consumed tokens: 3116367872 | elapsed time per iteration (s): 5.41 | learning rate: 2.373E-05 | global batch size: 512 | lm loss: 4.255383E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.681 | TFLOPs: 71.51 | +[default7]: iteration 2973/ 3814 | consumed samples: 1522176 | consumed tokens: 3117416448 | elapsed time per iteration (s): 5.43 | learning rate: 2.368E-05 | global batch size: 512 | lm loss: 4.259096E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.376 | TFLOPs: 71.28 | +[default7]: iteration 2974/ 3814 | consumed samples: 1522688 | consumed tokens: 3118465024 | elapsed time per iteration (s): 5.43 | learning rate: 2.362E-05 | global batch size: 512 | lm loss: 4.276221E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.338 | TFLOPs: 71.25 | +[default7]: iteration 2975/ 3814 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 5.46 | learning rate: 2.357E-05 | global batch size: 512 | lm loss: 4.263885E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.853 | TFLOPs: 70.89 | +[default7]: iteration 2976/ 3814 | consumed samples: 1523712 | consumed tokens: 3120562176 | elapsed time per iteration (s): 5.43 | learning rate: 2.352E-05 | global batch size: 512 | lm loss: 4.277803E+00 | loss scale: 131072.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.275 | TFLOPs: 71.21 | +[default7]: iteration 2977/ 3814 | consumed samples: 1524224 | consumed tokens: 3121610752 | elapsed time per iteration (s): 5.44 | learning rate: 2.346E-05 | global batch size: 512 | lm loss: 4.241909E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.174 | TFLOPs: 71.13 | +[default7]: iteration 2978/ 3814 | consumed samples: 1524736 | consumed tokens: 3122659328 | elapsed time per iteration (s): 5.45 | learning rate: 2.341E-05 | global batch size: 512 | lm loss: 4.239992E+00 | loss scale: 131072.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.998 | TFLOPs: 71.00 | +[default7]: iteration 2979/ 3814 | consumed samples: 1525248 | consumed tokens: 3123707904 | elapsed time per iteration (s): 5.42 | learning rate: 2.336E-05 | global batch size: 512 | lm loss: 4.298213E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.428 | TFLOPs: 71.32 | +[default7]: iteration 2980/ 3814 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 5.40 | learning rate: 2.330E-05 | global batch size: 512 | lm loss: 4.266277E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.738 | TFLOPs: 71.56 | +[default7]: iteration 2981/ 3814 | consumed samples: 1526272 | consumed tokens: 3125805056 | elapsed time per iteration (s): 5.42 | learning rate: 2.325E-05 | global batch size: 512 | lm loss: 4.277794E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.453 | TFLOPs: 71.34 | +[default7]: iteration 2982/ 3814 | consumed samples: 1526784 | consumed tokens: 3126853632 | elapsed time per iteration (s): 5.43 | learning rate: 2.320E-05 | global batch size: 512 | lm loss: 4.247940E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 2983/ 3814 | consumed samples: 1527296 | consumed tokens: 3127902208 | elapsed time per iteration (s): 5.42 | learning rate: 2.314E-05 | global batch size: 512 | lm loss: 4.296180E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.448 | TFLOPs: 71.34 | +[default7]: iteration 2984/ 3814 | consumed samples: 1527808 | consumed tokens: 3128950784 | elapsed time per iteration (s): 5.42 | learning rate: 2.309E-05 | global batch size: 512 | lm loss: 4.256469E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.432 | TFLOPs: 71.33 | +[default7]: iteration 2985/ 3814 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 5.43 | learning rate: 2.304E-05 | global batch size: 512 | lm loss: 4.271310E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.309 | TFLOPs: 71.23 | +[default7]: iteration 2986/ 3814 | consumed samples: 1528832 | consumed tokens: 3131047936 | elapsed time per iteration (s): 5.44 | learning rate: 2.298E-05 | global batch size: 512 | lm loss: 4.262430E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.134 | TFLOPs: 71.10 | +[default7]: iteration 2987/ 3814 | consumed samples: 1529344 | consumed tokens: 3132096512 | elapsed time per iteration (s): 5.42 | learning rate: 2.293E-05 | global batch size: 512 | lm loss: 4.254669E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.424 | TFLOPs: 71.32 | +[default7]: iteration 2988/ 3814 | consumed samples: 1529856 | consumed tokens: 3133145088 | elapsed time per iteration (s): 5.43 | learning rate: 2.288E-05 | global batch size: 512 | lm loss: 4.235205E+00 | loss scale: 131072.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.286 | TFLOPs: 71.22 | +[default7]: iteration 2989/ 3814 | consumed samples: 1530368 | consumed tokens: 3134193664 | elapsed time per iteration (s): 5.42 | learning rate: 2.283E-05 | global batch size: 512 | lm loss: 4.281855E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.430 | TFLOPs: 71.32 | +[default7]: iteration 2990/ 3814 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 5.43 | learning rate: 2.277E-05 | global batch size: 512 | lm loss: 4.286702E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.259 | TFLOPs: 71.19 | +[default7]: iteration 2991/ 3814 | consumed samples: 1531392 | consumed tokens: 3136290816 | elapsed time per iteration (s): 5.43 | learning rate: 2.272E-05 | global batch size: 512 | lm loss: 4.257583E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.237 | TFLOPs: 71.18 | +[default7]: iteration 2992/ 3814 | consumed samples: 1531904 | consumed tokens: 3137339392 | elapsed time per iteration (s): 5.43 | learning rate: 2.267E-05 | global batch size: 512 | lm loss: 4.277644E+00 | loss scale: 131072.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.335 | TFLOPs: 71.25 | +[default7]: iteration 2993/ 3814 | consumed samples: 1532416 | consumed tokens: 3138387968 | elapsed time per iteration (s): 5.42 | learning rate: 2.262E-05 | global batch size: 512 | lm loss: 4.255097E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.552 | TFLOPs: 71.42 | +[default7]: iteration 2994/ 3814 | consumed samples: 1532928 | consumed tokens: 3139436544 | elapsed time per iteration (s): 5.43 | learning rate: 2.256E-05 | global batch size: 512 | lm loss: 4.283978E+00 | loss scale: 131072.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.292 | TFLOPs: 71.22 | +[default7]: iteration 2995/ 3814 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 5.43 | learning rate: 2.251E-05 | global batch size: 512 | lm loss: 4.250919E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.267 | TFLOPs: 71.20 | +[default7]: iteration 2996/ 3814 | consumed samples: 1533952 | consumed tokens: 3141533696 | elapsed time per iteration (s): 5.44 | learning rate: 2.246E-05 | global batch size: 512 | lm loss: 4.272189E+00 | loss scale: 131072.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.152 | TFLOPs: 71.11 | +[default7]: iteration 2997/ 3814 | consumed samples: 1534464 | consumed tokens: 3142582272 | elapsed time per iteration (s): 5.42 | learning rate: 2.241E-05 | global batch size: 512 | lm loss: 4.229354E+00 | loss scale: 131072.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.412 | TFLOPs: 71.31 | +[default7]: iteration 2998/ 3814 | consumed samples: 1534976 | consumed tokens: 3143630848 | elapsed time per iteration (s): 5.43 | learning rate: 2.235E-05 | global batch size: 512 | lm loss: 4.256424E+00 | loss scale: 131072.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.211 | TFLOPs: 71.16 | +[default7]: iteration 2999/ 3814 | consumed samples: 1535488 | consumed tokens: 3144679424 | elapsed time per iteration (s): 5.43 | learning rate: 2.230E-05 | global batch size: 512 | lm loss: 4.267265E+00 | loss scale: 131072.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.363 | TFLOPs: 71.27 | +[default7]: iteration 3000/ 3814 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 5.44 | learning rate: 2.225E-05 | global batch size: 512 | lm loss: 4.273977E+00 | loss scale: 262144.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.122 | TFLOPs: 71.09 | +[default0]:saving checkpoint at iteration 3000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 15:52:22,707] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! +[default0]:[2023-02-16 15:52:22,710] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:22,710] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_01-model_01-model_states.pt... +[default7]:------------------------------------------------------------------------------------------ +[default7]:valid loss at iteration 3000 | lm loss value: 4.206972E+00 | lm loss PPL: 6.715287E+01 | +[default7]:------------------------------------------------------------------------------------------ +[default0]:[2023-02-16 15:52:22,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:22,876] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:22,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:22,880] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:22,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:22,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:22,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:22,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:22,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:22,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,004] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,068] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:23,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,129] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,183] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,304] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,256] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:23,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,315] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:23,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,448] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,489] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,551] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:23,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,798] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,760] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:23,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,832] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,893] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:23,932] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,932] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:23,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:23,991] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:23,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:23,952] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,019] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,057] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,078] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,138] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,204] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,242] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,313] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,512] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,537] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,634] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,693] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 15:52:24,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 15:52:24,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,874] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 15:52:24,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 15:52:24,876] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_00_model_states.pt +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,876] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 15:52:24,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_00_model_states.pt. +[default1]:[2023-02-16 15:52:24,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 15:52:24,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 15:52:24,906] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_01_model_states.pt +[default1]:[2023-02-16 15:52:24,906] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 15:52:24,908] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 15:52:24,941] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 15:52:25,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,448] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,437] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,433] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,479] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,481] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,529] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,532] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,473] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,524] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,550] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,496] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,569] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,590] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,599] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,549] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,582] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,611] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,623] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,586] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,593] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,634] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,611] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,635] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,560] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,635] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,607] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,628] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,640] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,604] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,655] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,599] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,609] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,566] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,584] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,632] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,591] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,667] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,612] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,642] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,624] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,587] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,603] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,693] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,617] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,682] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,638] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,665] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default2]:[2023-02-16 15:52:25,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 15:52:25,699] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 15:52:25,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,685] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,653] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,684] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,646] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:[2023-02-16 15:52:25,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 15:52:25,730] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 15:52:25,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,678] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default4]:[2023-02-16 15:52:25,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,684] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default3]:[2023-02-16 15:52:25,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 15:52:25,651] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 15:52:25,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,648] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,659] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]:[2023-02-16 15:52:25,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 15:52:25,788] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 15:52:25,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default6]:[2023-02-16 15:52:25,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 15:52:25,756] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 15:52:25,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default5]:[2023-02-16 15:52:25,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 15:52:25,765] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 15:52:25,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default1]:[2023-02-16 15:52:25,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 15:52:25,787] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 15:52:25,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default7]:time (ms) | save-checkpoint: 3124.96 +[default4]:[2023-02-16 15:52:25,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 15:52:25,831] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step3000/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 15:52:25,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +[default0]: successfully saved checkpoint at iteration 3000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0017-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 3001/ 3814 | consumed samples: 1536512 | consumed tokens: 3146776576 | elapsed time per iteration (s): 9.58 | learning rate: 2.220E-05 | global batch size: 512 | lm loss: 4.271979E+00 | loss scale: 262144.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 53.418 | TFLOPs: 40.35 | +[default7]: iteration 3002/ 3814 | consumed samples: 1537024 | consumed tokens: 3147825152 | elapsed time per iteration (s): 5.43 | learning rate: 2.215E-05 | global batch size: 512 | lm loss: 4.251648E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.294 | TFLOPs: 71.22 | +[default7]: iteration 3003/ 3814 | consumed samples: 1537536 | consumed tokens: 3148873728 | elapsed time per iteration (s): 5.45 | learning rate: 2.209E-05 | global batch size: 512 | lm loss: 4.279715E+00 | loss scale: 262144.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.921 | TFLOPs: 70.94 | +[default7]: iteration 3004/ 3814 | consumed samples: 1538048 | consumed tokens: 3149922304 | elapsed time per iteration (s): 5.45 | learning rate: 2.204E-05 | global batch size: 512 | lm loss: 4.273755E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.013 | TFLOPs: 71.01 | +[default7]: iteration 3005/ 3814 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 5.44 | learning rate: 2.199E-05 | global batch size: 512 | lm loss: 4.256320E+00 | loss scale: 262144.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.098 | TFLOPs: 71.07 | +[default7]: iteration 3006/ 3814 | consumed samples: 1539072 | consumed tokens: 3152019456 | elapsed time per iteration (s): 5.44 | learning rate: 2.194E-05 | global batch size: 512 | lm loss: 4.270726E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.176 | TFLOPs: 71.13 | +[default7]: iteration 3007/ 3814 | consumed samples: 1539584 | consumed tokens: 3153068032 | elapsed time per iteration (s): 5.45 | learning rate: 2.189E-05 | global batch size: 512 | lm loss: 4.285131E+00 | loss scale: 262144.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.972 | TFLOPs: 70.98 | +[default7]: iteration 3008/ 3814 | consumed samples: 1540096 | consumed tokens: 3154116608 | elapsed time per iteration (s): 5.44 | learning rate: 2.184E-05 | global batch size: 512 | lm loss: 4.266567E+00 | loss scale: 262144.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.064 | TFLOPs: 71.05 | +[default7]: iteration 3009/ 3814 | consumed samples: 1540608 | consumed tokens: 3155165184 | elapsed time per iteration (s): 5.46 | learning rate: 2.178E-05 | global batch size: 512 | lm loss: 4.285290E+00 | loss scale: 262144.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.849 | TFLOPs: 70.88 | +[default7]: iteration 3010/ 3814 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 5.43 | learning rate: 2.173E-05 | global batch size: 512 | lm loss: 4.252231E+00 | loss scale: 262144.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.221 | TFLOPs: 71.17 | +[default7]: iteration 3011/ 3814 | consumed samples: 1541632 | consumed tokens: 3157262336 | elapsed time per iteration (s): 5.42 | learning rate: 2.168E-05 | global batch size: 512 | lm loss: 4.255557E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.463 | TFLOPs: 71.35 | +[default7]: iteration 3012/ 3814 | consumed samples: 1542144 | consumed tokens: 3158310912 | elapsed time per iteration (s): 5.43 | learning rate: 2.163E-05 | global batch size: 512 | lm loss: 4.280749E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.263 | TFLOPs: 71.20 | +[default7]: iteration 3013/ 3814 | consumed samples: 1542656 | consumed tokens: 3159359488 | elapsed time per iteration (s): 5.42 | learning rate: 2.158E-05 | global batch size: 512 | lm loss: 4.273770E+00 | loss scale: 262144.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.446 | TFLOPs: 71.34 | +[default7]: iteration 3014/ 3814 | consumed samples: 1543168 | consumed tokens: 3160408064 | elapsed time per iteration (s): 5.43 | learning rate: 2.153E-05 | global batch size: 512 | lm loss: 4.272060E+00 | loss scale: 262144.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.265 | TFLOPs: 71.20 | +[default7]: iteration 3015/ 3814 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 5.42 | learning rate: 2.147E-05 | global batch size: 512 | lm loss: 4.280128E+00 | loss scale: 262144.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.453 | TFLOPs: 71.34 | +[default7]: iteration 3016/ 3814 | consumed samples: 1544192 | consumed tokens: 3162505216 | elapsed time per iteration (s): 5.42 | learning rate: 2.142E-05 | global batch size: 512 | lm loss: 4.223727E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.477 | TFLOPs: 71.36 | +[default7]: iteration 3017/ 3814 | consumed samples: 1544704 | consumed tokens: 3163553792 | elapsed time per iteration (s): 5.42 | learning rate: 2.137E-05 | global batch size: 512 | lm loss: 4.241262E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.401 | TFLOPs: 71.30 | +[default7]: iteration 3018/ 3814 | consumed samples: 1545216 | consumed tokens: 3164602368 | elapsed time per iteration (s): 5.43 | learning rate: 2.132E-05 | global batch size: 512 | lm loss: 4.231328E+00 | loss scale: 262144.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.306 | TFLOPs: 71.23 | +[default7]: iteration 3019/ 3814 | consumed samples: 1545728 | consumed tokens: 3165650944 | elapsed time per iteration (s): 5.43 | learning rate: 2.127E-05 | global batch size: 512 | lm loss: 4.238252E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.359 | TFLOPs: 71.27 | +[default7]: iteration 3020/ 3814 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 5.43 | learning rate: 2.122E-05 | global batch size: 512 | lm loss: 4.255992E+00 | loss scale: 262144.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.346 | TFLOPs: 71.26 | +[default7]: iteration 3021/ 3814 | consumed samples: 1546752 | consumed tokens: 3167748096 | elapsed time per iteration (s): 5.43 | learning rate: 2.117E-05 | global batch size: 512 | lm loss: 4.268054E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.365 | TFLOPs: 71.27 | +[default7]: iteration 3022/ 3814 | consumed samples: 1547264 | consumed tokens: 3168796672 | elapsed time per iteration (s): 5.43 | learning rate: 2.112E-05 | global batch size: 512 | lm loss: 4.260519E+00 | loss scale: 262144.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.242 | TFLOPs: 71.18 | +[default7]: iteration 3023/ 3814 | consumed samples: 1547776 | consumed tokens: 3169845248 | elapsed time per iteration (s): 5.41 | learning rate: 2.107E-05 | global batch size: 512 | lm loss: 4.263844E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.577 | TFLOPs: 71.44 | +[default7]: iteration 3024/ 3814 | consumed samples: 1548288 | consumed tokens: 3170893824 | elapsed time per iteration (s): 5.42 | learning rate: 2.101E-05 | global batch size: 512 | lm loss: 4.269551E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.525 | TFLOPs: 71.40 | +[default7]: iteration 3025/ 3814 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 5.42 | learning rate: 2.096E-05 | global batch size: 512 | lm loss: 4.260376E+00 | loss scale: 262144.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.471 | TFLOPs: 71.35 | +[default7]: iteration 3026/ 3814 | consumed samples: 1549312 | consumed tokens: 3172990976 | elapsed time per iteration (s): 5.43 | learning rate: 2.091E-05 | global batch size: 512 | lm loss: 4.281558E+00 | loss scale: 262144.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.300 | TFLOPs: 71.23 | +[default7]: iteration 3027/ 3814 | consumed samples: 1549824 | consumed tokens: 3174039552 | elapsed time per iteration (s): 5.44 | learning rate: 2.086E-05 | global batch size: 512 | lm loss: 4.273942E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.065 | TFLOPs: 71.05 | +[default7]: iteration 3028/ 3814 | consumed samples: 1550336 | consumed tokens: 3175088128 | elapsed time per iteration (s): 5.43 | learning rate: 2.081E-05 | global batch size: 512 | lm loss: 4.284454E+00 | loss scale: 262144.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.317 | TFLOPs: 71.24 | +[default7]: iteration 3029/ 3814 | consumed samples: 1550848 | consumed tokens: 3176136704 | elapsed time per iteration (s): 5.45 | learning rate: 2.076E-05 | global batch size: 512 | lm loss: 4.249059E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.976 | TFLOPs: 70.98 | +[default7]: iteration 3030/ 3814 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 5.42 | learning rate: 2.071E-05 | global batch size: 512 | lm loss: 4.262597E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.404 | TFLOPs: 71.30 | +[default7]: iteration 3031/ 3814 | consumed samples: 1551872 | consumed tokens: 3178233856 | elapsed time per iteration (s): 5.43 | learning rate: 2.066E-05 | global batch size: 512 | lm loss: 4.258542E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.322 | TFLOPs: 71.24 | +[default7]: iteration 3032/ 3814 | consumed samples: 1552384 | consumed tokens: 3179282432 | elapsed time per iteration (s): 5.44 | learning rate: 2.061E-05 | global batch size: 512 | lm loss: 4.236179E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.155 | TFLOPs: 71.12 | +[default7]: iteration 3033/ 3814 | consumed samples: 1552896 | consumed tokens: 3180331008 | elapsed time per iteration (s): 5.45 | learning rate: 2.056E-05 | global batch size: 512 | lm loss: 4.295895E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.916 | TFLOPs: 70.94 | +[default7]: iteration 3034/ 3814 | consumed samples: 1553408 | consumed tokens: 3181379584 | elapsed time per iteration (s): 5.47 | learning rate: 2.051E-05 | global batch size: 512 | lm loss: 4.226842E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.566 | TFLOPs: 70.67 | +[default7]: iteration 3035/ 3814 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 5.45 | learning rate: 2.046E-05 | global batch size: 512 | lm loss: 4.246263E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.962 | TFLOPs: 70.97 | +[default7]: iteration 3036/ 3814 | consumed samples: 1554432 | consumed tokens: 3183476736 | elapsed time per iteration (s): 5.42 | learning rate: 2.041E-05 | global batch size: 512 | lm loss: 4.254964E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.448 | TFLOPs: 71.34 | +[default7]: iteration 3037/ 3814 | consumed samples: 1554944 | consumed tokens: 3184525312 | elapsed time per iteration (s): 5.41 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 4.249855E+00 | loss scale: 262144.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.606 | TFLOPs: 71.46 | +[default7]: iteration 3038/ 3814 | consumed samples: 1555456 | consumed tokens: 3185573888 | elapsed time per iteration (s): 5.41 | learning rate: 2.031E-05 | global batch size: 512 | lm loss: 4.257885E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.553 | TFLOPs: 71.42 | +[default7]: iteration 3039/ 3814 | consumed samples: 1555968 | consumed tokens: 3186622464 | elapsed time per iteration (s): 5.44 | learning rate: 2.026E-05 | global batch size: 512 | lm loss: 4.271651E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.095 | TFLOPs: 71.07 | +[default7]: iteration 3040/ 3814 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 5.42 | learning rate: 2.021E-05 | global batch size: 512 | lm loss: 4.255747E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.492 | TFLOPs: 71.37 | +[default7]: iteration 3041/ 3814 | consumed samples: 1556992 | consumed tokens: 3188719616 | elapsed time per iteration (s): 5.44 | learning rate: 2.016E-05 | global batch size: 512 | lm loss: 4.281477E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.129 | TFLOPs: 71.10 | +[default7]: iteration 3042/ 3814 | consumed samples: 1557504 | consumed tokens: 3189768192 | elapsed time per iteration (s): 5.45 | learning rate: 2.011E-05 | global batch size: 512 | lm loss: 4.226360E+00 | loss scale: 262144.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.950 | TFLOPs: 70.96 | +[default7]: iteration 3043/ 3814 | consumed samples: 1558016 | consumed tokens: 3190816768 | elapsed time per iteration (s): 5.44 | learning rate: 2.006E-05 | global batch size: 512 | lm loss: 4.246866E+00 | loss scale: 262144.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.057 | TFLOPs: 71.04 | +[default7]: iteration 3044/ 3814 | consumed samples: 1558528 | consumed tokens: 3191865344 | elapsed time per iteration (s): 5.46 | learning rate: 2.001E-05 | global batch size: 512 | lm loss: 4.233343E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.780 | TFLOPs: 70.83 | +[default7]: iteration 3045/ 3814 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 5.43 | learning rate: 1.996E-05 | global batch size: 512 | lm loss: 4.271564E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.257 | TFLOPs: 71.19 | +[default7]: iteration 3046/ 3814 | consumed samples: 1559552 | consumed tokens: 3193962496 | elapsed time per iteration (s): 5.45 | learning rate: 1.991E-05 | global batch size: 512 | lm loss: 4.256383E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.021 | TFLOPs: 71.01 | +[default7]: iteration 3047/ 3814 | consumed samples: 1560064 | consumed tokens: 3195011072 | elapsed time per iteration (s): 5.42 | learning rate: 1.986E-05 | global batch size: 512 | lm loss: 4.263967E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.505 | TFLOPs: 71.38 | +[default7]: iteration 3048/ 3814 | consumed samples: 1560576 | consumed tokens: 3196059648 | elapsed time per iteration (s): 5.43 | learning rate: 1.981E-05 | global batch size: 512 | lm loss: 4.263535E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.342 | TFLOPs: 71.26 | +[default7]: iteration 3049/ 3814 | consumed samples: 1561088 | consumed tokens: 3197108224 | elapsed time per iteration (s): 5.43 | learning rate: 1.976E-05 | global batch size: 512 | lm loss: 4.259428E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.343 | TFLOPs: 71.26 | +[default7]: iteration 3050/ 3814 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 5.42 | learning rate: 1.971E-05 | global batch size: 512 | lm loss: 4.220758E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.416 | TFLOPs: 71.31 | +[default7]: iteration 3051/ 3814 | consumed samples: 1562112 | consumed tokens: 3199205376 | elapsed time per iteration (s): 5.41 | learning rate: 1.966E-05 | global batch size: 512 | lm loss: 4.262224E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.554 | TFLOPs: 71.42 | +[default7]: iteration 3052/ 3814 | consumed samples: 1562624 | consumed tokens: 3200253952 | elapsed time per iteration (s): 5.42 | learning rate: 1.961E-05 | global batch size: 512 | lm loss: 4.265257E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.501 | TFLOPs: 71.38 | +[default7]: iteration 3053/ 3814 | consumed samples: 1563136 | consumed tokens: 3201302528 | elapsed time per iteration (s): 5.42 | learning rate: 1.956E-05 | global batch size: 512 | lm loss: 4.259942E+00 | loss scale: 262144.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.547 | TFLOPs: 71.41 | +[default7]: iteration 3054/ 3814 | consumed samples: 1563648 | consumed tokens: 3202351104 | elapsed time per iteration (s): 5.42 | learning rate: 1.951E-05 | global batch size: 512 | lm loss: 4.261300E+00 | loss scale: 262144.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.407 | TFLOPs: 71.31 | +[default7]: iteration 3055/ 3814 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 5.41 | learning rate: 1.946E-05 | global batch size: 512 | lm loss: 4.209886E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.605 | TFLOPs: 71.46 | +[default7]: iteration 3056/ 3814 | consumed samples: 1564672 | consumed tokens: 3204448256 | elapsed time per iteration (s): 5.43 | learning rate: 1.941E-05 | global batch size: 512 | lm loss: 4.261804E+00 | loss scale: 262144.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.212 | TFLOPs: 71.16 | +[default7]: iteration 3057/ 3814 | consumed samples: 1565184 | consumed tokens: 3205496832 | elapsed time per iteration (s): 5.42 | learning rate: 1.937E-05 | global batch size: 512 | lm loss: 4.248659E+00 | loss scale: 262144.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.435 | TFLOPs: 71.33 | +[default7]: iteration 3058/ 3814 | consumed samples: 1565696 | consumed tokens: 3206545408 | elapsed time per iteration (s): 5.41 | learning rate: 1.932E-05 | global batch size: 512 | lm loss: 4.258440E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.614 | TFLOPs: 71.46 | +[default7]: iteration 3059/ 3814 | consumed samples: 1566208 | consumed tokens: 3207593984 | elapsed time per iteration (s): 5.43 | learning rate: 1.927E-05 | global batch size: 512 | lm loss: 4.258718E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.302 | TFLOPs: 71.23 | +[default7]: iteration 3060/ 3814 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 5.42 | learning rate: 1.922E-05 | global batch size: 512 | lm loss: 4.271428E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.442 | TFLOPs: 71.33 | +[default7]: iteration 3061/ 3814 | consumed samples: 1567232 | consumed tokens: 3209691136 | elapsed time per iteration (s): 5.40 | learning rate: 1.917E-05 | global batch size: 512 | lm loss: 4.260328E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.739 | TFLOPs: 71.56 | +[default7]: iteration 3062/ 3814 | consumed samples: 1567744 | consumed tokens: 3210739712 | elapsed time per iteration (s): 5.43 | learning rate: 1.912E-05 | global batch size: 512 | lm loss: 4.235797E+00 | loss scale: 262144.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 3063/ 3814 | consumed samples: 1568256 | consumed tokens: 3211788288 | elapsed time per iteration (s): 5.42 | learning rate: 1.907E-05 | global batch size: 512 | lm loss: 4.228390E+00 | loss scale: 262144.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.441 | TFLOPs: 71.33 | +[default7]: iteration 3064/ 3814 | consumed samples: 1568768 | consumed tokens: 3212836864 | elapsed time per iteration (s): 5.42 | learning rate: 1.902E-05 | global batch size: 512 | lm loss: 4.271337E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.547 | TFLOPs: 71.41 | +[default7]: iteration 3065/ 3814 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 5.43 | learning rate: 1.897E-05 | global batch size: 512 | lm loss: 4.235936E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.373 | TFLOPs: 71.28 | +[default7]: iteration 3066/ 3814 | consumed samples: 1569792 | consumed tokens: 3214934016 | elapsed time per iteration (s): 5.44 | learning rate: 1.893E-05 | global batch size: 512 | lm loss: 4.247077E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.202 | TFLOPs: 71.15 | +[default7]: iteration 3067/ 3814 | consumed samples: 1570304 | consumed tokens: 3215982592 | elapsed time per iteration (s): 5.45 | learning rate: 1.888E-05 | global batch size: 512 | lm loss: 4.252952E+00 | loss scale: 262144.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.893 | TFLOPs: 70.92 | +[default7]: iteration 3068/ 3814 | consumed samples: 1570816 | consumed tokens: 3217031168 | elapsed time per iteration (s): 5.44 | learning rate: 1.883E-05 | global batch size: 512 | lm loss: 4.260468E+00 | loss scale: 262144.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.046 | TFLOPs: 71.03 | +[default7]: iteration 3069/ 3814 | consumed samples: 1571328 | consumed tokens: 3218079744 | elapsed time per iteration (s): 5.45 | learning rate: 1.878E-05 | global batch size: 512 | lm loss: 4.245392E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.872 | TFLOPs: 70.90 | +[default7]: iteration 3070/ 3814 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 5.44 | learning rate: 1.873E-05 | global batch size: 512 | lm loss: 4.264019E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.104 | TFLOPs: 71.08 | +[default7]: iteration 3071/ 3814 | consumed samples: 1572352 | consumed tokens: 3220176896 | elapsed time per iteration (s): 5.45 | learning rate: 1.868E-05 | global batch size: 512 | lm loss: 4.261513E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.933 | TFLOPs: 70.95 | +[default7]: iteration 3072/ 3814 | consumed samples: 1572864 | consumed tokens: 3221225472 | elapsed time per iteration (s): 5.45 | learning rate: 1.864E-05 | global batch size: 512 | lm loss: 4.205717E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.015 | TFLOPs: 71.01 | +[default7]: iteration 3073/ 3814 | consumed samples: 1573376 | consumed tokens: 3222274048 | elapsed time per iteration (s): 5.46 | learning rate: 1.859E-05 | global batch size: 512 | lm loss: 4.257293E+00 | loss scale: 262144.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.723 | TFLOPs: 70.79 | +[default7]: iteration 3074/ 3814 | consumed samples: 1573888 | consumed tokens: 3223322624 | elapsed time per iteration (s): 5.46 | learning rate: 1.854E-05 | global batch size: 512 | lm loss: 4.252492E+00 | loss scale: 262144.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.761 | TFLOPs: 70.82 | +[default7]: iteration 3075/ 3814 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 5.45 | learning rate: 1.849E-05 | global batch size: 512 | lm loss: 4.232244E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.961 | TFLOPs: 70.97 | +[default7]: iteration 3076/ 3814 | consumed samples: 1574912 | consumed tokens: 3225419776 | elapsed time per iteration (s): 5.45 | learning rate: 1.844E-05 | global batch size: 512 | lm loss: 4.255676E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.992 | TFLOPs: 70.99 | +[default7]: iteration 3077/ 3814 | consumed samples: 1575424 | consumed tokens: 3226468352 | elapsed time per iteration (s): 5.43 | learning rate: 1.840E-05 | global batch size: 512 | lm loss: 4.264803E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.357 | TFLOPs: 71.27 | +[default7]: iteration 3078/ 3814 | consumed samples: 1575936 | consumed tokens: 3227516928 | elapsed time per iteration (s): 5.43 | learning rate: 1.835E-05 | global batch size: 512 | lm loss: 4.254387E+00 | loss scale: 262144.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.220 | TFLOPs: 71.17 | +[default7]: iteration 3079/ 3814 | consumed samples: 1576448 | consumed tokens: 3228565504 | elapsed time per iteration (s): 5.42 | learning rate: 1.830E-05 | global batch size: 512 | lm loss: 4.238435E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.382 | TFLOPs: 71.29 | +[default7]: iteration 3080/ 3814 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 5.45 | learning rate: 1.825E-05 | global batch size: 512 | lm loss: 4.262249E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.027 | TFLOPs: 71.02 | +[default7]: iteration 3081/ 3814 | consumed samples: 1577472 | consumed tokens: 3230662656 | elapsed time per iteration (s): 5.46 | learning rate: 1.820E-05 | global batch size: 512 | lm loss: 4.242275E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.791 | TFLOPs: 70.84 | +[default7]: iteration 3082/ 3814 | consumed samples: 1577984 | consumed tokens: 3231711232 | elapsed time per iteration (s): 5.46 | learning rate: 1.816E-05 | global batch size: 512 | lm loss: 4.253493E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.845 | TFLOPs: 70.88 | +[default7]: iteration 3083/ 3814 | consumed samples: 1578496 | consumed tokens: 3232759808 | elapsed time per iteration (s): 5.45 | learning rate: 1.811E-05 | global batch size: 512 | lm loss: 4.256220E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.902 | TFLOPs: 70.92 | +[default7]: iteration 3084/ 3814 | consumed samples: 1579008 | consumed tokens: 3233808384 | elapsed time per iteration (s): 5.45 | learning rate: 1.806E-05 | global batch size: 512 | lm loss: 4.246998E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.026 | TFLOPs: 71.02 | +[default7]: iteration 3085/ 3814 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 5.48 | learning rate: 1.801E-05 | global batch size: 512 | lm loss: 4.276633E+00 | loss scale: 262144.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.372 | TFLOPs: 70.53 | +[default7]: iteration 3086/ 3814 | consumed samples: 1580032 | consumed tokens: 3235905536 | elapsed time per iteration (s): 5.44 | learning rate: 1.797E-05 | global batch size: 512 | lm loss: 4.229846E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.168 | TFLOPs: 71.13 | +[default7]: iteration 3087/ 3814 | consumed samples: 1580544 | consumed tokens: 3236954112 | elapsed time per iteration (s): 5.42 | learning rate: 1.792E-05 | global batch size: 512 | lm loss: 4.254685E+00 | loss scale: 262144.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.413 | TFLOPs: 71.31 | +[default7]: iteration 3088/ 3814 | consumed samples: 1581056 | consumed tokens: 3238002688 | elapsed time per iteration (s): 5.44 | learning rate: 1.787E-05 | global batch size: 512 | lm loss: 4.260684E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 3089/ 3814 | consumed samples: 1581568 | consumed tokens: 3239051264 | elapsed time per iteration (s): 5.44 | learning rate: 1.782E-05 | global batch size: 512 | lm loss: 4.257212E+00 | loss scale: 262144.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.193 | TFLOPs: 71.15 | +[default7]: iteration 3090/ 3814 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 5.43 | learning rate: 1.778E-05 | global batch size: 512 | lm loss: 4.257510E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.325 | TFLOPs: 71.24 | +[default7]: iteration 3091/ 3814 | consumed samples: 1582592 | consumed tokens: 3241148416 | elapsed time per iteration (s): 5.44 | learning rate: 1.773E-05 | global batch size: 512 | lm loss: 4.222025E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.149 | TFLOPs: 71.11 | +[default7]: iteration 3092/ 3814 | consumed samples: 1583104 | consumed tokens: 3242196992 | elapsed time per iteration (s): 5.44 | learning rate: 1.768E-05 | global batch size: 512 | lm loss: 4.252770E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.146 | TFLOPs: 71.11 | +[default7]: iteration 3093/ 3814 | consumed samples: 1583616 | consumed tokens: 3243245568 | elapsed time per iteration (s): 5.43 | learning rate: 1.763E-05 | global batch size: 512 | lm loss: 4.248899E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.217 | TFLOPs: 71.16 | +[default7]: iteration 3094/ 3814 | consumed samples: 1584128 | consumed tokens: 3244294144 | elapsed time per iteration (s): 5.46 | learning rate: 1.759E-05 | global batch size: 512 | lm loss: 4.232171E+00 | loss scale: 262144.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.805 | TFLOPs: 70.85 | +[default7]: iteration 3095/ 3814 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 5.49 | learning rate: 1.754E-05 | global batch size: 512 | lm loss: 4.244451E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.197 | TFLOPs: 70.39 | +[default7]: iteration 3096/ 3814 | consumed samples: 1585152 | consumed tokens: 3246391296 | elapsed time per iteration (s): 5.47 | learning rate: 1.749E-05 | global batch size: 512 | lm loss: 4.256460E+00 | loss scale: 262144.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.526 | TFLOPs: 70.64 | +[default7]: iteration 3097/ 3814 | consumed samples: 1585664 | consumed tokens: 3247439872 | elapsed time per iteration (s): 5.48 | learning rate: 1.745E-05 | global batch size: 512 | lm loss: 4.259949E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.486 | TFLOPs: 70.61 | +[default7]: iteration 3098/ 3814 | consumed samples: 1586176 | consumed tokens: 3248488448 | elapsed time per iteration (s): 5.45 | learning rate: 1.740E-05 | global batch size: 512 | lm loss: 4.246684E+00 | loss scale: 262144.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.983 | TFLOPs: 70.99 | +[default7]: iteration 3099/ 3814 | consumed samples: 1586688 | consumed tokens: 3249537024 | elapsed time per iteration (s): 5.46 | learning rate: 1.735E-05 | global batch size: 512 | lm loss: 4.266778E+00 | loss scale: 262144.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.748 | TFLOPs: 70.81 | +[default7]: iteration 3100/ 3814 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 5.43 | learning rate: 1.731E-05 | global batch size: 512 | lm loss: 4.245927E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.348 | TFLOPs: 71.26 | +[default7]: iteration 3101/ 3814 | consumed samples: 1587712 | consumed tokens: 3251634176 | elapsed time per iteration (s): 5.46 | learning rate: 1.726E-05 | global batch size: 512 | lm loss: 4.263980E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.728 | TFLOPs: 70.79 | +[default7]: iteration 3102/ 3814 | consumed samples: 1588224 | consumed tokens: 3252682752 | elapsed time per iteration (s): 5.46 | learning rate: 1.721E-05 | global batch size: 512 | lm loss: 4.242828E+00 | loss scale: 262144.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.840 | TFLOPs: 70.88 | +[default7]: iteration 3103/ 3814 | consumed samples: 1588736 | consumed tokens: 3253731328 | elapsed time per iteration (s): 5.45 | learning rate: 1.717E-05 | global batch size: 512 | lm loss: 4.256754E+00 | loss scale: 262144.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.942 | TFLOPs: 70.96 | +[default7]: iteration 3104/ 3814 | consumed samples: 1589248 | consumed tokens: 3254779904 | elapsed time per iteration (s): 5.43 | learning rate: 1.712E-05 | global batch size: 512 | lm loss: 4.245749E+00 | loss scale: 262144.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.334 | TFLOPs: 71.25 | +[default7]: iteration 3105/ 3814 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 5.47 | learning rate: 1.707E-05 | global batch size: 512 | lm loss: 4.259723E+00 | loss scale: 262144.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.641 | TFLOPs: 70.73 | +[default7]: iteration 3106/ 3814 | consumed samples: 1590272 | consumed tokens: 3256877056 | elapsed time per iteration (s): 5.46 | learning rate: 1.703E-05 | global batch size: 512 | lm loss: 4.276598E+00 | loss scale: 262144.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.752 | TFLOPs: 70.81 | +[default7]: iteration 3107/ 3814 | consumed samples: 1590784 | consumed tokens: 3257925632 | elapsed time per iteration (s): 5.44 | learning rate: 1.698E-05 | global batch size: 512 | lm loss: 4.244333E+00 | loss scale: 262144.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.063 | TFLOPs: 71.05 | +[default7]: iteration 3108/ 3814 | consumed samples: 1591296 | consumed tokens: 3258974208 | elapsed time per iteration (s): 5.44 | learning rate: 1.693E-05 | global batch size: 512 | lm loss: 4.244439E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.136 | TFLOPs: 71.10 | +[default7]: iteration 3109/ 3814 | consumed samples: 1591808 | consumed tokens: 3260022784 | elapsed time per iteration (s): 5.45 | learning rate: 1.689E-05 | global batch size: 512 | lm loss: 4.239487E+00 | loss scale: 262144.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.878 | TFLOPs: 70.91 | +[default7]: iteration 3110/ 3814 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 5.44 | learning rate: 1.684E-05 | global batch size: 512 | lm loss: 4.213886E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.168 | TFLOPs: 71.13 | +[default7]: iteration 3111/ 3814 | consumed samples: 1592832 | consumed tokens: 3262119936 | elapsed time per iteration (s): 5.44 | learning rate: 1.680E-05 | global batch size: 512 | lm loss: 4.244797E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.039 | TFLOPs: 71.03 | +[default7]: iteration 3112/ 3814 | consumed samples: 1593344 | consumed tokens: 3263168512 | elapsed time per iteration (s): 5.46 | learning rate: 1.675E-05 | global batch size: 512 | lm loss: 4.237634E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.856 | TFLOPs: 70.89 | +[default7]: iteration 3113/ 3814 | consumed samples: 1593856 | consumed tokens: 3264217088 | elapsed time per iteration (s): 5.42 | learning rate: 1.670E-05 | global batch size: 512 | lm loss: 4.238375E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.387 | TFLOPs: 71.29 | +[default7]: iteration 3114/ 3814 | consumed samples: 1594368 | consumed tokens: 3265265664 | elapsed time per iteration (s): 5.43 | learning rate: 1.666E-05 | global batch size: 512 | lm loss: 4.248171E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.378 | TFLOPs: 71.28 | +[default7]: iteration 3115/ 3814 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 5.43 | learning rate: 1.661E-05 | global batch size: 512 | lm loss: 4.244816E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.373 | TFLOPs: 71.28 | +[default7]: iteration 3116/ 3814 | consumed samples: 1595392 | consumed tokens: 3267362816 | elapsed time per iteration (s): 5.44 | learning rate: 1.657E-05 | global batch size: 512 | lm loss: 4.243607E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.102 | TFLOPs: 71.08 | +[default7]: iteration 3117/ 3814 | consumed samples: 1595904 | consumed tokens: 3268411392 | elapsed time per iteration (s): 5.44 | learning rate: 1.652E-05 | global batch size: 512 | lm loss: 4.208370E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.200 | TFLOPs: 71.15 | +[default7]: iteration 3118/ 3814 | consumed samples: 1596416 | consumed tokens: 3269459968 | elapsed time per iteration (s): 5.44 | learning rate: 1.647E-05 | global batch size: 512 | lm loss: 4.274101E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.185 | TFLOPs: 71.14 | +[default7]: iteration 3119/ 3814 | consumed samples: 1596928 | consumed tokens: 3270508544 | elapsed time per iteration (s): 5.41 | learning rate: 1.643E-05 | global batch size: 512 | lm loss: 4.274301E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.577 | TFLOPs: 71.44 | +[default7]: iteration 3120/ 3814 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 5.43 | learning rate: 1.638E-05 | global batch size: 512 | lm loss: 4.246347E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.269 | TFLOPs: 71.20 | +[default7]: iteration 3121/ 3814 | consumed samples: 1597952 | consumed tokens: 3272605696 | elapsed time per iteration (s): 5.43 | learning rate: 1.634E-05 | global batch size: 512 | lm loss: 4.242575E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.287 | TFLOPs: 71.22 | +[default7]: iteration 3122/ 3814 | consumed samples: 1598464 | consumed tokens: 3273654272 | elapsed time per iteration (s): 5.43 | learning rate: 1.629E-05 | global batch size: 512 | lm loss: 4.253531E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.262 | TFLOPs: 71.20 | +[default7]: iteration 3123/ 3814 | consumed samples: 1598976 | consumed tokens: 3274702848 | elapsed time per iteration (s): 5.47 | learning rate: 1.625E-05 | global batch size: 512 | lm loss: 4.285728E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.652 | TFLOPs: 70.74 | +[default7]: iteration 3124/ 3814 | consumed samples: 1599488 | consumed tokens: 3275751424 | elapsed time per iteration (s): 5.45 | learning rate: 1.620E-05 | global batch size: 512 | lm loss: 4.240905E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.923 | TFLOPs: 70.94 | +[default7]: iteration 3125/ 3814 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 5.45 | learning rate: 1.616E-05 | global batch size: 512 | lm loss: 4.242100E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.988 | TFLOPs: 70.99 | +[default7]: iteration 3126/ 3814 | consumed samples: 1600512 | consumed tokens: 3277848576 | elapsed time per iteration (s): 5.46 | learning rate: 1.611E-05 | global batch size: 512 | lm loss: 4.236230E+00 | loss scale: 262144.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.765 | TFLOPs: 70.82 | +[default7]: iteration 3127/ 3814 | consumed samples: 1601024 | consumed tokens: 3278897152 | elapsed time per iteration (s): 5.45 | learning rate: 1.607E-05 | global batch size: 512 | lm loss: 4.243431E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.936 | TFLOPs: 70.95 | +[default7]: iteration 3128/ 3814 | consumed samples: 1601536 | consumed tokens: 3279945728 | elapsed time per iteration (s): 5.45 | learning rate: 1.602E-05 | global batch size: 512 | lm loss: 4.237486E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.899 | TFLOPs: 70.92 | +[default7]: iteration 3129/ 3814 | consumed samples: 1602048 | consumed tokens: 3280994304 | elapsed time per iteration (s): 5.45 | learning rate: 1.597E-05 | global batch size: 512 | lm loss: 4.244437E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.965 | TFLOPs: 70.97 | +[default7]: iteration 3130/ 3814 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 5.43 | learning rate: 1.593E-05 | global batch size: 512 | lm loss: 4.212792E+00 | loss scale: 262144.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.248 | TFLOPs: 71.19 | +[default7]: iteration 3131/ 3814 | consumed samples: 1603072 | consumed tokens: 3283091456 | elapsed time per iteration (s): 5.44 | learning rate: 1.588E-05 | global batch size: 512 | lm loss: 4.259573E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.090 | TFLOPs: 71.07 | +[default7]: iteration 3132/ 3814 | consumed samples: 1603584 | consumed tokens: 3284140032 | elapsed time per iteration (s): 5.45 | learning rate: 1.584E-05 | global batch size: 512 | lm loss: 4.243366E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.950 | TFLOPs: 70.96 | +[default7]: iteration 3133/ 3814 | consumed samples: 1604096 | consumed tokens: 3285188608 | elapsed time per iteration (s): 5.44 | learning rate: 1.580E-05 | global batch size: 512 | lm loss: 4.285527E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.184 | TFLOPs: 71.14 | +[default7]: iteration 3134/ 3814 | consumed samples: 1604608 | consumed tokens: 3286237184 | elapsed time per iteration (s): 5.44 | learning rate: 1.575E-05 | global batch size: 512 | lm loss: 4.253715E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.064 | TFLOPs: 71.05 | +[default7]: iteration 3135/ 3814 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 5.44 | learning rate: 1.571E-05 | global batch size: 512 | lm loss: 4.271239E+00 | loss scale: 262144.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.115 | TFLOPs: 71.09 | +[default7]: iteration 3136/ 3814 | consumed samples: 1605632 | consumed tokens: 3288334336 | elapsed time per iteration (s): 5.43 | learning rate: 1.566E-05 | global batch size: 512 | lm loss: 4.216692E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.366 | TFLOPs: 71.28 | +[default7]: iteration 3137/ 3814 | consumed samples: 1606144 | consumed tokens: 3289382912 | elapsed time per iteration (s): 5.46 | learning rate: 1.562E-05 | global batch size: 512 | lm loss: 4.226488E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 93.785 | TFLOPs: 70.84 | +[default7]: iteration 3138/ 3814 | consumed samples: 1606656 | consumed tokens: 3290431488 | elapsed time per iteration (s): 5.43 | learning rate: 1.557E-05 | global batch size: 512 | lm loss: 4.240158E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.344 | TFLOPs: 71.26 | +[default7]: iteration 3139/ 3814 | consumed samples: 1607168 | consumed tokens: 3291480064 | elapsed time per iteration (s): 5.43 | learning rate: 1.553E-05 | global batch size: 512 | lm loss: 4.247791E+00 | loss scale: 262144.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.358 | TFLOPs: 71.27 | +[default7]: iteration 3140/ 3814 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 5.42 | learning rate: 1.548E-05 | global batch size: 512 | lm loss: 4.257149E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.420 | TFLOPs: 71.32 | +[default7]: iteration 3141/ 3814 | consumed samples: 1608192 | consumed tokens: 3293577216 | elapsed time per iteration (s): 5.42 | learning rate: 1.544E-05 | global batch size: 512 | lm loss: 4.211727E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.504 | TFLOPs: 71.38 | +[default7]: iteration 3142/ 3814 | consumed samples: 1608704 | consumed tokens: 3294625792 | elapsed time per iteration (s): 5.44 | learning rate: 1.539E-05 | global batch size: 512 | lm loss: 4.243881E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.087 | TFLOPs: 71.07 | +[default7]: iteration 3143/ 3814 | consumed samples: 1609216 | consumed tokens: 3295674368 | elapsed time per iteration (s): 5.43 | learning rate: 1.535E-05 | global batch size: 512 | lm loss: 4.277615E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.256 | TFLOPs: 71.19 | +[default7]: iteration 3144/ 3814 | consumed samples: 1609728 | consumed tokens: 3296722944 | elapsed time per iteration (s): 5.40 | learning rate: 1.531E-05 | global batch size: 512 | lm loss: 4.241041E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.769 | TFLOPs: 71.58 | +[default7]: iteration 3145/ 3814 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 5.41 | learning rate: 1.526E-05 | global batch size: 512 | lm loss: 4.257729E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.706 | TFLOPs: 71.53 | +[default7]: iteration 3146/ 3814 | consumed samples: 1610752 | consumed tokens: 3298820096 | elapsed time per iteration (s): 5.43 | learning rate: 1.522E-05 | global batch size: 512 | lm loss: 4.273560E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.300 | TFLOPs: 71.23 | +[default7]: iteration 3147/ 3814 | consumed samples: 1611264 | consumed tokens: 3299868672 | elapsed time per iteration (s): 5.42 | learning rate: 1.517E-05 | global batch size: 512 | lm loss: 4.239741E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.392 | TFLOPs: 71.30 | +[default7]: iteration 3148/ 3814 | consumed samples: 1611776 | consumed tokens: 3300917248 | elapsed time per iteration (s): 5.43 | learning rate: 1.513E-05 | global batch size: 512 | lm loss: 4.248119E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.324 | TFLOPs: 71.24 | +[default7]: iteration 3149/ 3814 | consumed samples: 1612288 | consumed tokens: 3301965824 | elapsed time per iteration (s): 5.43 | learning rate: 1.508E-05 | global batch size: 512 | lm loss: 4.226894E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.210 | TFLOPs: 71.16 | +[default7]: iteration 3150/ 3814 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 5.42 | learning rate: 1.504E-05 | global batch size: 512 | lm loss: 4.211771E+00 | loss scale: 262144.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.508 | TFLOPs: 71.38 | +[default7]: iteration 3151/ 3814 | consumed samples: 1613312 | consumed tokens: 3304062976 | elapsed time per iteration (s): 5.41 | learning rate: 1.500E-05 | global batch size: 512 | lm loss: 4.247902E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.665 | TFLOPs: 71.50 | +[default7]: iteration 3152/ 3814 | consumed samples: 1613824 | consumed tokens: 3305111552 | elapsed time per iteration (s): 5.42 | learning rate: 1.495E-05 | global batch size: 512 | lm loss: 4.260790E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.524 | TFLOPs: 71.39 | +[default7]: iteration 3153/ 3814 | consumed samples: 1614336 | consumed tokens: 3306160128 | elapsed time per iteration (s): 5.40 | learning rate: 1.491E-05 | global batch size: 512 | lm loss: 4.289088E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.790 | TFLOPs: 71.60 | +[default7]: iteration 3154/ 3814 | consumed samples: 1614848 | consumed tokens: 3307208704 | elapsed time per iteration (s): 5.42 | learning rate: 1.487E-05 | global batch size: 512 | lm loss: 4.205788E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.551 | TFLOPs: 71.42 | +[default7]: iteration 3155/ 3814 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 5.40 | learning rate: 1.482E-05 | global batch size: 512 | lm loss: 4.235598E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.840 | TFLOPs: 71.63 | +[default7]: iteration 3156/ 3814 | consumed samples: 1615872 | consumed tokens: 3309305856 | elapsed time per iteration (s): 5.42 | learning rate: 1.478E-05 | global batch size: 512 | lm loss: 4.228075E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.549 | TFLOPs: 71.41 | +[default7]: iteration 3157/ 3814 | consumed samples: 1616384 | consumed tokens: 3310354432 | elapsed time per iteration (s): 5.42 | learning rate: 1.474E-05 | global batch size: 512 | lm loss: 4.221089E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.425 | TFLOPs: 71.32 | +[default7]: iteration 3158/ 3814 | consumed samples: 1616896 | consumed tokens: 3311403008 | elapsed time per iteration (s): 5.43 | learning rate: 1.469E-05 | global batch size: 512 | lm loss: 4.271920E+00 | loss scale: 262144.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.319 | TFLOPs: 71.24 | +[default7]: iteration 3159/ 3814 | consumed samples: 1617408 | consumed tokens: 3312451584 | elapsed time per iteration (s): 5.40 | learning rate: 1.465E-05 | global batch size: 512 | lm loss: 4.255845E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.747 | TFLOPs: 71.56 | +[default7]: iteration 3160/ 3814 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 5.42 | learning rate: 1.461E-05 | global batch size: 512 | lm loss: 4.233467E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.458 | TFLOPs: 71.35 | +[default7]: iteration 3161/ 3814 | consumed samples: 1618432 | consumed tokens: 3314548736 | elapsed time per iteration (s): 5.41 | learning rate: 1.456E-05 | global batch size: 512 | lm loss: 4.260049E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.618 | TFLOPs: 71.47 | +[default7]: iteration 3162/ 3814 | consumed samples: 1618944 | consumed tokens: 3315597312 | elapsed time per iteration (s): 5.42 | learning rate: 1.452E-05 | global batch size: 512 | lm loss: 4.260565E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.451 | TFLOPs: 71.34 | +[default7]: iteration 3163/ 3814 | consumed samples: 1619456 | consumed tokens: 3316645888 | elapsed time per iteration (s): 5.41 | learning rate: 1.448E-05 | global batch size: 512 | lm loss: 4.241580E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.707 | TFLOPs: 71.53 | +[default7]: iteration 3164/ 3814 | consumed samples: 1619968 | consumed tokens: 3317694464 | elapsed time per iteration (s): 5.42 | learning rate: 1.443E-05 | global batch size: 512 | lm loss: 4.241119E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.507 | TFLOPs: 71.38 | +[default7]: iteration 3165/ 3814 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 5.41 | learning rate: 1.439E-05 | global batch size: 512 | lm loss: 4.250598E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.664 | TFLOPs: 71.50 | +[default7]: iteration 3166/ 3814 | consumed samples: 1620992 | consumed tokens: 3319791616 | elapsed time per iteration (s): 5.42 | learning rate: 1.435E-05 | global batch size: 512 | lm loss: 4.235000E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.476 | TFLOPs: 71.36 | +[default7]: iteration 3167/ 3814 | consumed samples: 1621504 | consumed tokens: 3320840192 | elapsed time per iteration (s): 5.43 | learning rate: 1.430E-05 | global batch size: 512 | lm loss: 4.243563E+00 | loss scale: 262144.0 | grad norm: 0.097 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.283 | TFLOPs: 71.21 | +[default7]: iteration 3168/ 3814 | consumed samples: 1622016 | consumed tokens: 3321888768 | elapsed time per iteration (s): 5.44 | learning rate: 1.426E-05 | global batch size: 512 | lm loss: 4.245268E+00 | loss scale: 262144.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.075 | TFLOPs: 71.06 | +[default7]: iteration 3169/ 3814 | consumed samples: 1622528 | consumed tokens: 3322937344 | elapsed time per iteration (s): 5.42 | learning rate: 1.422E-05 | global batch size: 512 | lm loss: 4.258990E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.427 | TFLOPs: 71.32 | +[default7]: iteration 3170/ 3814 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 5.43 | learning rate: 1.418E-05 | global batch size: 512 | lm loss: 4.255926E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.264 | TFLOPs: 71.20 | +[default7]: iteration 3171/ 3814 | consumed samples: 1623552 | consumed tokens: 3325034496 | elapsed time per iteration (s): 5.41 | learning rate: 1.413E-05 | global batch size: 512 | lm loss: 4.246141E+00 | loss scale: 262144.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.661 | TFLOPs: 71.50 | +[default7]: iteration 3172/ 3814 | consumed samples: 1624064 | consumed tokens: 3326083072 | elapsed time per iteration (s): 5.43 | learning rate: 1.409E-05 | global batch size: 512 | lm loss: 4.255187E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.338 | TFLOPs: 71.25 | +[default7]: iteration 3173/ 3814 | consumed samples: 1624576 | consumed tokens: 3327131648 | elapsed time per iteration (s): 5.42 | learning rate: 1.405E-05 | global batch size: 512 | lm loss: 4.240652E+00 | loss scale: 262144.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.526 | TFLOPs: 71.40 | +[default7]: iteration 3174/ 3814 | consumed samples: 1625088 | consumed tokens: 3328180224 | elapsed time per iteration (s): 5.43 | learning rate: 1.400E-05 | global batch size: 512 | lm loss: 4.253660E+00 | loss scale: 262144.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.306 | TFLOPs: 71.23 | +[default7]: iteration 3175/ 3814 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 5.40 | learning rate: 1.396E-05 | global batch size: 512 | lm loss: 4.241210E+00 | loss scale: 262144.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.786 | TFLOPs: 71.59 | +[default7]: iteration 3176/ 3814 | consumed samples: 1626112 | consumed tokens: 3330277376 | elapsed time per iteration (s): 5.40 | learning rate: 1.392E-05 | global batch size: 512 | lm loss: 4.234361E+00 | loss scale: 262144.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.755 | TFLOPs: 71.57 | +[default7]: iteration 3177/ 3814 | consumed samples: 1626624 | consumed tokens: 3331325952 | elapsed time per iteration (s): 5.42 | learning rate: 1.388E-05 | global batch size: 512 | lm loss: 4.231936E+00 | loss scale: 262144.0 | grad norm: 0.094 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.466 | TFLOPs: 71.35 | +[default7]: iteration 3178/ 3814 | consumed samples: 1627136 | consumed tokens: 3332374528 | elapsed time per iteration (s): 5.41 | learning rate: 1.384E-05 | global batch size: 512 | lm loss: 4.267732E+00 | loss scale: 262144.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.706 | TFLOPs: 71.53 | +[default7]: iteration 3179/ 3814 | consumed samples: 1627648 | consumed tokens: 3333423104 | elapsed time per iteration (s): 5.41 | learning rate: 1.379E-05 | global batch size: 512 | lm loss: 4.246267E+00 | loss scale: 262144.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.670 | TFLOPs: 71.51 | +[default7]: iteration 3180/ 3814 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 5.40 | learning rate: 1.375E-05 | global batch size: 512 | lm loss: 4.213445E+00 | loss scale: 262144.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.850 | TFLOPs: 71.64 | +[default7]: iteration 3181/ 3814 | consumed samples: 1628672 | consumed tokens: 3335520256 | elapsed time per iteration (s): 5.41 | learning rate: 1.371E-05 | global batch size: 512 | lm loss: 4.278794E+00 | loss scale: 262144.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.686 | TFLOPs: 71.52 | +[default7]: iteration 3182/ 3814 | consumed samples: 1629184 | consumed tokens: 3336568832 | elapsed time per iteration (s): 5.41 | learning rate: 1.367E-05 | global batch size: 512 | lm loss: 4.262996E+00 | loss scale: 262144.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.666 | TFLOPs: 71.50 | +[default7]: iteration 3183/ 3814 | consumed samples: 1629696 | consumed tokens: 3337617408 | elapsed time per iteration (s): 5.40 | learning rate: 1.362E-05 | global batch size: 512 | lm loss: 4.242826E+00 | loss scale: 262144.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.885 | TFLOPs: 71.67 | +[default7]: iteration 3184/ 3814 | consumed samples: 1630208 | consumed tokens: 3338665984 | elapsed time per iteration (s): 5.40 | learning rate: 1.358E-05 | global batch size: 512 | lm loss: 4.241774E+00 | loss scale: 262144.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.769 | TFLOPs: 71.58 | +[default7]: iteration 3185/ 3814 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 5.39 | learning rate: 1.354E-05 | global batch size: 512 | lm loss: 4.259750E+00 | loss scale: 262144.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 95.011 | TFLOPs: 71.76 | +[default7]: iteration 3186/ 3814 | consumed samples: 1631232 | consumed tokens: 3340763136 | elapsed time per iteration (s): 5.40 | learning rate: 1.350E-05 | global batch size: 512 | lm loss: 4.269930E+00 | loss scale: 262144.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.789 | TFLOPs: 71.60 | +[default7]: iteration 3187/ 3814 | consumed samples: 1631744 | consumed tokens: 3341811712 | elapsed time per iteration (s): 5.40 | learning rate: 1.346E-05 | global batch size: 512 | lm loss: 4.226227E+00 | loss scale: 262144.0 | grad norm: 0.091 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.851 | TFLOPs: 71.64 | +[default7]: iteration 3188/ 3814 | consumed samples: 1632256 | consumed tokens: 3342860288 | elapsed time per iteration (s): 5.44 | learning rate: 1.342E-05 | global batch size: 512 | lm loss: 4.220816E+00 | loss scale: 262144.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 94.041 | TFLOPs: 71.03 |