Upload llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2

.gitattributes

@@ -66,3 +66,4 @@ llama-1B/16_GPUS/dp-1_tp-4_pp-4_mbz-16/profiler/ip-26-0-163-147_683312.171994997
 llama-1B/16_GPUS/dp-2_tp-8_pp-1_mbz-4/profiler/ip-26-0-171-21_2582701.1719950103572137437.pt.trace.json.tmp filter=lfs diff=lfs merge=lfs -text
 llama-1B/16_GPUS/dp-1_tp-4_pp-4_mbz-8/profiler/ip-26-0-169-139_2571529.1719950310974795475.pt.trace.json filter=lfs diff=lfs merge=lfs -text
 llama-1B/16_GPUS/dp-4_tp-2_pp-2_mbz-4/profiler/ip-26-0-160-225_1672146.1719950266162829584.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2/profiler/ip-26-0-163-147_704351.1719950608420005259.pt.trace.json filter=lfs diff=lfs merge=lfs -text

llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2/log.out

@@ -1,5 +1,5 @@
 ========================
-START TIME: Tue Jul  2 16:30:13 UTC 2024
+START TIME: Tue Jul  2 19:59:42 UTC 2024
 python3 version = Python 3.10.14
 ========================
 The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
@@ -14,120 +14,284 @@ M	src/nanotron/models/llama.py
 M	src/nanotron/trainer.py
 Your branch is up to date with 'origin/bench_cluster'.
 Job status: RUNNING
-W0702 16:30:16.125000 140327896655680 torch/distributed/run.py:757] 
-W0702 16:30:16.125000 140327896655680 torch/distributed/run.py:757] *****************************************
-W0702 16:30:16.125000 140327896655680 torch/distributed/run.py:757] 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. 
-W0702 16:30:16.125000 140327896655680 torch/distributed/run.py:757] *****************************************
-W0702 16:30:16.135000 139775981082432 torch/distributed/run.py:757] 
-W0702 16:30:16.135000 139775981082432 torch/distributed/run.py:757] *****************************************
-W0702 16:30:16.135000 139775981082432 torch/distributed/run.py:757] 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. 
-W0702 16:30:16.135000 139775981082432 torch/distributed/run.py:757] *****************************************
-[default0]:[W socket.cpp:464] [c10d] The server socket has failed to bind to [::]:36391 (errno: 98 - Address already in use).
-[default0]:[W socket.cpp:464] [c10d] The server socket has failed to bind to ?UNKNOWN? (errno: 98 - Address already in use).
-[default0]:[E socket.cpp:500] [c10d] The server socket has failed to listen on any local network address.
-[default0]:Traceback (most recent call last):
-[default0]:  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 233, in <module>
-[default0]:    trainer = DistributedTrainer(config_file)
-[default0]:  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 145, in __init__
-[default0]:    self.parallel_context = ParallelContext(
-[default0]:  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/context.py", line 53, in __init__
-[default0]:    dist.initialize_torch_distributed()
-[default0]:  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/distributed.py", line 278, in initialize_torch_distributed
-[default0]:    dist.init_process_group(
-[default0]:  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/c10d_logger.py", line 75, in wrapper
-[default0]:    return func(*args, **kwargs)
-[default0]:  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/c10d_logger.py", line 89, in wrapper
-[default0]:    func_return = func(*args, **kwargs)
-[default0]:  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 1305, in init_process_group
-[default0]:    store, rank, world_size = next(rendezvous_iterator)
-[default0]:  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/rendezvous.py", line 246, in _env_rendezvous_handler
-[default0]:    store = _create_c10d_store(master_addr, master_port, rank, world_size, timeout, use_libuv)
-[default0]:  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/rendezvous.py", line 174, in _create_c10d_store
-[default0]:    return TCPStore(
-[default0]:torch.distributed.DistNetworkError: The server socket has failed to listen on any local network address. The server socket has failed to bind to [::]:36391 (errno: 98 - Address already in use). The server socket has failed to bind to ?UNKNOWN? (errno: 98 - Address already in use).
-W0702 16:30:27.302000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853935 closing signal SIGTERM
-W0702 16:30:27.303000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853936 closing signal SIGTERM
-W0702 16:30:27.303000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853937 closing signal SIGTERM
-W0702 16:30:27.303000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853938 closing signal SIGTERM
-W0702 16:30:27.303000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853939 closing signal SIGTERM
-W0702 16:30:27.303000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853940 closing signal SIGTERM
-W0702 16:30:27.304000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 853941 closing signal SIGTERM
-E0702 16:30:27.706000 140327896655680 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1) local_rank: 0 (pid: 853934) of binary: /fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/bin/python3.10
+W0702 19:59:45.097000 139860515530560 torch/distributed/run.py:757] 
+W0702 19:59:45.097000 139860515530560 torch/distributed/run.py:757] *****************************************
+W0702 19:59:45.097000 139860515530560 torch/distributed/run.py:757] 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. 
+W0702 19:59:45.097000 139860515530560 torch/distributed/run.py:757] *****************************************
+W0702 19:59:45.099000 139859587696448 torch/distributed/run.py:757] 
+W0702 19:59:45.099000 139859587696448 torch/distributed/run.py:757] *****************************************
+W0702 19:59:45.099000 139859587696448 torch/distributed/run.py:757] 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. 
+W0702 19:59:45.099000 139859587696448 torch/distributed/run.py:757] *****************************************
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Config:
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Config(general=GeneralArgs(project='bench_cluster',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            run='%date_%jobid',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            seed=42,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            step=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            consumed_train_samples=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            benchmark_csv_path=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            ignore_sanity_checks=True),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        parallelism=ParallelismArgs(dp=16,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    pp=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    tp=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    pp_engine=<nanotron.parallel.pipeline_parallel.engine.OneForwardOneBackwardPipelineEngine object at 0x7ff74a400910>,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    tp_mode=<TensorParallelLinearMode.REDUCE_SCATTER: 2>,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    tp_linear_async_communication=False,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    expert_parallel_size=1),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        model=ModelArgs(model_config=LlamaConfig(bos_token_id=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 eos_token_id=2,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 hidden_act='silu',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 hidden_size=2048,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 initializer_range=0.02,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 intermediate_size=4096,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 is_llama_config=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 max_position_embeddings=4096,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 num_attention_heads=32,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 num_hidden_layers=24,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 num_key_value_heads=32,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 pad_token_id=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 pretraining_tp=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 rms_norm_eps=1e-05,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 rope_scaling=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 rope_theta=10000.0,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 tie_word_embeddings=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 use_cache=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                 vocab_size=50257),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                        init_method=RandomInit(std=0.025),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                        dtype=torch.bfloat16,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                        make_vocab_size_divisible_by=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                        ddp_bucket_cap_mb=25),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        tokenizer=TokenizerArgs(tokenizer_name_or_path='openai-community/gpt2',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                tokenizer_revision=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                tokenizer_max_length=None),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        checkpoints=CheckpointsArgs(checkpoints_path=Path('/dev/null'),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    checkpoint_interval=100000,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    save_initial_state=False,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    resume_checkpoint_path=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                    checkpoints_path_is_shared_file_system=False),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        logging=LoggingArgs(log_level='info',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            log_level_replica='info',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                            iteration_step_info_interval=1),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        tokens=TokensArgs(sequence_length=4096,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          train_steps=20,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          micro_batch_size=2,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          batch_accumulation_per_replica=32,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          val_check_interval=-1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          limit_val_batches=0,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                          limit_test_batches=0),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        optimizer=OptimizerArgs(optimizer_factory=AdamWOptimizerArgs(adam_eps=1e-08,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                     adam_beta1=0.9,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                     adam_beta2=0.95,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                     torch_adam_is_fused=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                     name='adamW'),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                zero_stage=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                weight_decay=0.01,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                clip_grad=1.0,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                accumulate_grad_in_fp32=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                learning_rate_scheduler=LRSchedulerArgs(learning_rate=0.0001,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        lr_warmup_steps=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        lr_warmup_style='linear',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        lr_decay_style='linear',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        lr_decay_steps=19,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        lr_decay_starting_step=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                        min_decay_lr=1e-05)),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        data_stages=[DatasetStageArgs(name='Training Stage',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                      start_training_step=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                      data=DataArgs(dataset=PretrainDatasetsArgs(hf_dataset_or_datasets='roneneldan/TinyStories',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                                 hf_dataset_splits='train',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                                 hf_dataset_config_name=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                                 dataset_processing_num_proc_per_process=64,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                                 dataset_overwrite_cache=False,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                                                 text_column_name='text'),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                    seed=42,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:                                                    num_loading_workers=32))],
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        profiler=ProfilerArgs(profiler_export_path=Path('/fsx/ferdinandmom/ferdinand-hf/bench_cluster/results/llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2')),
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:        lighteval=None)
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Model Config:
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: LlamaConfig(bos_token_id=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             eos_token_id=2,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             hidden_act='silu',
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             hidden_size=2048,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             initializer_range=0.02,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             intermediate_size=4096,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             is_llama_config=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             max_position_embeddings=4096,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             num_attention_heads=32,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             num_hidden_layers=24,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             num_key_value_heads=32,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             pad_token_id=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             pretraining_tp=1,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             rms_norm_eps=1e-05,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             rope_scaling=None,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             rope_theta=10000.0,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             tie_word_embeddings=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             use_cache=True,
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:             vocab_size=50257)
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Building model..
+[default0]:07/02/2024 20:00:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Setting PP block ranks...
+[default4]:07/02/2024 20:00:11 [INFO|DP=12|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default5]:07/02/2024 20:00:11 [INFO|DP=13|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default6]:07/02/2024 20:00:11 [INFO|DP=14|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default1]:07/02/2024 20:00:11 [INFO|DP=9|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default2]:07/02/2024 20:00:11 [INFO|DP=10|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default3]:07/02/2024 20:00:11 [INFO|DP=11|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default0]:07/02/2024 20:00:11 [INFO|DP=8|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default7]:07/02/2024 20:00:11 [INFO|DP=15|PP=0|TP=0|ip-26-0-163-226]: No checkpoint path provided.
+[default0]:07/02/2024 20:00:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Total number of parameters: 1.11G (2116.51MiB)
+[default0]:07/02/2024 20:00:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Local number of parameters: 1.11G (2116.51MiB)
+[default0]:07/02/2024 20:00:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [After model building] Memory usage: 2140.53MiB. Peak allocated: 2338.88MiB Peak reserved: 2392.00MiB
+[default0]:07/02/2024 20:00:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default0]:07/02/2024 20:00:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Parametrizing model parameters using StandardParametrizator
+[default2]:07/02/2024 20:00:11 [INFO|DP=2|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default1]:07/02/2024 20:00:11 [INFO|DP=1|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default4]:07/02/2024 20:00:11 [INFO|DP=4|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default6]:07/02/2024 20:00:11 [INFO|DP=6|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default5]:07/02/2024 20:00:11 [INFO|DP=5|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default7]:07/02/2024 20:00:11 [INFO|DP=7|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default3]:07/02/2024 20:00:11 [INFO|DP=3|PP=0|TP=0|ip-26-0-163-147]: No checkpoint path provided.
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [Optimizer Building] Using LearningRateForSP as learning rate
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] Size of optimizer params per rank:
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 0 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 1 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 2 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 3 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 4 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 5 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 6 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 7 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 8 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 9 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 10 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 11 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 12 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 13 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 14 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [ZeRO sharding] DP Rank 15 has 69.4M out of 1.11G (6.25%) params' optimizer states
+[default0]:07/02/2024 20:00:21 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [Training Plan] Stage Training Stage has 19 remaining training steps and has consumed 0 samples
+[default0]:07/02/2024 20:00:21 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Using `datasets` library
+[default0]:07/02/2024 20:00:21 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Loading tokenizer from openai-community/gpt2 and transformers/hf_hub versions ('4.41.2', '0.23.4')
+[default0]:07/02/2024 20:00:22 [WARNING|DP=0|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default0]:Repo card metadata block was not found. Setting CardData to empty.
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [Training Plan] There are 1 training stages 
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [Stage Training Stage] start from step 1 
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: 
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: [Start training] datetime: 2024-07-02 20:00:23.244810 | mbs: 2 | grad_accum: 32 | global_batch_size: 1024 | sequence_length: 4096 | train_steps: 20 | start_iteration_step: 0 | consumed_train_samples: 0
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: Resuming training from stage Training Stage, it has trained for 0 samples and has 19 remaining train steps
+[default0]:07/02/2024 20:00:23 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 6639.09MiB. Peak allocated 6639.09MiB. Peak reserved: 6892.00MiB
+[default0]:07/02/2024 20:00:23 [WARNING|DP=8|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default1]:07/02/2024 20:00:23 [WARNING|DP=9|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default3]:07/02/2024 20:00:23 [WARNING|DP=11|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default6]:07/02/2024 20:00:23 [WARNING|DP=14|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default4]:07/02/2024 20:00:23 [WARNING|DP=12|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default5]:07/02/2024 20:00:23 [WARNING|DP=13|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default4]:Repo card metadata block was not found. Setting CardData to empty.
+[default0]:Repo card metadata block was not found. Setting CardData to empty.
+[default7]:07/02/2024 20:00:23 [WARNING|DP=15|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default7]:Repo card metadata block was not found. Setting CardData to empty.
+[default6]:Repo card metadata block was not found. Setting CardData to empty.
+[default1]:Repo card metadata block was not found. Setting CardData to empty.
+[default3]:Repo card metadata block was not found. Setting CardData to empty.
+[default1]:07/02/2024 20:00:23 [WARNING|DP=1|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default3]:07/02/2024 20:00:23 [WARNING|DP=3|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default4]:07/02/2024 20:00:23 [WARNING|DP=4|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default5]:Repo card metadata block was not found. Setting CardData to empty.
+[default7]:Repo card metadata block was not found. Setting CardData to empty.
+[default6]:Repo card metadata block was not found. Setting CardData to empty.
+[default7]:07/02/2024 20:00:23 [WARNING|DP=7|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default4]:Repo card metadata block was not found. Setting CardData to empty.
+[default6]:07/02/2024 20:00:23 [WARNING|DP=6|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default1]:Repo card metadata block was not found. Setting CardData to empty.
+[default3]:Repo card metadata block was not found. Setting CardData to empty.
+[default2]:07/02/2024 20:00:23 [WARNING|DP=10|PP=0|TP=0|ip-26-0-163-226]: Repo card metadata block was not found. Setting CardData to empty.
+[default2]:Repo card metadata block was not found. Setting CardData to empty.
+[default5]:07/02/2024 20:00:23 [WARNING|DP=5|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default5]:Repo card metadata block was not found. Setting CardData to empty.
+[default0]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default0]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default4]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default4]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default2]:07/02/2024 20:00:28 [WARNING|DP=2|PP=0|TP=0|ip-26-0-163-147]: Repo card metadata block was not found. Setting CardData to empty.
+[default2]:Repo card metadata block was not found. Setting CardData to empty.
+[default4]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default4]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default3]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default3]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default1]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default1]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default3]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default3]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default6]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default6]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default5]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default5]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default6]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default6]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default1]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default1]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default7]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default7]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default7]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default7]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default5]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default5]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default0]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default0]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default2]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default2]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default2]:/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: c10d::allreduce_: an autograd kernel was not registered to the Autograd key(s) but we are trying to backprop through it. This may lead to silently incorrect behavior. This behavior is deprecated and will be removed in a future version of PyTorch. If your operator is differentiable, please ensure you have registered an autograd kernel to the correct Autograd key (e.g. DispatchKey::Autograd, DispatchKey::CompositeImplicitAutograd). If your operator is not differentiable, or to squash this warning and use the previous behavior, please register torch::CppFunction::makeFallthrough() to DispatchKey::Autograd. (Triggered internally at ../torch/csrc/autograd/autograd_not_implemented_fallback.cpp:63.)
+[default2]:  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+[default0]:07/02/2024 20:00:34 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 6715.25MiB. Peak allocated 24538.23MiB. Peak reserved: 25402.00MiB
+[default0]:07/02/2024 20:00:42 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 1 / 20 | consumed_tokens: 4.19M | elapsed_time_per_iteration_ms: 18.9K | tokens_per_sec: 222K | tokens_per_sec_per_gpu: 13.9K | global_batch_size: 1.02K | lm_loss: 11.3 | lr: 0.0001 | model_tflops_per_gpu: 126 | hardware_tflops_per_gpu: 126 | grad_norm: 33.1 | cuda_memory_allocated: 7.6G | cuda_max_memory_reserved: 28.9G | hd_total_memory_tb: 312G | hd_used_memory_tb: 68.6G | hd_free_memory_tb: 244G
+[default0]:07/02/2024 20:00:42 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 11617.74MiB. Peak reserved: 27544.00MiB
+[default0]:07/02/2024 20:00:49 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.46MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:00:51 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 2 / 20 | consumed_tokens: 8.39M | elapsed_time_per_iteration_ms: 9.35K | tokens_per_sec: 449K | tokens_per_sec_per_gpu: 28K | global_batch_size: 1.02K | lm_loss: 11.3 | lr: 9.53e-05 | model_tflops_per_gpu: 254 | hardware_tflops_per_gpu: 254 | grad_norm: 33.3 | cuda_memory_allocated: 7.6G | cuda_max_memory_reserved: 28.9G | hd_total_memory_tb: 312G | hd_used_memory_tb: 68.6G | hd_free_memory_tb: 244G
+[default0]:07/02/2024 20:00:51 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 11617.76MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:00:58 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.46MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:01:00 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 3 / 20 | consumed_tokens: 12.6M | elapsed_time_per_iteration_ms: 9.08K | tokens_per_sec: 462K | tokens_per_sec_per_gpu: 28.9K | global_batch_size: 1.02K | lm_loss: 16 | lr: 9.05e-05 | model_tflops_per_gpu: 262 | hardware_tflops_per_gpu: 262 | grad_norm: 249 | cuda_memory_allocated: 7.6G | cuda_max_memory_reserved: 28.9G | hd_total_memory_tb: 312G | hd_used_memory_tb: 68.6G | hd_free_memory_tb: 244G
+[default0]:07/02/2024 20:01:00 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 11617.76MiB. Peak reserved: 27568.00MiB
+[default0]:STAGE:2024-07-02 20:01:00 704351:704351 ActivityProfilerController.cpp:314] Completed Stage: Warm Up
+[default0]:07/02/2024 20:01:08 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.46MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:01:10 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 4 / 20 | consumed_tokens: 16.8M | elapsed_time_per_iteration_ms: 9.64K | tokens_per_sec: 435K | tokens_per_sec_per_gpu: 27.2K | global_batch_size: 1.02K | lm_loss: 15.1 | lr: 8.58e-05 | model_tflops_per_gpu: 247 | hardware_tflops_per_gpu: 247 | grad_norm: 41.6 | cuda_memory_allocated: 7.6G | cuda_max_memory_reserved: 28.9G | hd_total_memory_tb: 312G | hd_used_memory_tb: 68.6G | hd_free_memory_tb: 244G
+[default0]:07/02/2024 20:01:10 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 11617.76MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:01:19 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 5 / 20 | consumed_tokens: 21M | elapsed_time_per_iteration_ms: 9.5K | tokens_per_sec: 441K | tokens_per_sec_per_gpu: 27.6K | global_batch_size: 1.02K | lm_loss: 10.8 | lr: 8.11e-05 | model_tflops_per_gpu: 250 | hardware_tflops_per_gpu: 250 | grad_norm: 25.9
+[default0]:07/02/2024 20:01:19 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:01:29 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 6 / 20 | consumed_tokens: 25.2M | elapsed_time_per_iteration_ms: 9.73K | tokens_per_sec: 431K | tokens_per_sec_per_gpu: 26.9K | global_batch_size: 1.02K | lm_loss: 10.8 | lr: 7.63e-05 | model_tflops_per_gpu: 244 | hardware_tflops_per_gpu: 244 | grad_norm: 18.9
+[default0]:STAGE:2024-07-02 20:01:47 704351:704351 ActivityProfilerController.cpp:320] Completed Stage: Collection
+[default0]:STAGE:2024-07-02 20:01:49 704351:704351 ActivityProfilerController.cpp:324] Completed Stage: Post Processing
+[default0]:07/02/2024 20:03:59 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:08 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 7 / 20 | consumed_tokens: 29.4M | elapsed_time_per_iteration_ms: 8.9K | tokens_per_sec: 471K | tokens_per_sec_per_gpu: 29.5K | global_batch_size: 1.02K | lm_loss: 10.2 | lr: 7.16e-05 | model_tflops_per_gpu: 267 | hardware_tflops_per_gpu: 267 | grad_norm: 7.97
+[default0]:07/02/2024 20:04:08 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:17 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 8 / 20 | consumed_tokens: 33.6M | elapsed_time_per_iteration_ms: 8.86K | tokens_per_sec: 473K | tokens_per_sec_per_gpu: 29.6K | global_batch_size: 1.02K | lm_loss: 9.15 | lr: 6.68e-05 | model_tflops_per_gpu: 268 | hardware_tflops_per_gpu: 268 | grad_norm: 6.46
+[default0]:07/02/2024 20:04:17 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:26 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 9 / 20 | consumed_tokens: 37.7M | elapsed_time_per_iteration_ms: 9.08K | tokens_per_sec: 462K | tokens_per_sec_per_gpu: 28.9K | global_batch_size: 1.02K | lm_loss: 11.2 | lr: 6.21e-05 | model_tflops_per_gpu: 262 | hardware_tflops_per_gpu: 262 | grad_norm: 59.7
+[default0]:07/02/2024 20:04:26 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:35 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 10 / 20 | consumed_tokens: 41.9M | elapsed_time_per_iteration_ms: 9.13K | tokens_per_sec: 459K | tokens_per_sec_per_gpu: 28.7K | global_batch_size: 1.02K | lm_loss: 9.6 | lr: 5.74e-05 | model_tflops_per_gpu: 260 | hardware_tflops_per_gpu: 260 | grad_norm: 44.2
+[default0]:07/02/2024 20:04:35 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:44 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 11 / 20 | consumed_tokens: 46.1M | elapsed_time_per_iteration_ms: 9.39K | tokens_per_sec: 447K | tokens_per_sec_per_gpu: 27.9K | global_batch_size: 1.02K | lm_loss: 8.08 | lr: 5.26e-05 | model_tflops_per_gpu: 253 | hardware_tflops_per_gpu: 253 | grad_norm: 8.69
+[default0]:07/02/2024 20:04:44 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:04:53 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 12 / 20 | consumed_tokens: 50.3M | elapsed_time_per_iteration_ms: 8.91K | tokens_per_sec: 471K | tokens_per_sec_per_gpu: 29.4K | global_batch_size: 1.02K | lm_loss: 7.86 | lr: 4.79e-05 | model_tflops_per_gpu: 267 | hardware_tflops_per_gpu: 267 | grad_norm: 5.1
+[default0]:07/02/2024 20:04:53 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 13 / 20 | consumed_tokens: 54.5M | elapsed_time_per_iteration_ms: 9.06K | tokens_per_sec: 463K | tokens_per_sec_per_gpu: 28.9K | global_batch_size: 1.02K | lm_loss: 7.7 | lr: 4.32e-05 | model_tflops_per_gpu: 263 | hardware_tflops_per_gpu: 263 | grad_norm: 4.73
+[default0]:07/02/2024 20:05:02 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 14 / 20 | consumed_tokens: 58.7M | elapsed_time_per_iteration_ms: 9.03K | tokens_per_sec: 464K | tokens_per_sec_per_gpu: 29K | global_batch_size: 1.02K | lm_loss: 7.56 | lr: 3.84e-05 | model_tflops_per_gpu: 263 | hardware_tflops_per_gpu: 263 | grad_norm: 5.09
+[default0]:07/02/2024 20:05:11 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 15 / 20 | consumed_tokens: 62.9M | elapsed_time_per_iteration_ms: 9.03K | tokens_per_sec: 464K | tokens_per_sec_per_gpu: 29K | global_batch_size: 1.02K | lm_loss: 7.4 | lr: 3.37e-05 | model_tflops_per_gpu: 263 | hardware_tflops_per_gpu: 263 | grad_norm: 5.16
+[default0]:07/02/2024 20:05:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:29 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 16 / 20 | consumed_tokens: 67.1M | elapsed_time_per_iteration_ms: 9.27K | tokens_per_sec: 453K | tokens_per_sec_per_gpu: 28.3K | global_batch_size: 1.02K | lm_loss: 7.3 | lr: 2.89e-05 | model_tflops_per_gpu: 257 | hardware_tflops_per_gpu: 257 | grad_norm: 5.15
+[default0]:07/02/2024 20:05:29 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:39 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 17 / 20 | consumed_tokens: 71.3M | elapsed_time_per_iteration_ms: 9.24K | tokens_per_sec: 454K | tokens_per_sec_per_gpu: 28.4K | global_batch_size: 1.02K | lm_loss: 7.22 | lr: 2.42e-05 | model_tflops_per_gpu: 258 | hardware_tflops_per_gpu: 258 | grad_norm: 5.14
+[default0]:07/02/2024 20:05:39 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:48 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 18 / 20 | consumed_tokens: 75.5M | elapsed_time_per_iteration_ms: 9.12K | tokens_per_sec: 460K | tokens_per_sec_per_gpu: 28.8K | global_batch_size: 1.02K | lm_loss: 7.15 | lr: 1.95e-05 | model_tflops_per_gpu: 261 | hardware_tflops_per_gpu: 261 | grad_norm: 5.04
+[default0]:07/02/2024 20:05:48 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:05:57 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 19 / 20 | consumed_tokens: 79.7M | elapsed_time_per_iteration_ms: 9.11K | tokens_per_sec: 460K | tokens_per_sec_per_gpu: 28.8K | global_batch_size: 1.02K | lm_loss: 7.08 | lr: 1.47e-05 | model_tflops_per_gpu: 261 | hardware_tflops_per_gpu: 261 | grad_norm: 3.86
+[default0]:07/02/2024 20:05:57 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]:  Memory usage: 7252.45MiB. Peak allocated 25075.44MiB. Peak reserved: 27568.00MiB
+[default0]:07/02/2024 20:06:06 [INFO|DP=0|PP=0|TP=0|ip-26-0-163-147]: iteration: 20 / 20 | consumed_tokens: 83.9M | elapsed_time_per_iteration_ms: 8.99K | tokens_per_sec: 467K | tokens_per_sec_per_gpu: 29.2K | global_batch_size: 1.02K | lm_loss: 7.03 | lr: 1e-05 | model_tflops_per_gpu: 265 | hardware_tflops_per_gpu: 265 | grad_norm: 2.94
 Traceback (most recent call last):
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/bin/torchrun", line 8, in <module>
-    sys.exit(main())
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
-    return f(*args, **kwargs)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
-    run(args)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
-    elastic_launch(
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
-    return launch_agent(self._config, self._entrypoint, list(args))
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 263, in launch_agent
-    raise ChildFailedError(
-torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
-============================================================
-/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py FAILED
-------------------------------------------------------------
-Failures:
-  <NO_OTHER_FAILURES>
-------------------------------------------------------------
-Root Cause (first observed failure):
-[0]:
-  time      : 2024-07-02_16:30:27
-  host      : ip-26-0-163-43.ec2.internal
-  rank      : 0 (local_rank: 0)
-  exitcode  : 1 (pid: 853934)
-  error_file: <N/A>
-  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
-============================================================
-srun: error: ip-26-0-163-43: task 0: Exited with exit code 1
-W0702 16:30:31.395000 139770314262272 torch/distributed/elastic/rendezvous/dynamic_rendezvous.py:1252] The node 'ip-26-0-169-207.ec2.internal_2422832_0' has failed to send a keep-alive heartbeat to the rendezvous 'none' due to an error of type RendezvousConnectionError.
-W0702 16:30:32.306000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422901 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422902 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422903 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422904 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422905 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422906 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422907 closing signal SIGTERM
-W0702 16:30:32.307000 139775981082432 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 2422908 closing signal SIGTERM
-W0702 16:30:32.813000 139775981082432 torch/distributed/elastic/rendezvous/dynamic_rendezvous.py:1203] The node 'ip-26-0-169-207.ec2.internal_2422832_0' has failed to shutdown the rendezvous 'none' due to an error of type RendezvousConnectionError.
-W0702 16:30:32.820000 139775981082432 torch/distributed/elastic/rendezvous/dynamic_rendezvous.py:1203] The node 'ip-26-0-169-207.ec2.internal_2422832_0' has failed to shutdown the rendezvous 'none' due to an error of type RendezvousConnectionError.
+  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/main.py", line 4, in <module>
+    from bench_cluster.submit_jobs import submit_jobs, check_status
+ImportError: cannot import name 'check_status' from 'bench_cluster.submit_jobs' (/fsx/ferdinandmom/ferdinand-hf/bench_cluster/bench_cluster/submit_jobs.py)
 Traceback (most recent call last):
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py", line 113, in _call_store
-    return getattr(self._store, store_op)(*args, **kwargs)
-torch.distributed.DistNetworkError: Broken pipe
-
-The above exception was the direct cause of the following exception:
-
-Traceback (most recent call last):
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/bin/torchrun", line 8, in <module>
-    sys.exit(main())
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
-    return f(*args, **kwargs)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
-    run(args)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
-    elastic_launch(
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
-    return launch_agent(self._config, self._entrypoint, list(args))
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 254, in launch_agent
-    result = agent.run()
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 123, in wrapper
-    result = f(*args, **kwargs)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 733, in run
-    result = self._invoke_run(role)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 908, in _invoke_run
-    num_nodes_waiting = rdzv_handler.num_nodes_waiting()
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py", line 1174, in num_nodes_waiting
-    self._state_holder.sync()
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py", line 419, in sync
-    get_response = self._backend.get_state()
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py", line 73, in get_state
-    base64_state: bytes = self._call_store("get", self._key)
-  File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py", line 115, in _call_store
-    raise RendezvousConnectionError(
-torch.distributed.elastic.rendezvous.api.RendezvousConnectionError: The connection to the C10d store has failed. See inner exception for details.
-srun: error: ip-26-0-169-207: task 1: Exited with exit code 1
+  File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/main.py", line 4, in <module>
+    from bench_cluster.submit_jobs import submit_jobs, check_status
+ImportError: cannot import name 'check_status' from 'bench_cluster.submit_jobs' (/fsx/ferdinandmom/ferdinand-hf/bench_cluster/bench_cluster/submit_jobs.py)
 Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.
+

llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2/profiler/ip-26-0-163-147_704351.1719950608420005259.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca10a77173217c1d6842b282b1881e21564f87670ab7e2ad71d5f3b9a24f517f
+size 4331528811

llama-1B/16_GPUS/dp-16_tp-1_pp-1_mbz-2/status.txt

@@ -1 +1 @@
-fail
+completed