| 01/04/2024 10:04:05 - WARNING - llmtuner.model.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training. | |
| [INFO|training_args.py:1838] 2024-01-04 10:04:05,581 >> PyTorch: setting up devices | |
| /home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead. | |
| warnings.warn( | |
| 01/04/2024 10:04:05 - INFO - llmtuner.model.parser - Process rank: 0, device: cuda:0, n_gpu: 1 | |
| distributed training: True, compute dtype: None | |
| 01/04/2024 10:04:05 - INFO - llmtuner.model.parser - Training/evaluation parameters Seq2SeqTrainingArguments( | |
| _n_gpu=1, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| ddp_backend=None, | |
| ddp_broadcast_buffers=None, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=False, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| dispatch_batches=None, | |
| do_eval=False, | |
| do_predict=True, | |
| do_train=False, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=None, | |
| evaluation_strategy=IntervalStrategy.NO, | |
| fp16=False, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| generation_config=None, | |
| generation_max_length=None, | |
| generation_num_beams=None, | |
| gradient_accumulation_steps=1, | |
| gradient_checkpointing=False, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=None, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| include_num_input_tokens_seen=False, | |
| include_tokens_per_second=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=5e-05, | |
| length_column_name=length, | |
| load_best_model_at_end=False, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=./models/sft/dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1-lora/Predict_20/runs/Jan04_10-04-05_yhyu13fuwuqi, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.LINEAR, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=3.0, | |
| optim=OptimizerNames.ADAMW_TORCH, | |
| optim_args=None, | |
| output_dir=./models/sft/dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1-lora/Predict_20, | |
| overwrite_output_dir=False, | |
| past_index=-1, | |
| per_device_eval_batch_size=1, | |
| per_device_train_batch_size=8, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['tensorboard'], | |
| resume_from_checkpoint=None, | |
| run_name=./models/sft/dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1-lora/Predict_20, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=IntervalStrategy.STEPS, | |
| save_total_limit=None, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| split_batches=False, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_cpu=False, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=0, | |
| weight_decay=0.0, | |
| ) | |
| 01/04/2024 10:04:05 - INFO - llmtuner.data.loader - Loading dataset ./glaive-function-calling-v2/simple-function-calling-v2_converted.json... | |
| 01/04/2024 10:04:05 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| Using custom data configuration default-b024aadef2a1493c | |
| Loading Dataset Infos from /home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/datasets/packaged_modules/json | |
| Overwrite dataset info from restored data version if exists. | |
| Loading Dataset info from /home/hangyu5/.cache/huggingface/datasets/json/default-b024aadef2a1493c/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96 | |
| Found cached dataset json (/home/hangyu5/.cache/huggingface/datasets/json/default-b024aadef2a1493c/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96) | |
| Loading Dataset info from /home/hangyu5/.cache/huggingface/datasets/json/default-b024aadef2a1493c/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96 | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file vocab.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file merges.txt | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file added_tokens.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-01-04 10:04:06,381 >> loading file tokenizer.json | |
| [WARNING|logging.py:314] 2024-01-04 10:04:06,448 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|configuration_utils.py:737] 2024-01-04 10:04:06,448 >> loading configuration file cognitivecomputations/dolphin-2_6-phi-2/config.json | |
| [INFO|configuration_utils.py:737] 2024-01-04 10:04:06,449 >> loading configuration file cognitivecomputations/dolphin-2_6-phi-2/config.json | |
| [INFO|configuration_utils.py:802] 2024-01-04 10:04:06,450 >> Model config PhiConfig { | |
| "_name_or_path": "cognitivecomputations/dolphin-2_6-phi-2", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "PhiForCausalLM" | |
| ], | |
| "attn_pdrop": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_phi.PhiConfig", | |
| "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM" | |
| }, | |
| "embd_pdrop": 0.0, | |
| "flash_attn": false, | |
| "flash_rotary": false, | |
| "fused_dense": false, | |
| "img_processor": null, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "phi-msft", | |
| "n_embd": 2560, | |
| "n_head": 32, | |
| "n_head_kv": null, | |
| "n_inner": null, | |
| "n_layer": 32, | |
| "n_positions": 2048, | |
| "resid_pdrop": 0.1, | |
| "rotary_dim": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": false, | |
| "vocab_size": 51200 | |
| } | |
| [INFO|modeling_utils.py:3341] 2024-01-04 10:04:06,482 >> loading weights file cognitivecomputations/dolphin-2_6-phi-2/model.safetensors.index.json | |
| [INFO|configuration_utils.py:826] 2024-01-04 10:04:06,483 >> Generate config GenerationConfig { | |
| "use_cache": false | |
| } | |
| [INFO|configuration_utils.py:826] 2024-01-04 10:04:06,483 >> Generate config GenerationConfig { | |
| "use_cache": false | |
| } | |
| Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]cognitivecomputations/dolphin-2_6-phi-2 | |
| Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.41it/s] | |
| Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.34it/s] | |
| Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.13it/s]cognitivecomputations/dolphin-2_6-phi-2 | |
| [WARNING|modeling_utils.py:4175] 2024-01-04 10:04:07,704 >> Some weights of the model checkpoint at ./models/dolphin-2_6-phi-2 were not used when initializing PhiForCausalLM: ['lm_head.linear.lora_B.default.weight', 'lm_head.linear.lora_A.default.weight'] | |
| - This IS expected if you are initializing PhiForCausalLM from the checkpoint of a modelcognitivecomputations/dolphin-2_6-phi-2r with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). | |
| - This IS NOT expected if you are initializing PhiForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). | |
| [INFO|modeling_utils.py:4193] 2024-01-04 10:04:07,704 >> All the weights of PhiForCausalLM were initialized from the model checkpoint at ./models/dolphin-2_6-phi-2. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use PhiForCausalLM for predictions without further training. | |
| [INFO|configuration_utils.py:779] 2024-01-04 10:04:07,707 >> loading configuration file ./models/dolphin-2_6-phi-2/generation_config.json | |
| [INFO|configuration_utils.py:826] 2024-01-04 10:04:07,707 >> Generate config GenerationConfig {} | |
| 01/04/2024 10:04:08 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 01/04/2024 10:04:09 - INFO - llmtuner.model.adapter - Merged 1 adapter(s). | |
| 01/04/2024 10:04:09 - INFO - llmtuner.model.adapter - Loaded adapter(s): ./models/sft/dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1-lora | |
| 01/04/2024 10:04:09 - INFO - llmtuner.model.loader - trainable params: 0 || all params: 2779683840 || trainable%: 0.0000 | |
| 01/04/2024 10:04:09 - INFO - llmtuner.model.loader - This IS expected that the trainable params is 0 if you are using model for inference only. | |
| Running tokenizer on dataset: 0%| | 0/20 [00:00<?, ? examples/s]Caching processed dataset at /home/hangyu5/.cache/huggingface/datasets/json/default-b024aadef2a1493c/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-c7eb5697298b6539.arrow | |
| Running tokenizer on dataset: 100%|██████████| 20/20 [00:00<00:00, 360.26 examples/s] | |
| [INFO|training_args.py:1838] 2024-01-04 10:04:09,995 >> PyTorch: setting up devices | |
| [INFO|trainer.py:3166] 2024-01-04 10:04:10,639 >> ***** Running Prediction ***** | |
| [INFO|trainer.py:3168] 2024-01-04 10:04:10,639 >> Num examples = 20 | |
| [INFO|trainer.py:3171] 2024-01-04 10:04:10,639 >> Batch size = 1 | |
| [INFO|configuration_utils.py:826] 2024-01-04 10:04:10,651 >> Generate config GenerationConfig { | |
| "use_cache": false | |
| } | |
| /home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/generation/utils.py:1518: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration ) | |
| warnings.warn( | |
| input_ids: | |
| [32, 8537, 1022, 257, 11040, 2836, 290, 281, 11666, 4430, 8796, 13, 383, 8796, 3607, 7613, 11, 6496, 11, 290, 23507, 7429, 284, 262, 2836, 338, 2683, 13, 198, 20490, 25, 36230, 25, 921, 389, 257, 7613, 8796, 351, 1895, 284, 262, 1708, 5499, 13, 5765, 606, 611, 2672, 532, 198, 90, 198, 50284, 1, 3672, 1298, 366, 1136, 62, 1069, 3803, 62, 4873, 1600, 198, 50284, 1, 11213, 1298, 366, 3855, 262, 5163, 2494, 1022, 734, 19247, 1600, 198, 50284, 1, 17143, 7307, 1298, 1391, 198, 50280, 1, 4906, 1298, 366, 15252, 1600, 198, 50280, 1, 48310, 1298, 1391, 198, 50276, 1, 8692, 62, 34415, 1298, 1391, 198, 50272, 1, 4906, 1298, 366, 8841, 1600, 198, 50272, 1, 11213, 1298, 366, 464, 7395, 284, 10385, 422, 1, 198, 50276, 5512, 198, 50276, 1, 16793, 62, 34415, 1298, 1391, 198, 50272, 1, 4906, 1298, 366, 8841, 1600, 198, 50272, 1, 11213, 1298, 366, 464, 7395, 284, 10385, 284, 1, 198, 50276, 92, 198, 50280, 5512, 198, 50280, 1, 35827, 1298, 685, 198, 50276, 1, 8692, 62, 34415, 1600, 198, 50276, 1, 16793, 62, 34415, 1, 198, 50280, 60, 198, 50284, 92, 198, 92, 198, 198, 6090, 345, 1492, 257, 5474, 329, 502, 422, 968, 1971, 284, 3576, 30, 198, 48902, 25] | |
| inputs: | |
| A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. | |
| Human: SYSTEM: You are a helpful assistant with access to the following functions. Use them if required - | |
| { | |
| "name": "get_exchange_rate", | |
| "description": "Get the exchange rate between two currencies", | |
| "parameters": { | |
| "type": "object", | |
| "properties": { | |
| "base_currency": { | |
| "type": "string", | |
| "description": "The currency to convert from" | |
| }, | |
| "target_currency": { | |
| "type": "string", | |
| "description": "The currency to convert to" | |
| } | |
| }, | |
| "required": [ | |
| "base_currency", | |
| "target_currency" | |
| ] | |
| } | |
| } | |
| Can you book a flight for me from New York to London? | |
| Assistant: | |
| 0%| | 0/20 [00:00<?, ?it/s] | |
| 10%|█ | 2/20 [00:01<00:11, 1.56it/s] | |
| 15%|█▌ | 3/20 [00:03<00:19, 1.15s/it] | |
| 20%|██ | 4/20 [00:04<00:20, 1.26s/it] | |
| 25%|██▌ | 5/20 [00:07<00:25, 1.67s/it] | |
| 30%|███ | 6/20 [00:07<00:19, 1.38s/it] | |
| 35%|███▌ | 7/20 [00:09<00:18, 1.45s/it] | |
| 40%|████ | 8/20 [00:10<00:17, 1.47s/it] | |
| 45%|████▌ | 9/20 [00:12<00:15, 1.39s/it] | |
| 50%|█████ | 10/20 [00:13<00:15, 1.51s/it] | |
| 55%|█████▌ | 11/20 [00:14<00:11, 1.29s/it] | |
| 60%|██████ | 12/20 [00:15<00:09, 1.13s/it] | |
| 65%|██████▌ | 13/20 [00:17<00:09, 1.35s/it] | |
| 70%|███████ | 14/20 [00:18<00:07, 1.29s/it] | |
| 75%|███████▌ | 15/20 [00:20<00:07, 1.49s/it] | |
| 80%|████████ | 16/20 [00:21<00:04, 1.25s/it] | |
| 85%|████████▌ | 17/20 [00:22<00:03, 1.17s/it] | |
| 90%|█████████ | 18/20 [00:24<00:02, 1.40s/it] | |
| 95%|█████████▌| 19/20 [00:24<00:01, 1.14s/it] | |
| 100%|██████████| 20/20 [00:26<00:00, 1.34s/it]Building prefix dict from the default dictionary ... | |
| Loading model from cache /tmp/jieba.cache | |
| Loading model cost 0.697 seconds. | |
| Prefix dict has been built successfully. | |
| 100%|██████████| 20/20 [00:27<00:00, 1.36s/it] | |
| ***** predict metrics ***** | |
| predict_bleu-4 = 74.1969 | |
| predict_rouge-1 = 80.3725 | |
| predict_rouge-2 = 70.3403 | |
| predict_rouge-l = 77.7235 | |
| predict_runtime = 0:00:29.41 | |
| predict_samples_per_second = 0.68 | |
| predict_steps_per_second = 0.68 | |
| 01/04/2024 10:04:40 - INFO - llmtuner.train.sft.trainer - Saving prediction results to ./models/sft/dolphin-2_6-phi-2-sft-glaive-function-calling-v2-ep1-lora/Predict_20/generated_predictions.jsonl | |