| 09/02/2024 09:22:37 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False | |
| 09/02/2024 09:22:37 - INFO - __main__ - Training parameters TrainingArguments( | |
| _n_gpu=1, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| analysis_dataset=bbh, | |
| analysis_mode=False, | |
| auto_find_batch_size=False, | |
| bf16=True, | |
| bf16_full_eval=False, | |
| data_seed=9, | |
| 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=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| dispatch_batches=None, | |
| do_eval=False, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=None, | |
| evaluation_strategy=no, | |
| fp16=False, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[<FSDPOption.FULL_SHARD: 'full_shard'>, <FSDPOption.AUTO_WRAP: 'auto_wrap'>], | |
| fsdp_config={'fsdp_transformer_layer_cls_to_wrap': ['LlamaDecoderLayer'], 'fsdp_backward_prefetch': 'backward_pre', 'limit_all_gathers': 'true', 'use_orig_params': 'true', '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, | |
| gradient_accumulation_steps=32, | |
| 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=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=2e-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=../out/llama2-7b-p0.05-lora-seed9/runs/Sep02_09-22-37_dlc19oe6tjflhwaw-master-0, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=1.0, | |
| logging_strategy=steps, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=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=4.0, | |
| optim=adamw_torch, | |
| optim_args=None, | |
| output_dir=../out/llama2-7b-p0.05-lora-seed9, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=1, | |
| 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=['wandb'], | |
| resume_from_checkpoint=None, | |
| run_name=../out/llama2-7b-p0.05-lora-seed9, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=500, | |
| save_strategy=epoch, | |
| save_total_limit=None, | |
| seed=0, | |
| skip_memory_metrics=True, | |
| split_batches=False, | |
| tf32=False, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| train_dataset_names=None, | |
| use_cpu=False, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.03, | |
| warmup_steps=0, | |
| weight_decay=0.0, | |
| ) | |
| 09/02/2024 09:22:37 - INFO - __main__ - Model parameters ModelArguments(model_name_or_path='/mnt/data_large/ccy/Llama-2-7b-hf', config_name=None, tokenizer_name=None, cache_dir=None, use_fast_tokenizer=True, model_revision='main', use_auth_token=False, torch_dtype=None, lora=True, lora_r=128, lora_alpha=512.0, lora_dropout=0.1, lora_target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj']) | |
| 09/02/2024 09:22:37 - INFO - __main__ - Dataset parameters DataArguments(train_files=['./data/train/processed/flan_v2/flan_v2_data.jsonl', './data/train/processed/cot/cot_data.jsonl', './data/train/processed/dolly/dolly_data.jsonl', './data/train/processed/oasst1/oasst1_data.jsonl'], overwrite_cache=False, preprocessing_num_workers=None, max_seq_length=2048, sample_data_seed=42, percentage=0.05) | |
| [INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer.model | |
| [INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file added_tokens.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2024] 2024-09-02 09:22:37,635 >> loading file tokenizer_config.json | |
| Using custom data configuration default-f9134d95c1961a9a | |
| 09/02/2024 09:22:38 - INFO - datasets.builder - Using custom data configuration default-f9134d95c1961a9a | |
| Loading Dataset Infos from /home/pai/envs/less/lib/python3.10/site-packages/datasets/packaged_modules/json | |
| 09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset Infos from /home/pai/envs/less/lib/python3.10/site-packages/datasets/packaged_modules/json | |
| Overwrite dataset info from restored data version if exists. | |
| 09/02/2024 09:22:38 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists. | |
| Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7 | |
| 09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7 | |
| Found cached dataset json (/root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7) | |
| 09/02/2024 09:22:38 - INFO - datasets.builder - Found cached dataset json (/root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7) | |
| Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7 | |
| 09/02/2024 09:22:38 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7 | |
| /mnt/data_large/ccy/Llama-2-7b-hf | |
| ['./data/train/processed/flan_v2/flan_v2_data.jsonl', './data/train/processed/cot/cot_data.jsonl', './data/train/processed/dolly/dolly_data.jsonl', './data/train/processed/oasst1/oasst1_data.jsonl'] | |
| ['dataset', 'id', 'messages'] | |
| Process #0 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00000_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #0 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00000_of_00010.arrow | |
| Process #1 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00001_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #1 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00001_of_00010.arrow | |
| Process #2 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00002_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #2 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00002_of_00010.arrow | |
| Process #3 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00003_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #3 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00003_of_00010.arrow | |
| Process #4 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00004_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #4 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00004_of_00010.arrow | |
| Process #5 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00005_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #5 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00005_of_00010.arrow | |
| Process #6 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00006_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #6 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00006_of_00010.arrow | |
| Process #7 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00007_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #7 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00007_of_00010.arrow | |
| Process #8 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00008_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #8 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00008_of_00010.arrow | |
| Process #9 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00009_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Process #9 will write at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_00009_of_00010.arrow | |
| Loading cached processed dataset at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_*_of_00010.arrow | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /root/.cache/huggingface/datasets/json/default-f9134d95c1961a9a/0.0.0/c8d2d9508a2a2067ab02cd118834ecef34c3700d143b31835ec4235bf10109f7/cache-7ad18c1f20ceb8df_*_of_00010.arrow | |
| Concatenating 10 shards | |
| 09/02/2024 09:22:38 - INFO - datasets.arrow_dataset - Concatenating 10 shards | |
| [INFO|configuration_utils.py:737] 2024-09-02 09:22:38,728 >> loading configuration file /mnt/data_large/ccy/Llama-2-7b-hf/config.json | |
| [INFO|configuration_utils.py:802] 2024-09-02 09:22:38,729 >> Model config LlamaConfig { | |
| "_name_or_path": "/mnt/data_large/ccy/Llama-2-7b-hf", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|modeling_utils.py:3341] 2024-09-02 09:22:38,764 >> loading weights file /mnt/data_large/ccy/Llama-2-7b-hf/model.safetensors.index.json | |
| [INFO|configuration_utils.py:826] 2024-09-02 09:22:38,765 >> Generate config GenerationConfig { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2 | |
| } | |
| Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] |