csujeong commited on
Commit
d0bdc78
1 Parent(s): ab868af

End of training

Browse files
README.md CHANGED
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
52
 
53
  ### Framework versions
54
 
55
- - PEFT 0.7.2.dev0
56
- - Transformers 4.36.2
57
- - Pytorch 2.1.0+cu121
58
- - Datasets 2.16.1
59
- - Tokenizers 0.15.0
 
52
 
53
  ### Framework versions
54
 
55
+ - PEFT 0.9.1.dev0
56
+ - Transformers 4.39.0
57
+ - Pytorch 2.2.1+cu121
58
+ - Datasets 2.18.0
59
+ - Tokenizers 0.15.2
wandb/debug-internal.log CHANGED
@@ -468,3 +468,42 @@
468
  2024-03-21 02:10:50,484 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
469
  2024-03-21 02:10:53,331 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
470
  2024-03-21 02:10:55,485 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
468
  2024-03-21 02:10:50,484 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
469
  2024-03-21 02:10:53,331 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
470
  2024-03-21 02:10:55,485 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
471
+ 2024-03-21 02:10:58,332 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
472
+ 2024-03-21 02:11:00,486 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
473
+ 2024-03-21 02:11:03,333 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
474
+ 2024-03-21 02:11:04,246 DEBUG SenderThread:7197 [sender.py:send():378] send: stats
475
+ 2024-03-21 02:11:05,487 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
476
+ 2024-03-21 02:11:09,247 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
477
+ 2024-03-21 02:11:10,488 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
478
+ 2024-03-21 02:11:10,544 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: pause
479
+ 2024-03-21 02:11:10,545 INFO HandlerThread:7197 [handler.py:handle_request_pause():708] stopping system metrics thread
480
+ 2024-03-21 02:11:10,545 INFO HandlerThread:7197 [system_monitor.py:finish():203] Stopping system monitor
481
+ 2024-03-21 02:11:10,545 DEBUG SystemMonitor:7197 [system_monitor.py:_start():179] Finished system metrics aggregation loop
482
+ 2024-03-21 02:11:10,549 DEBUG SystemMonitor:7197 [system_monitor.py:_start():183] Publishing last batch of metrics
483
+ 2024-03-21 02:11:10,547 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined cpu monitor
484
+ 2024-03-21 02:11:10,554 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined disk monitor
485
+ 2024-03-21 02:11:10,563 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined gpu monitor
486
+ 2024-03-21 02:11:10,563 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined memory monitor
487
+ 2024-03-21 02:11:10,564 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined network monitor
488
+ 2024-03-21 02:11:10,564 DEBUG SenderThread:7197 [sender.py:send():378] send: stats
489
+ 2024-03-21 02:11:14,565 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
490
+ 2024-03-21 02:11:15,489 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
491
+ 2024-03-21 02:11:19,566 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
492
+ 2024-03-21 02:11:20,490 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
493
+ 2024-03-21 02:11:24,567 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
494
+ 2024-03-21 02:11:25,491 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
495
+ 2024-03-21 02:11:29,568 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
496
+ 2024-03-21 02:11:30,492 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
497
+ 2024-03-21 02:11:34,569 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
498
+ 2024-03-21 02:11:35,493 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
499
+ 2024-03-21 02:11:38,632 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: resume
500
+ 2024-03-21 02:11:38,633 INFO HandlerThread:7197 [handler.py:handle_request_resume():699] starting system metrics thread
501
+ 2024-03-21 02:11:38,634 INFO HandlerThread:7197 [system_monitor.py:start():194] Starting system monitor
502
+ 2024-03-21 02:11:38,634 INFO SystemMonitor:7197 [system_monitor.py:_start():158] Starting system asset monitoring threads
503
+ 2024-03-21 02:11:38,637 INFO SystemMonitor:7197 [interfaces.py:start():190] Started cpu monitoring
504
+ 2024-03-21 02:11:38,640 INFO SystemMonitor:7197 [interfaces.py:start():190] Started disk monitoring
505
+ 2024-03-21 02:11:38,642 INFO SystemMonitor:7197 [interfaces.py:start():190] Started gpu monitoring
506
+ 2024-03-21 02:11:38,649 INFO SystemMonitor:7197 [interfaces.py:start():190] Started memory monitoring
507
+ 2024-03-21 02:11:38,651 INFO SystemMonitor:7197 [interfaces.py:start():190] Started network monitoring
508
+ 2024-03-21 02:11:39,570 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
509
+ 2024-03-21 02:11:40,615 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
wandb/debug.log CHANGED
@@ -29,3 +29,6 @@ config: {}
29
  2024-03-21 01:55:04,649 INFO MainThread:3894 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-21 01:55:04,651 INFO MainThread:3894 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-21 01:55:04,659 INFO MainThread:3894 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.39.0', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Mar21_01-53-07_d72aea89d4b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
 
 
 
 
29
  2024-03-21 01:55:04,649 INFO MainThread:3894 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-21 01:55:04,651 INFO MainThread:3894 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-21 01:55:04,659 INFO MainThread:3894 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.39.0', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Mar21_01-53-07_d72aea89d4b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
32
+ 2024-03-21 02:11:10,542 INFO MainThread:3894 [jupyter.py:save_ipynb():373] not saving jupyter notebook
33
+ 2024-03-21 02:11:10,543 INFO MainThread:3894 [wandb_init.py:_pause_backend():437] pausing backend
34
+ 2024-03-21 02:11:38,631 INFO MainThread:3894 [wandb_init.py:_resume_backend():442] resuming backend
wandb/run-20240321_015458-y11xrjxv/logs/debug-internal.log CHANGED
@@ -468,3 +468,42 @@
468
  2024-03-21 02:10:50,484 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
469
  2024-03-21 02:10:53,331 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
470
  2024-03-21 02:10:55,485 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
468
  2024-03-21 02:10:50,484 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
469
  2024-03-21 02:10:53,331 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
470
  2024-03-21 02:10:55,485 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
471
+ 2024-03-21 02:10:58,332 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
472
+ 2024-03-21 02:11:00,486 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
473
+ 2024-03-21 02:11:03,333 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
474
+ 2024-03-21 02:11:04,246 DEBUG SenderThread:7197 [sender.py:send():378] send: stats
475
+ 2024-03-21 02:11:05,487 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
476
+ 2024-03-21 02:11:09,247 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
477
+ 2024-03-21 02:11:10,488 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
478
+ 2024-03-21 02:11:10,544 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: pause
479
+ 2024-03-21 02:11:10,545 INFO HandlerThread:7197 [handler.py:handle_request_pause():708] stopping system metrics thread
480
+ 2024-03-21 02:11:10,545 INFO HandlerThread:7197 [system_monitor.py:finish():203] Stopping system monitor
481
+ 2024-03-21 02:11:10,545 DEBUG SystemMonitor:7197 [system_monitor.py:_start():179] Finished system metrics aggregation loop
482
+ 2024-03-21 02:11:10,549 DEBUG SystemMonitor:7197 [system_monitor.py:_start():183] Publishing last batch of metrics
483
+ 2024-03-21 02:11:10,547 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined cpu monitor
484
+ 2024-03-21 02:11:10,554 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined disk monitor
485
+ 2024-03-21 02:11:10,563 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined gpu monitor
486
+ 2024-03-21 02:11:10,563 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined memory monitor
487
+ 2024-03-21 02:11:10,564 INFO HandlerThread:7197 [interfaces.py:finish():202] Joined network monitor
488
+ 2024-03-21 02:11:10,564 DEBUG SenderThread:7197 [sender.py:send():378] send: stats
489
+ 2024-03-21 02:11:14,565 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
490
+ 2024-03-21 02:11:15,489 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
491
+ 2024-03-21 02:11:19,566 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
492
+ 2024-03-21 02:11:20,490 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
493
+ 2024-03-21 02:11:24,567 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
494
+ 2024-03-21 02:11:25,491 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
495
+ 2024-03-21 02:11:29,568 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
496
+ 2024-03-21 02:11:30,492 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
497
+ 2024-03-21 02:11:34,569 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
498
+ 2024-03-21 02:11:35,493 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
499
+ 2024-03-21 02:11:38,632 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: resume
500
+ 2024-03-21 02:11:38,633 INFO HandlerThread:7197 [handler.py:handle_request_resume():699] starting system metrics thread
501
+ 2024-03-21 02:11:38,634 INFO HandlerThread:7197 [system_monitor.py:start():194] Starting system monitor
502
+ 2024-03-21 02:11:38,634 INFO SystemMonitor:7197 [system_monitor.py:_start():158] Starting system asset monitoring threads
503
+ 2024-03-21 02:11:38,637 INFO SystemMonitor:7197 [interfaces.py:start():190] Started cpu monitoring
504
+ 2024-03-21 02:11:38,640 INFO SystemMonitor:7197 [interfaces.py:start():190] Started disk monitoring
505
+ 2024-03-21 02:11:38,642 INFO SystemMonitor:7197 [interfaces.py:start():190] Started gpu monitoring
506
+ 2024-03-21 02:11:38,649 INFO SystemMonitor:7197 [interfaces.py:start():190] Started memory monitoring
507
+ 2024-03-21 02:11:38,651 INFO SystemMonitor:7197 [interfaces.py:start():190] Started network monitoring
508
+ 2024-03-21 02:11:39,570 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: status_report
509
+ 2024-03-21 02:11:40,615 DEBUG HandlerThread:7197 [handler.py:handle_request():146] handle_request: keepalive
wandb/run-20240321_015458-y11xrjxv/logs/debug.log CHANGED
@@ -29,3 +29,6 @@ config: {}
29
  2024-03-21 01:55:04,649 INFO MainThread:3894 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-21 01:55:04,651 INFO MainThread:3894 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-21 01:55:04,659 INFO MainThread:3894 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.39.0', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Mar21_01-53-07_d72aea89d4b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
 
 
 
 
29
  2024-03-21 01:55:04,649 INFO MainThread:3894 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-21 01:55:04,651 INFO MainThread:3894 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-21 01:55:04,659 INFO MainThread:3894 [wandb_run.py:_config_callback():1343] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.39.0', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Mar21_01-53-07_d72aea89d4b6', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
32
+ 2024-03-21 02:11:10,542 INFO MainThread:3894 [jupyter.py:save_ipynb():373] not saving jupyter notebook
33
+ 2024-03-21 02:11:10,543 INFO MainThread:3894 [wandb_init.py:_pause_backend():437] pausing backend
34
+ 2024-03-21 02:11:38,631 INFO MainThread:3894 [wandb_init.py:_resume_backend():442] resuming backend