csujeong commited on
Commit
5c5c369
1 Parent(s): 1f30149

End of training

Browse files
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: mistralai/Mistral-7B-v0.1
9
  model-index:
10
  - name: Mistral-7B-Finetuning-Insurance
11
  results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # Mistral-7B-Finetuning-Insurance
18
 
19
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
 
21
  ## Model description
22
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
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
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
9
  model-index:
10
  - name: Mistral-7B-Finetuning-Insurance
11
  results: []
 
16
 
17
  # Mistral-7B-Finetuning-Insurance
18
 
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
52
 
53
  ### Framework versions
54
 
55
+ - PEFT 0.10.1.dev0
56
  - Transformers 4.39.0
57
  - Pytorch 2.2.1+cu121
58
  - Datasets 2.18.0
wandb/debug-internal.log CHANGED
@@ -399,3 +399,76 @@
399
  2024-03-22 04:48:22,163 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
400
  2024-03-22 04:48:27,164 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
401
  2024-03-22 04:48:32,165 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
399
  2024-03-22 04:48:22,163 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
400
  2024-03-22 04:48:27,164 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
401
  2024-03-22 04:48:32,165 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
402
+ 2024-03-22 04:48:34,363 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: pause
403
+ 2024-03-22 04:48:34,363 INFO HandlerThread:4275 [handler.py:handle_request_pause():708] stopping system metrics thread
404
+ 2024-03-22 04:48:34,363 INFO HandlerThread:4275 [system_monitor.py:finish():203] Stopping system monitor
405
+ 2024-03-22 04:48:34,363 DEBUG SystemMonitor:4275 [system_monitor.py:_start():179] Finished system metrics aggregation loop
406
+ 2024-03-22 04:48:34,367 DEBUG SystemMonitor:4275 [system_monitor.py:_start():183] Publishing last batch of metrics
407
+ 2024-03-22 04:48:34,367 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined cpu monitor
408
+ 2024-03-22 04:48:34,376 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined disk monitor
409
+ 2024-03-22 04:48:34,381 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined gpu monitor
410
+ 2024-03-22 04:48:34,383 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined memory monitor
411
+ 2024-03-22 04:48:34,383 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined network monitor
412
+ 2024-03-22 04:48:34,384 DEBUG SenderThread:4275 [sender.py:send():378] send: stats
413
+ 2024-03-22 04:48:35,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
414
+ 2024-03-22 04:48:35,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
415
+ 2024-03-22 04:48:37,861 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
416
+ 2024-03-22 04:48:42,861 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
417
+ 2024-03-22 04:48:47,862 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
418
+ 2024-03-22 04:48:50,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
419
+ 2024-03-22 04:48:50,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
420
+ 2024-03-22 04:48:52,893 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
421
+ 2024-03-22 04:48:57,894 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
422
+ 2024-03-22 04:49:02,895 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
423
+ 2024-03-22 04:49:05,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
424
+ 2024-03-22 04:49:05,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
425
+ 2024-03-22 04:49:08,854 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
426
+ 2024-03-22 04:49:13,855 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
427
+ 2024-03-22 04:49:18,856 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
428
+ 2024-03-22 04:49:20,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
429
+ 2024-03-22 04:49:20,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
430
+ 2024-03-22 04:49:23,927 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
431
+ 2024-03-22 04:49:28,928 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
432
+ 2024-03-22 04:49:33,929 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
433
+ 2024-03-22 04:49:35,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
434
+ 2024-03-22 04:49:35,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
435
+ 2024-03-22 04:49:39,888 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
436
+ 2024-03-22 04:49:44,889 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
437
+ 2024-03-22 04:49:49,890 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
438
+ 2024-03-22 04:49:50,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
439
+ 2024-03-22 04:49:50,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
440
+ 2024-03-22 04:49:55,837 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
441
+ 2024-03-22 04:50:00,838 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
442
+ 2024-03-22 04:50:05,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
443
+ 2024-03-22 04:50:05,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
444
+ 2024-03-22 04:50:05,876 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
445
+ 2024-03-22 04:50:10,878 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
446
+ 2024-03-22 04:50:15,879 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
447
+ 2024-03-22 04:50:20,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
448
+ 2024-03-22 04:50:20,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
449
+ 2024-03-22 04:50:21,843 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
450
+ 2024-03-22 04:50:26,844 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
451
+ 2024-03-22 04:50:31,845 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
452
+ 2024-03-22 04:50:35,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
453
+ 2024-03-22 04:50:35,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
454
+ 2024-03-22 04:50:36,879 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
455
+ 2024-03-22 04:50:41,880 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
456
+ 2024-03-22 04:50:46,881 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
457
+ 2024-03-22 04:50:50,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
458
+ 2024-03-22 04:50:50,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
459
+ 2024-03-22 04:50:51,886 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
460
+ 2024-03-22 04:50:56,887 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
461
+ 2024-03-22 04:51:01,888 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
462
+ 2024-03-22 04:51:05,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
463
+ 2024-03-22 04:51:05,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
464
+ 2024-03-22 04:51:06,907 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
465
+ 2024-03-22 04:51:09,923 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: resume
466
+ 2024-03-22 04:51:09,924 INFO HandlerThread:4275 [handler.py:handle_request_resume():699] starting system metrics thread
467
+ 2024-03-22 04:51:09,925 INFO HandlerThread:4275 [system_monitor.py:start():194] Starting system monitor
468
+ 2024-03-22 04:51:09,925 INFO SystemMonitor:4275 [system_monitor.py:_start():158] Starting system asset monitoring threads
469
+ 2024-03-22 04:51:09,926 INFO SystemMonitor:4275 [interfaces.py:start():190] Started cpu monitoring
470
+ 2024-03-22 04:51:09,927 INFO SystemMonitor:4275 [interfaces.py:start():190] Started disk monitoring
471
+ 2024-03-22 04:51:09,929 INFO SystemMonitor:4275 [interfaces.py:start():190] Started gpu monitoring
472
+ 2024-03-22 04:51:09,930 INFO SystemMonitor:4275 [interfaces.py:start():190] Started memory monitoring
473
+ 2024-03-22 04:51:09,935 INFO SystemMonitor:4275 [interfaces.py:start():190] Started network monitoring
474
+ 2024-03-22 04:51:11,908 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
wandb/debug.log CHANGED
@@ -29,3 +29,6 @@ config: {}
29
  2024-03-22 04:34:13,734 INFO MainThread:209 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-22 04:34:13,737 INFO MainThread:209 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-22 04:34:13,745 INFO MainThread:209 [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': None, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 1000000.0, '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-Instruct-v0.2', '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/Mar22_04-33-33_6b98cdd15d10', '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
  2024-03-22 04:34:13,734 INFO MainThread:209 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-22 04:34:13,737 INFO MainThread:209 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-22 04:34:13,745 INFO MainThread:209 [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': None, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 1000000.0, '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-Instruct-v0.2', '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/Mar22_04-33-33_6b98cdd15d10', '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
+ 2024-03-22 04:48:34,361 INFO MainThread:209 [jupyter.py:save_ipynb():373] not saving jupyter notebook
33
+ 2024-03-22 04:48:34,362 INFO MainThread:209 [wandb_init.py:_pause_backend():437] pausing backend
34
+ 2024-03-22 04:51:09,922 INFO MainThread:209 [wandb_init.py:_resume_backend():442] resuming backend
wandb/run-20240322_043407-hize5f4p/logs/debug-internal.log CHANGED
@@ -399,3 +399,76 @@
399
  2024-03-22 04:48:22,163 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
400
  2024-03-22 04:48:27,164 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
401
  2024-03-22 04:48:32,165 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
399
  2024-03-22 04:48:22,163 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
400
  2024-03-22 04:48:27,164 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
401
  2024-03-22 04:48:32,165 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
402
+ 2024-03-22 04:48:34,363 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: pause
403
+ 2024-03-22 04:48:34,363 INFO HandlerThread:4275 [handler.py:handle_request_pause():708] stopping system metrics thread
404
+ 2024-03-22 04:48:34,363 INFO HandlerThread:4275 [system_monitor.py:finish():203] Stopping system monitor
405
+ 2024-03-22 04:48:34,363 DEBUG SystemMonitor:4275 [system_monitor.py:_start():179] Finished system metrics aggregation loop
406
+ 2024-03-22 04:48:34,367 DEBUG SystemMonitor:4275 [system_monitor.py:_start():183] Publishing last batch of metrics
407
+ 2024-03-22 04:48:34,367 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined cpu monitor
408
+ 2024-03-22 04:48:34,376 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined disk monitor
409
+ 2024-03-22 04:48:34,381 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined gpu monitor
410
+ 2024-03-22 04:48:34,383 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined memory monitor
411
+ 2024-03-22 04:48:34,383 INFO HandlerThread:4275 [interfaces.py:finish():202] Joined network monitor
412
+ 2024-03-22 04:48:34,384 DEBUG SenderThread:4275 [sender.py:send():378] send: stats
413
+ 2024-03-22 04:48:35,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
414
+ 2024-03-22 04:48:35,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
415
+ 2024-03-22 04:48:37,861 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
416
+ 2024-03-22 04:48:42,861 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
417
+ 2024-03-22 04:48:47,862 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
418
+ 2024-03-22 04:48:50,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
419
+ 2024-03-22 04:48:50,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
420
+ 2024-03-22 04:48:52,893 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
421
+ 2024-03-22 04:48:57,894 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
422
+ 2024-03-22 04:49:02,895 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
423
+ 2024-03-22 04:49:05,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
424
+ 2024-03-22 04:49:05,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
425
+ 2024-03-22 04:49:08,854 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
426
+ 2024-03-22 04:49:13,855 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
427
+ 2024-03-22 04:49:18,856 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
428
+ 2024-03-22 04:49:20,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
429
+ 2024-03-22 04:49:20,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
430
+ 2024-03-22 04:49:23,927 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
431
+ 2024-03-22 04:49:28,928 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
432
+ 2024-03-22 04:49:33,929 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
433
+ 2024-03-22 04:49:35,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
434
+ 2024-03-22 04:49:35,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
435
+ 2024-03-22 04:49:39,888 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
436
+ 2024-03-22 04:49:44,889 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
437
+ 2024-03-22 04:49:49,890 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
438
+ 2024-03-22 04:49:50,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
439
+ 2024-03-22 04:49:50,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
440
+ 2024-03-22 04:49:55,837 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
441
+ 2024-03-22 04:50:00,838 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
442
+ 2024-03-22 04:50:05,681 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
443
+ 2024-03-22 04:50:05,682 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
444
+ 2024-03-22 04:50:05,876 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
445
+ 2024-03-22 04:50:10,878 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
446
+ 2024-03-22 04:50:15,879 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
447
+ 2024-03-22 04:50:20,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
448
+ 2024-03-22 04:50:20,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
449
+ 2024-03-22 04:50:21,843 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
450
+ 2024-03-22 04:50:26,844 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
451
+ 2024-03-22 04:50:31,845 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
452
+ 2024-03-22 04:50:35,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
453
+ 2024-03-22 04:50:35,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
454
+ 2024-03-22 04:50:36,879 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
455
+ 2024-03-22 04:50:41,880 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
456
+ 2024-03-22 04:50:46,881 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
457
+ 2024-03-22 04:50:50,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
458
+ 2024-03-22 04:50:50,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
459
+ 2024-03-22 04:50:51,886 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
460
+ 2024-03-22 04:50:56,887 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
461
+ 2024-03-22 04:51:01,888 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
462
+ 2024-03-22 04:51:05,682 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: stop_status
463
+ 2024-03-22 04:51:05,683 DEBUG SenderThread:4275 [sender.py:send_request():405] send_request: stop_status
464
+ 2024-03-22 04:51:06,907 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
465
+ 2024-03-22 04:51:09,923 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: resume
466
+ 2024-03-22 04:51:09,924 INFO HandlerThread:4275 [handler.py:handle_request_resume():699] starting system metrics thread
467
+ 2024-03-22 04:51:09,925 INFO HandlerThread:4275 [system_monitor.py:start():194] Starting system monitor
468
+ 2024-03-22 04:51:09,925 INFO SystemMonitor:4275 [system_monitor.py:_start():158] Starting system asset monitoring threads
469
+ 2024-03-22 04:51:09,926 INFO SystemMonitor:4275 [interfaces.py:start():190] Started cpu monitoring
470
+ 2024-03-22 04:51:09,927 INFO SystemMonitor:4275 [interfaces.py:start():190] Started disk monitoring
471
+ 2024-03-22 04:51:09,929 INFO SystemMonitor:4275 [interfaces.py:start():190] Started gpu monitoring
472
+ 2024-03-22 04:51:09,930 INFO SystemMonitor:4275 [interfaces.py:start():190] Started memory monitoring
473
+ 2024-03-22 04:51:09,935 INFO SystemMonitor:4275 [interfaces.py:start():190] Started network monitoring
474
+ 2024-03-22 04:51:11,908 DEBUG HandlerThread:4275 [handler.py:handle_request():146] handle_request: status_report
wandb/run-20240322_043407-hize5f4p/logs/debug.log CHANGED
@@ -29,3 +29,6 @@ config: {}
29
  2024-03-22 04:34:13,734 INFO MainThread:209 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-22 04:34:13,737 INFO MainThread:209 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-22 04:34:13,745 INFO MainThread:209 [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': None, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 1000000.0, '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-Instruct-v0.2', '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/Mar22_04-33-33_6b98cdd15d10', '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
  2024-03-22 04:34:13,734 INFO MainThread:209 [wandb_run.py:_redirect():2186] Redirects installed.
30
  2024-03-22 04:34:13,737 INFO MainThread:209 [wandb_init.py:init():847] run started, returning control to user process
31
  2024-03-22 04:34:13,745 INFO MainThread:209 [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': None, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 1000000.0, '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-Instruct-v0.2', '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/Mar22_04-33-33_6b98cdd15d10', '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
+ 2024-03-22 04:48:34,361 INFO MainThread:209 [jupyter.py:save_ipynb():373] not saving jupyter notebook
33
+ 2024-03-22 04:48:34,362 INFO MainThread:209 [wandb_init.py:_pause_backend():437] pausing backend
34
+ 2024-03-22 04:51:09,922 INFO MainThread:209 [wandb_init.py:_resume_backend():442] resuming backend