2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.16.4 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {} 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False} 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': ''} 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'} 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_init.py:_log_setup():526] Logging user logs to /kaggle/working/wandb/run-20240401_065413-yzd7dxs3/logs/debug.log 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_init.py:_log_setup():527] Logging internal logs to /kaggle/working/wandb/run-20240401_065413-yzd7dxs3/logs/debug-internal.log 2024-04-01 06:54:13,060 INFO MainThread:34 [wandb_init.py:_jupyter_setup():472] configuring jupyter hooks 2024-04-01 06:54:13,061 INFO MainThread:34 [wandb_init.py:init():566] calling init triggers 2024-04-01 06:54:13,061 INFO MainThread:34 [wandb_init.py:init():573] wandb.init called with sweep_config: {} config: {} 2024-04-01 06:54:13,061 INFO MainThread:34 [wandb_init.py:init():616] starting backend 2024-04-01 06:54:13,061 INFO MainThread:34 [wandb_init.py:init():620] setting up manager 2024-04-01 06:54:13,063 INFO MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn 2024-04-01 06:54:13,066 INFO MainThread:34 [wandb_init.py:init():628] backend started and connected 2024-04-01 06:54:13,078 INFO MainThread:34 [wandb_run.py:_label_probe_notebook():1295] probe notebook 2024-04-01 06:54:13,454 INFO MainThread:34 [wandb_init.py:init():720] updated telemetry 2024-04-01 06:54:13,458 INFO MainThread:34 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout 2024-04-01 06:54:13,586 INFO MainThread:34 [wandb_run.py:_on_init():2262] communicating current version 2024-04-01 06:54:13,675 INFO MainThread:34 [wandb_run.py:_on_init():2271] got version response upgrade_message: "wandb version 0.16.5 is available! To upgrade, please run:\n $ pip install wandb --upgrade" 2024-04-01 06:54:13,675 INFO MainThread:34 [wandb_init.py:init():804] starting run threads in backend 2024-04-01 06:54:44,704 INFO MainThread:34 [wandb_run.py:_console_start():2241] atexit reg 2024-04-01 06:54:44,705 INFO MainThread:34 [wandb_run.py:_redirect():2096] redirect: wrap_raw 2024-04-01 06:54:44,705 INFO MainThread:34 [wandb_run.py:_redirect():2161] Wrapping output streams. 2024-04-01 06:54:44,705 INFO MainThread:34 [wandb_run.py:_redirect():2186] Redirects installed. 2024-04-01 06:54:44,707 INFO MainThread:34 [wandb_init.py:init():847] run started, returning control to user process 2024-04-01 06:54:44,713 INFO MainThread:34 [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': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'TheBloke/Mistral-7B-Instruct-v0.2-GPTQ', 'transformers_version': '4.38.2', 'model_type': 'mistral', 'pretraining_tp': 1, 'quantization_config': {'quant_method': 'QuantizationMethod.GPTQ', 'bits': 4, 'tokenizer': None, 'dataset': None, 'group_size': 128, 'damp_percent': 0.1, 'desc_act': True, 'sym': True, 'true_sequential': True, 'use_cuda_fp16': False, 'model_seqlen': None, 'block_name_to_quantize': None, 'module_name_preceding_first_block': None, 'batch_size': 1, 'pad_token_id': None, 'use_exllama': True, 'max_input_length': None, 'exllama_config': {'version': 'ExllamaVersion.ONE'}, 'cache_block_outputs': True, 'modules_in_block_to_quantize': None}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 6, 'per_device_eval_batch_size': 6, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 2, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr01_06-53-57_e5cddbcf0d54', 'logging_strategy': 'epoch', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, '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': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, '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': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, '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_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, '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': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', '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': '', '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} 2024-04-01 08:30:55,358 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook 2024-04-01 08:30:55,358 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend 2024-04-01 08:52:13,855 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend 2024-04-01 08:52:13,887 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook 2024-04-01 08:52:13,888 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend 2024-04-01 08:52:43,723 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend 2024-04-01 08:52:43,725 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook 2024-04-01 08:52:43,726 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend 2024-04-01 08:52:46,758 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend