|
config: {'time_start': '2025-02-03_10-36-45', 'DEBUG': False, 'debug_model': 'unsloth/Qwen2.5-7B-bnb-4bit', 'fold': 0, 'random_seed': True, 'train_on_all_folds': False, 'eval_only': False, 'merge_adapters': False, 'wandb_id': None, 'val_split_name': 'val', 'pad_token': '<pad>', 'response_template_ids': [4], 'num_proc': 20, 'hub_repo_tags': ['odesia'], 'script_args': {'dataset_name': 'nbroad/odesia-dipromats-seq-cls-v1', 'config': 't1', 'gradient_checkpointing_use_reentrant': True, 'ignore_bias_buffers': False}, 'model_config': {'model_name_or_path': 'mistralai/Ministral-8B-Instruct-2410', 'torch_dtype': 'bfloat16', 'attn_implementation': 'flash_attention_2', 'use_peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'lora_target_modules': ['q_proj', 'v_proj', 'k_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'], 'lora_modules_to_save': None, 'lora_task_type': 'SEQ_CLS', 'use_rslora': True, 'load_in_8bit': False, 'load_in_4bit': False, 'bnb_4bit_quant_type': 'nf4', 'use_bnb_nested_quant': True}, 'training_args': {'resume_from_checkpoint': None, 'output_dir': './', 'num_train_epochs': 1, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'warmup_ratio': 0.1, 'fp16': False, 'bf16': True, 'eval_strategy': 'steps', 'save_strategy': 'steps', 'eval_steps': 10, 'save_steps': 10, 'save_total_limit': 2, 'logging_steps': 2, 'run_name': None, 'weight_decay': 0.01, 'report_to': 'wandb', 'learning_rate': 4e-05, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'gradient_checkpointing': True, 'gradient_accumulation_steps': 8, 'gradient_checkpointing_kwargs': {'use_reentrant': True}, 'optim': 'adamw_torch', 'dataloader_num_workers': 4, 'seed': 18, 'max_grad_norm': 2.0, 'load_best_model_at_end': True, 'push_to_hub': True, 'hub_private_repo': True, 'lr_scheduler_type': 'cosine', 'remove_unused_columns': False, 'ddp_find_unused_parameters': False, 'use_liger_kernel': True}, '_wandb': {}} |
|
2025-02-03 10:37:12,234 INFO MainThread:2048 [wandb_run.py:_config_callback():1253] config_cb None None {'peft_config': {'default': {'task_type': 'SEQ_CLS', 'peft_type': <PeftType.LORA: 'LORA'>, 'auto_mapping': None, 'base_model_name_or_path': 'mistralai/Ministral-8B-Instruct-2410', 'revision': None, 'inference_mode': False, 'r': 16, 'target_modules': {'q_proj', 'down_proj', 'up_proj', 'k_proj', 'o_proj', 'gate_proj', 'v_proj'}, 'exclude_modules': None, 'lora_alpha': 32, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': True, 'modules_to_save': ['classifier', 'score'], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'loftq_config': {}, 'eva_config': None, 'use_dora': False, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False}}, 'vocab_size': 131072, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 12288, 'num_hidden_layers': 36, 'num_attention_heads': 32, 'sliding_window': 32768, 'head_dim': 128, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 100000000.0, '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/Ministral-8B-Instruct-2410', '_attn_implementation_autoset': True, 'transformers_version': '4.48.2', 'model_type': 'mistral', 'wandb_id': 'f5yiqx2u', 'fold': 0, 'group': 'dipro-t1', 'dataset': 'nbroad/odesia-dipromats-seq-cls-v1', 'output_dir': './', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 4e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 2.0, 'num_train_epochs': 1, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Feb03_10-36-45_a08f80423bec', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 2, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 18, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, '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': 10, 'dataloader_num_workers': 4, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': False, '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, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, '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': 'nbroad/nbroad-odesia-dipro-t1-f5yiqx2u', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': True, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': True}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, '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, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': True, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'dataset_text_field': 'text', 'packing': False, 'max_seq_length': 1024, 'dataset_num_proc': None, 'dataset_batch_size': 1000, 'model_init_kwargs': None, 'dataset_kwargs': {}, 'eval_packing': None, 'num_of_sequences': 1024, 'chars_per_token': '<CHARS_PER_TOKEN>', 'use_liger': False} |
