| config: {'model': {'key': 'flan-t5-small', 'quantize': False, 'use_lora': True}, 'lora': {'r': 8, 'lora_alpha': 16, 'lora_dropout': 0.05, 'target_modules': ['q', 'v', 'k', 'o', 'wi_0', 'wi_1', 'wo']}, 'data': {'train_path': 'data/processed/train.jsonl', 'val_path': 'data/processed/val.jsonl', 'test_path': 'data/processed/test.jsonl', 'max_input_length': 128, 'max_target_length': 128, 'augment_synthetic': True, 'synthetic_ratio': 0.3}, 'training': {'output_dir': 'checkpoints/', 'num_train_epochs': 5, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 8, 'gradient_accumulation_steps': 8, 'learning_rate': 0.0003, 'lr_scheduler_type': 'cosine', 'warmup_ratio': 0.05, 'weight_decay': 0.01, 'fp16': False, 'bf16': True, 'evaluation_strategy': 'steps', 'eval_steps': 100, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': 3, 'load_best_model_at_end': True, 'metric_for_best_model': 'eval_loss', 'greater_is_better': False, 'logging_dir': 'logs/', 'logging_steps': 25, 'report_to': ['wandb', 'tensorboard'], 'dataloader_num_workers': 0, 'seed': 42, 'push_to_hub': False}, 'loss': {'lambda_style': 0.3, 'lambda_semantic': 0.5, 'lambda_human_pattern': 0.4, 'sem_model_name': 'all-mpnet-base-v2'}, 'generation': {'num_beams': 5, 'length_penalty': 1.0, 'no_repeat_ngram_size': 3, 'min_length': 10, 'max_new_tokens': 512, 'early_stopping': True}, 'human_pattern': {'classifier_path': 'checkpoints/human_pattern_classifier.pt', 'shanegerami_path': 'data/raw/shanegerami/AI_Human.csv', 'starblasters_path': 'data/raw/starblasters8/data.parquet', 'max_samples_per_source': 50000, 'pretrain_epochs': 20, 'pretrain_lr': 0.001, 'pretrain_batch_size': 512, 'target_auc': 0.88}, '_wandb': {}} |
| 2026-05-03 12:41:39,987 INFO MainThread:34388 [wandb_run.py:_config_callback():1415] config_cb None None {'peft_config': {'default': {'task_type': 'SEQ_2_SEQ_LM', 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.19.1', 'base_model_name_or_path': 'google/flan-t5-small', 'revision': None, 'inference_mode': False, 'r': 8, 'target_modules': ['wo', 'wi_0', 'v', 'q', 'k', 'o', 'wi_1'], 'exclude_modules': None, 'lora_alpha': 16, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'lora_ga_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'use_bdlora': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 32128, 'd_model': 512, 'd_kv': 64, 'd_ff': 1024, 'num_layers': 8, 'num_decoder_layers': 8, 'num_heads': 6, 'relative_attention_num_buckets': 32, 'relative_attention_max_distance': 128, 'dropout_rate': 0.1, 'classifier_dropout': 0.0, 'layer_norm_epsilon': 1e-06, 'initializer_factor': 1.0, 'feed_forward_proj': 'gated-gelu', 'use_cache': True, 'dense_act_fn': 'gelu_new', 'is_gated_act': True, 'return_dict': True, 'output_hidden_states': 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': True, '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': ['T5ForConditionalGeneration'], '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': None, 'pad_token_id': 0, 'eos_token_id': 1, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': {'summarization': {'early_stopping': True, 'length_penalty': 2.0, 'max_length': 200, 'min_length': 30, 'no_repeat_ngram_size': 3, 'num_beams': 4, 'prefix': 'summarize: '}, 'translation_en_to_de': {'early_stopping': True, 'max_length': 300, 'num_beams': 4, 'prefix': 'translate English to German: '}, 'translation_en_to_fr': {'early_stopping': True, 'max_length': 300, 'num_beams': 4, 'prefix': 'translate English to French: '}, 'translation_en_to_ro': {'early_stopping': True, 'max_length': 300, 'num_beams': 4, 'prefix': 'translate English to Romanian: '}}, 'problem_type': None, '_name_or_path': 'google/flan-t5-small', 'transformers_version': '4.53.2', 'model_type': 't5', 'n_positions': 512, 'output_past': True, 'output_attentions': False, 'output_dir': 'checkpoints/', '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': 4, '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': 0.0003, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'logs/', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 100, 'save_total_limit': 3, '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': 42, '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': 100, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'checkpoints/', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'eval_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', 'tensorboard'], '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_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, '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, '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': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': False} |
