{ "total_samples": 35526, "config": { "model_path": "./outputs/phase1_phase3a_dpo_alignment", "output_dir": "./outputs/phase4_medreason_cot", "max_seq_length": 8192, "min_reasoning_length": 500, "max_reasoning_length": 4500, "learning_rate": 5e-07, "num_train_epochs": 2, "per_device_train_batch_size": 2, "gradient_accumulation_steps": 8, "warmup_ratio": 0.05, "lr_scheduler_type": "cosine", "weight_decay": 0.01, "max_grad_norm": 0.5, "optim": "adamw_torch", "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "use_curriculum": true, "use_neftune": true, "neftune_noise_alpha": 5.0, "save_steps": 200, "save_total_limit": 3, "logging_steps": 10, "eval_steps": 500, "seed": 42, "bf16": true, "gradient_checkpointing": true, "dataloader_num_workers": 4 }, "timestamp": "2026-01-26T18:01:49.960457" }