{
  "experiment_name": "exp4b_dpo",
  "config_file": "/scratch/jennifer/standard-project-m2-the-transformers/configs/exp4b_dpo.yaml",
  "resolved_config": {
    "num_train_epochs": 1,
    "learning_rate": 5e-07,
    "per_device_train_batch_size": 1,
    "per_device_eval_batch_size": 1,
    "gradient_accumulation_steps": 8,
    "warmup_ratio": 0.1,
    "seed": 42,
    "save_total_limit": 3,
    "eval_steps": 50,
    "logging_steps": 10,
    "beta": 0.1,
    "loss_type": "sigmoid",
    "max_length": 4096,
    "max_completion_length": 3072,
    "val_fraction": 0.1,
    "wandb_project": "cs552-math-dpo",
    "experiment_name": "exp4b_dpo",
    "output_dir": "/scratch/checkpoints/exp4b_dpo",
    "sft_checkpoint": "/scratch/checkpoints/sft_mixlong_full",
    "train_source": "/scratch/data/dpo_pairs_v2/pairs.jsonl"
  },
  "n_train": 5048,
  "n_val": 561
}