{
  "model": "/data/screenwriter/training/outputs/sgs-smoke/sft",
  "base_model": null,
  "seq_len": 2048,
  "load_in_4bit": false,
  "beta": 0.1,
  "data": "/data/screenwriter/training/outputs/_smoke_data/dpo_train.jsonl",
  "eval": "/data/screenwriter/training/outputs/_smoke_data/dpo_test.jsonl",
  "epochs": 1,
  "batch_size": 1,
  "grad_accum": 1,
  "lr": 2e-05,
  "warmup_steps": 0,
  "max_steps": 1,
  "output": "/data/screenwriter/training/outputs/sgs-smoke/dpo",
  "save_steps": 1,
  "logging_steps": 1,
  "seed": 3407,
  "wandb": false
}