trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "grad_norm": 5.0885691336788925,
      "learning_rate": 2.5e-07,
      "logits/chosen": -1.1367864608764648,
      "logits/rejected": -0.8539448976516724,
      "logps/chosen": -199.5379180908203,
      "logps/rejected": -728.93701171875,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.56,
      "grad_norm": 5.003858987570864,
      "learning_rate": 2.5e-07,
      "logits/chosen": -1.1000946760177612,
      "logits/rejected": -0.859523355960846,
      "logps/chosen": -194.80165100097656,
      "logps/rejected": -695.8270263671875,
      "loss": 0.6896,
      "rewards/accuracies": 0.5972222089767456,
      "rewards/chosen": -9.916844282997772e-05,
      "rewards/margins": 0.006284303963184357,
      "rewards/rejected": -0.006383472587913275,
      "step": 10
    },
    {
      "epoch": 1.0,
      "step": 18,
      "total_flos": 0.0,
      "train_loss": 0.6850088967217339,
      "train_runtime": 241.6299,
      "train_samples_per_second": 4.735,
      "train_steps_per_second": 0.074
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}