trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00032133676092544985,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "logits/generated": -1.854715347290039,
      "logits/real": -1.7835123538970947,
      "logps/generated": -667.4280395507812,
      "logps/real": -384.09954833984375,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0,
      "step": 1,
      "total_flos": 0.0,
      "train_loss": 0.6931471824645996,
      "train_runtime": 10.6478,
      "train_samples_per_second": 1.503,
      "train_steps_per_second": 0.094
    }
  ],
  "logging_steps": 10,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}