checkpoint-13/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "outputs/checkpoint-13",
  "epoch": 0.9904761904761905,
  "eval_steps": 500,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9904761904761905,
      "eval_loss": NaN,
      "eval_runtime": 25.9464,
      "eval_samples_per_second": 16.187,
      "eval_steps_per_second": 2.043,
      "step": 13
    }
  ],
  "logging_steps": 20,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1959304152219648.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}