{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5688888888888889,
  "eval_steps": 6,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035555555555555556,
      "eval_loss": 12.9937105178833,
      "eval_runtime": 0.9451,
      "eval_samples_per_second": 201.043,
      "eval_steps_per_second": 25.395,
      "step": 1
    },
    {
      "epoch": 0.21333333333333335,
      "eval_loss": 12.368244171142578,
      "eval_runtime": 0.9262,
      "eval_samples_per_second": 205.147,
      "eval_steps_per_second": 25.913,
      "step": 6
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 10.741405487060547,
      "learning_rate": 7.985792958513931e-05,
      "loss": 12.5778,
      "step": 10
    },
    {
      "epoch": 0.4266666666666667,
      "eval_loss": 11.853507995605469,
      "eval_runtime": 0.9425,
      "eval_samples_per_second": 201.589,
      "eval_steps_per_second": 25.464,
      "step": 12
    }
  ],
  "logging_steps": 10,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 33565974724608.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}