{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 1,
  "global_step": 144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.3582516312599182,
      "eval_runtime": 4.9392,
      "eval_samples_per_second": 51.627,
      "eval_steps_per_second": 6.479,
      "step": 36
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.12783880531787872,
      "eval_runtime": 4.4185,
      "eval_samples_per_second": 57.711,
      "eval_steps_per_second": 7.242,
      "step": 72
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.24191316962242126,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 0.4019,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.05018627643585205,
      "eval_runtime": 4.4037,
      "eval_samples_per_second": 57.906,
      "eval_steps_per_second": 7.267,
      "step": 108
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.039800360798835754,
      "eval_runtime": 4.4427,
      "eval_samples_per_second": 57.397,
      "eval_steps_per_second": 7.203,
      "step": 144
    },
    {
      "epoch": 4.0,
      "step": 144,
      "total_flos": 6.116937949616538e+17,
      "train_loss": 0.2839497621688578,
      "train_runtime": 414.9456,
      "train_samples_per_second": 22.104,
      "train_steps_per_second": 0.347
    }
  ],
  "logging_steps": 100,
  "max_steps": 144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.116937949616538e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}