{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 10.64614486694336,
      "eval_runtime": 3.6647,
      "eval_samples_per_second": 2.456,
      "eval_steps_per_second": 2.456,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_loss": 10.314367294311523,
      "eval_runtime": 3.354,
      "eval_samples_per_second": 2.683,
      "eval_steps_per_second": 2.683,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 10.004138946533203,
      "eval_runtime": 3.2378,
      "eval_samples_per_second": 2.78,
      "eval_steps_per_second": 2.78,
      "step": 9
    },
    {
      "epoch": 3.4050632911392404,
      "grad_norm": 18.727033615112305,
      "learning_rate": 1.55e-05,
      "loss": 14.3667,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_loss": 9.67867374420166,
      "eval_runtime": 3.241,
      "eval_samples_per_second": 2.777,
      "eval_steps_per_second": 2.777,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_loss": 9.405113220214844,
      "eval_runtime": 3.3565,
      "eval_samples_per_second": 2.681,
      "eval_steps_per_second": 2.681,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_loss": 9.119384765625,
      "eval_runtime": 3.2333,
      "eval_samples_per_second": 2.784,
      "eval_steps_per_second": 2.784,
      "step": 18
    },
    {
      "epoch": 6.810126582278481,
      "grad_norm": 24.65047836303711,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 12.716,
      "step": 20
    },
    {
      "epoch": 7.0,
      "eval_loss": 8.926345825195312,
      "eval_runtime": 3.2359,
      "eval_samples_per_second": 2.781,
      "eval_steps_per_second": 2.781,
      "step": 21
    },
    {
      "epoch": 8.0,
      "eval_loss": 8.806801795959473,
      "eval_runtime": 3.3469,
      "eval_samples_per_second": 2.689,
      "eval_steps_per_second": 2.689,
      "step": 24
    },
    {
      "epoch": 9.0,
      "eval_loss": 8.627554893493652,
      "eval_runtime": 3.2357,
      "eval_samples_per_second": 2.781,
      "eval_steps_per_second": 2.781,
      "step": 27
    },
    {
      "epoch": 10.0,
      "grad_norm": 31.947998046875,
      "learning_rate": 5.500000000000001e-06,
      "loss": 11.4678,
      "step": 30
    },
    {
      "epoch": 10.0,
      "eval_loss": 8.587936401367188,
      "eval_runtime": 3.2323,
      "eval_samples_per_second": 2.784,
      "eval_steps_per_second": 2.784,
      "step": 30
    },
    {
      "epoch": 11.0,
      "eval_loss": 8.51167106628418,
      "eval_runtime": 3.3567,
      "eval_samples_per_second": 2.681,
      "eval_steps_per_second": 2.681,
      "step": 33
    },
    {
      "epoch": 12.0,
      "eval_loss": 8.46914005279541,
      "eval_runtime": 3.2448,
      "eval_samples_per_second": 2.774,
      "eval_steps_per_second": 2.774,
      "step": 36
    },
    {
      "epoch": 13.0,
      "eval_loss": 8.401935577392578,
      "eval_runtime": 3.2368,
      "eval_samples_per_second": 2.78,
      "eval_steps_per_second": 2.78,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.085903189147648e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}