{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016909744240118367,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "grad_norm": 9.8369779586792,
      "learning_rate": 2e-05,
      "loss": 4.6538,
      "step": 1
    },
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 4.714530944824219,
      "eval_runtime": 49.0189,
      "eval_samples_per_second": 50.797,
      "eval_steps_per_second": 25.398,
      "step": 1
    },
    {
      "epoch": 0.0003381948848023674,
      "grad_norm": 9.245512962341309,
      "learning_rate": 4e-05,
      "loss": 4.5746,
      "step": 2
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 10.763644218444824,
      "learning_rate": 6e-05,
      "loss": 4.5088,
      "step": 3
    },
    {
      "epoch": 0.000507292327203551,
      "eval_loss": 4.614694118499756,
      "eval_runtime": 47.4096,
      "eval_samples_per_second": 52.521,
      "eval_steps_per_second": 26.261,
      "step": 3
    },
    {
      "epoch": 0.0006763897696047348,
      "grad_norm": 8.866936683654785,
      "learning_rate": 8e-05,
      "loss": 4.5292,
      "step": 4
    },
    {
      "epoch": 0.0008454872120059184,
      "grad_norm": 11.931519508361816,
      "learning_rate": 0.0001,
      "loss": 4.052,
      "step": 5
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 9.325718879699707,
      "learning_rate": 0.00012,
      "loss": 3.8607,
      "step": 6
    },
    {
      "epoch": 0.001014584654407102,
      "eval_loss": 3.2516112327575684,
      "eval_runtime": 48.3448,
      "eval_samples_per_second": 51.505,
      "eval_steps_per_second": 25.753,
      "step": 6
    },
    {
      "epoch": 0.0011836820968082857,
      "grad_norm": 13.148191452026367,
      "learning_rate": 0.00014,
      "loss": 3.1169,
      "step": 7
    },
    {
      "epoch": 0.0013527795392094695,
      "grad_norm": 15.300745010375977,
      "learning_rate": 0.00016,
      "loss": 2.8337,
      "step": 8
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 15.626968383789062,
      "learning_rate": 0.00018,
      "loss": 1.9764,
      "step": 9
    },
    {
      "epoch": 0.0015218769816106531,
      "eval_loss": 1.4432624578475952,
      "eval_runtime": 48.5206,
      "eval_samples_per_second": 51.318,
      "eval_steps_per_second": 25.659,
      "step": 9
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": 11.509749412536621,
      "learning_rate": 0.0002,
      "loss": 1.3347,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 104619842469888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}