{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.139458351874657e-05,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3798194506248858e-05,
      "grad_norm": 11.564373970031738,
      "learning_rate": 2e-05,
      "loss": 10.563,
      "step": 1
    },
    {
      "epoch": 1.3798194506248858e-05,
      "eval_loss": 10.16752815246582,
      "eval_runtime": 4125.8399,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 3.698,
      "step": 1
    },
    {
      "epoch": 2.7596389012497716e-05,
      "grad_norm": 13.19704532623291,
      "learning_rate": 4e-05,
      "loss": 11.0015,
      "step": 2
    },
    {
      "epoch": 4.139458351874657e-05,
      "grad_norm": 10.903892517089844,
      "learning_rate": 6e-05,
      "loss": 10.4111,
      "step": 3
    },
    {
      "epoch": 4.139458351874657e-05,
      "eval_loss": 9.961125373840332,
      "eval_runtime": 4123.3416,
      "eval_samples_per_second": 7.401,
      "eval_steps_per_second": 3.7,
      "step": 3
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 573327424880640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}