{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08456659619450317,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008456659619450317,
      "grad_norm": 3.9527852535247803,
      "learning_rate": 2e-05,
      "loss": 1.9794,
      "step": 1
    },
    {
      "epoch": 0.008456659619450317,
      "eval_loss": 1.9686825275421143,
      "eval_runtime": 1.0428,
      "eval_samples_per_second": 190.838,
      "eval_steps_per_second": 23.975,
      "step": 1
    },
    {
      "epoch": 0.016913319238900635,
      "grad_norm": 4.683907985687256,
      "learning_rate": 4e-05,
      "loss": 2.0737,
      "step": 2
    },
    {
      "epoch": 0.02536997885835095,
      "grad_norm": 3.480458974838257,
      "learning_rate": 6e-05,
      "loss": 1.6003,
      "step": 3
    },
    {
      "epoch": 0.02536997885835095,
      "eval_loss": 1.9255709648132324,
      "eval_runtime": 1.0454,
      "eval_samples_per_second": 190.363,
      "eval_steps_per_second": 23.915,
      "step": 3
    },
    {
      "epoch": 0.03382663847780127,
      "grad_norm": 3.8384430408477783,
      "learning_rate": 8e-05,
      "loss": 1.9747,
      "step": 4
    },
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 3.766523599624634,
      "learning_rate": 0.0001,
      "loss": 1.8881,
      "step": 5
    },
    {
      "epoch": 0.0507399577167019,
      "grad_norm": 3.0816407203674316,
      "learning_rate": 0.00012,
      "loss": 1.351,
      "step": 6
    },
    {
      "epoch": 0.0507399577167019,
      "eval_loss": 1.408592700958252,
      "eval_runtime": 1.0814,
      "eval_samples_per_second": 184.015,
      "eval_steps_per_second": 23.117,
      "step": 6
    },
    {
      "epoch": 0.05919661733615222,
      "grad_norm": 3.3297595977783203,
      "learning_rate": 0.00014,
      "loss": 1.4472,
      "step": 7
    },
    {
      "epoch": 0.06765327695560254,
      "grad_norm": 2.8894972801208496,
      "learning_rate": 0.00016,
      "loss": 1.2052,
      "step": 8
    },
    {
      "epoch": 0.07610993657505286,
      "grad_norm": 2.847442626953125,
      "learning_rate": 0.00018,
      "loss": 0.8708,
      "step": 9
    },
    {
      "epoch": 0.07610993657505286,
      "eval_loss": 0.6713989973068237,
      "eval_runtime": 1.0636,
      "eval_samples_per_second": 187.106,
      "eval_steps_per_second": 23.506,
      "step": 9
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 2.7782552242279053,
      "learning_rate": 0.0002,
      "loss": 0.5466,
      "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": 1074326317039616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}