{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008520246235116195,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.520246235116194e-05,
      "grad_norm": 11.395092010498047,
      "learning_rate": 2e-05,
      "loss": 1.5967,
      "step": 1
    },
    {
      "epoch": 8.520246235116194e-05,
      "eval_loss": 1.6326349973678589,
      "eval_runtime": 94.3337,
      "eval_samples_per_second": 52.388,
      "eval_steps_per_second": 26.194,
      "step": 1
    },
    {
      "epoch": 0.00017040492470232388,
      "grad_norm": 16.79621696472168,
      "learning_rate": 4e-05,
      "loss": 1.9276,
      "step": 2
    },
    {
      "epoch": 0.00025560738705348587,
      "grad_norm": 13.302032470703125,
      "learning_rate": 6e-05,
      "loss": 1.2433,
      "step": 3
    },
    {
      "epoch": 0.00025560738705348587,
      "eval_loss": 1.5383052825927734,
      "eval_runtime": 95.0292,
      "eval_samples_per_second": 52.005,
      "eval_steps_per_second": 26.003,
      "step": 3
    },
    {
      "epoch": 0.00034080984940464777,
      "grad_norm": 8.872673988342285,
      "learning_rate": 8e-05,
      "loss": 1.0232,
      "step": 4
    },
    {
      "epoch": 0.0004260123117558097,
      "grad_norm": 7.118113994598389,
      "learning_rate": 0.0001,
      "loss": 0.9401,
      "step": 5
    },
    {
      "epoch": 0.0005112147741069717,
      "grad_norm": 9.416373252868652,
      "learning_rate": 0.00012,
      "loss": 1.2182,
      "step": 6
    },
    {
      "epoch": 0.0005112147741069717,
      "eval_loss": 0.8956790566444397,
      "eval_runtime": 95.0931,
      "eval_samples_per_second": 51.97,
      "eval_steps_per_second": 25.985,
      "step": 6
    },
    {
      "epoch": 0.0005964172364581337,
      "grad_norm": 4.938461780548096,
      "learning_rate": 0.00014,
      "loss": 0.5221,
      "step": 7
    },
    {
      "epoch": 0.0006816196988092955,
      "grad_norm": 8.094161987304688,
      "learning_rate": 0.00016,
      "loss": 0.6498,
      "step": 8
    },
    {
      "epoch": 0.0007668221611604575,
      "grad_norm": 6.507604122161865,
      "learning_rate": 0.00018,
      "loss": 0.3727,
      "step": 9
    },
    {
      "epoch": 0.0007668221611604575,
      "eval_loss": 0.32682183384895325,
      "eval_runtime": 94.5851,
      "eval_samples_per_second": 52.249,
      "eval_steps_per_second": 26.125,
      "step": 9
    },
    {
      "epoch": 0.0008520246235116195,
      "grad_norm": 3.768209934234619,
      "learning_rate": 0.0002,
      "loss": 0.4065,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}