{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009687575684185032,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009687575684185032,
      "grad_norm": 10.598124504089355,
      "learning_rate": 2e-05,
      "loss": 11.3937,
      "step": 1
    },
    {
      "epoch": 0.0009687575684185032,
      "eval_loss": 2.8135902881622314,
      "eval_runtime": 9.621,
      "eval_samples_per_second": 45.214,
      "eval_steps_per_second": 22.659,
      "step": 1
    },
    {
      "epoch": 0.0019375151368370065,
      "grad_norm": 8.16740894317627,
      "learning_rate": 4e-05,
      "loss": 10.2391,
      "step": 2
    },
    {
      "epoch": 0.00290627270525551,
      "grad_norm": 10.407310485839844,
      "learning_rate": 6e-05,
      "loss": 10.9136,
      "step": 3
    },
    {
      "epoch": 0.00290627270525551,
      "eval_loss": 2.7827765941619873,
      "eval_runtime": 7.9007,
      "eval_samples_per_second": 55.059,
      "eval_steps_per_second": 27.593,
      "step": 3
    },
    {
      "epoch": 0.003875030273674013,
      "grad_norm": 10.340521812438965,
      "learning_rate": 8e-05,
      "loss": 10.3661,
      "step": 4
    },
    {
      "epoch": 0.004843787842092516,
      "grad_norm": 11.17447280883789,
      "learning_rate": 0.0001,
      "loss": 11.1699,
      "step": 5
    },
    {
      "epoch": 0.00581254541051102,
      "grad_norm": 10.030872344970703,
      "learning_rate": 0.00012,
      "loss": 10.6455,
      "step": 6
    },
    {
      "epoch": 0.00581254541051102,
      "eval_loss": 2.499315023422241,
      "eval_runtime": 8.0644,
      "eval_samples_per_second": 53.941,
      "eval_steps_per_second": 27.032,
      "step": 6
    },
    {
      "epoch": 0.006781302978929523,
      "grad_norm": 11.862367630004883,
      "learning_rate": 0.00014,
      "loss": 9.8063,
      "step": 7
    },
    {
      "epoch": 0.007750060547348026,
      "grad_norm": 9.301877975463867,
      "learning_rate": 0.00016,
      "loss": 9.0216,
      "step": 8
    },
    {
      "epoch": 0.00871881811576653,
      "grad_norm": 8.93769359588623,
      "learning_rate": 0.00018,
      "loss": 8.7468,
      "step": 9
    },
    {
      "epoch": 0.00871881811576653,
      "eval_loss": 1.897975206375122,
      "eval_runtime": 7.8608,
      "eval_samples_per_second": 55.338,
      "eval_steps_per_second": 27.733,
      "step": 9
    },
    {
      "epoch": 0.009687575684185032,
      "grad_norm": 7.668942451477051,
      "learning_rate": 0.0002,
      "loss": 7.9645,
      "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": 750891722342400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}