{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009338279162667636,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010375865736297373,
      "grad_norm": 1.1354926824569702,
      "learning_rate": 2e-05,
      "loss": 2.1367,
      "step": 1
    },
    {
      "epoch": 0.00010375865736297373,
      "eval_loss": 2.0775890350341797,
      "eval_runtime": 82.2723,
      "eval_samples_per_second": 49.324,
      "eval_steps_per_second": 24.662,
      "step": 1
    },
    {
      "epoch": 0.00020751731472594745,
      "grad_norm": 1.1936341524124146,
      "learning_rate": 4e-05,
      "loss": 2.0164,
      "step": 2
    },
    {
      "epoch": 0.00031127597208892115,
      "grad_norm": 1.2371667623519897,
      "learning_rate": 6e-05,
      "loss": 2.1292,
      "step": 3
    },
    {
      "epoch": 0.00031127597208892115,
      "eval_loss": 2.074251413345337,
      "eval_runtime": 80.6,
      "eval_samples_per_second": 50.347,
      "eval_steps_per_second": 25.174,
      "step": 3
    },
    {
      "epoch": 0.0004150346294518949,
      "grad_norm": 1.0456353425979614,
      "learning_rate": 8e-05,
      "loss": 1.9339,
      "step": 4
    },
    {
      "epoch": 0.0005187932868148687,
      "grad_norm": 1.2975083589553833,
      "learning_rate": 0.0001,
      "loss": 2.0544,
      "step": 5
    },
    {
      "epoch": 0.0006225519441778423,
      "grad_norm": 1.0521240234375,
      "learning_rate": 0.00012,
      "loss": 2.1387,
      "step": 6
    },
    {
      "epoch": 0.0006225519441778423,
      "eval_loss": 2.0402276515960693,
      "eval_runtime": 80.8247,
      "eval_samples_per_second": 50.207,
      "eval_steps_per_second": 25.104,
      "step": 6
    },
    {
      "epoch": 0.000726310601540816,
      "grad_norm": 1.1553844213485718,
      "learning_rate": 0.00014,
      "loss": 1.9767,
      "step": 7
    },
    {
      "epoch": 0.0008300692589037898,
      "grad_norm": 1.0176719427108765,
      "learning_rate": 0.00016,
      "loss": 1.7407,
      "step": 8
    },
    {
      "epoch": 0.0009338279162667636,
      "grad_norm": 1.0879982709884644,
      "learning_rate": 0.00018,
      "loss": 1.8643,
      "step": 9
    },
    {
      "epoch": 0.0009338279162667636,
      "eval_loss": 1.9784159660339355,
      "eval_runtime": 81.6761,
      "eval_samples_per_second": 49.684,
      "eval_steps_per_second": 24.842,
      "step": 9
    }
  ],
  "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": 109071750660096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}