{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003373724310495094,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011245747701650313,
      "eval_loss": 0.2725933790206909,
      "eval_runtime": 783.1851,
      "eval_samples_per_second": 4.782,
      "eval_steps_per_second": 2.392,
      "step": 1
    },
    {
      "epoch": 0.0003373724310495094,
      "grad_norm": 0.4556724727153778,
      "learning_rate": 6e-05,
      "loss": 0.2498,
      "step": 3
    },
    {
      "epoch": 0.0006747448620990188,
      "grad_norm": 0.6135880947113037,
      "learning_rate": 0.00012,
      "loss": 0.2376,
      "step": 6
    },
    {
      "epoch": 0.000899659816132025,
      "eval_loss": 0.12375504523515701,
      "eval_runtime": 787.1556,
      "eval_samples_per_second": 4.758,
      "eval_steps_per_second": 2.379,
      "step": 8
    },
    {
      "epoch": 0.0010121172931485281,
      "grad_norm": 0.7029567956924438,
      "learning_rate": 0.00018,
      "loss": 0.1598,
      "step": 9
    },
    {
      "epoch": 0.0013494897241980376,
      "grad_norm": 0.5015170574188232,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.1172,
      "step": 12
    },
    {
      "epoch": 0.001686862155247547,
      "grad_norm": 0.4365912675857544,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0597,
      "step": 15
    },
    {
      "epoch": 0.00179931963226405,
      "eval_loss": 0.0423223152756691,
      "eval_runtime": 787.2146,
      "eval_samples_per_second": 4.757,
      "eval_steps_per_second": 2.379,
      "step": 16
    },
    {
      "epoch": 0.0020242345862970562,
      "grad_norm": 0.38968926668167114,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0475,
      "step": 18
    },
    {
      "epoch": 0.002361607017346566,
      "grad_norm": 0.2808378040790558,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0315,
      "step": 21
    },
    {
      "epoch": 0.0026989794483960753,
      "grad_norm": 0.34844180941581726,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0352,
      "step": 24
    },
    {
      "epoch": 0.0026989794483960753,
      "eval_loss": 0.029852185398340225,
      "eval_runtime": 786.1536,
      "eval_samples_per_second": 4.764,
      "eval_steps_per_second": 2.382,
      "step": 24
    },
    {
      "epoch": 0.0030363518794455846,
      "grad_norm": 0.27075034379959106,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0229,
      "step": 27
    },
    {
      "epoch": 0.003373724310495094,
      "grad_norm": 0.7711063623428345,
      "learning_rate": 0.0,
      "loss": 0.0375,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7434351163670528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}