{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01800761860787256,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004617338104582708,
      "eval_loss": 7.1389384269714355,
      "eval_runtime": 52.8697,
      "eval_samples_per_second": 17.25,
      "eval_steps_per_second": 8.625,
      "step": 1
    },
    {
      "epoch": 0.002308669052291354,
      "grad_norm": 7.467071533203125,
      "learning_rate": 5e-05,
      "loss": 6.8472,
      "step": 5
    },
    {
      "epoch": 0.004617338104582708,
      "grad_norm": 12.589896202087402,
      "learning_rate": 0.0001,
      "loss": 6.3527,
      "step": 10
    },
    {
      "epoch": 0.004617338104582708,
      "eval_loss": 4.855079174041748,
      "eval_runtime": 53.5111,
      "eval_samples_per_second": 17.043,
      "eval_steps_per_second": 8.522,
      "step": 10
    },
    {
      "epoch": 0.006926007156874062,
      "grad_norm": 18.49090576171875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.5476,
      "step": 15
    },
    {
      "epoch": 0.009234676209165417,
      "grad_norm": 8.904321670532227,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0529,
      "step": 20
    },
    {
      "epoch": 0.009234676209165417,
      "eval_loss": 1.4587453603744507,
      "eval_runtime": 54.09,
      "eval_samples_per_second": 16.861,
      "eval_steps_per_second": 8.43,
      "step": 20
    },
    {
      "epoch": 0.01154334526145677,
      "grad_norm": 5.717966556549072,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6869,
      "step": 25
    },
    {
      "epoch": 0.013852014313748124,
      "grad_norm": 3.3944246768951416,
      "learning_rate": 5e-05,
      "loss": 1.3047,
      "step": 30
    },
    {
      "epoch": 0.013852014313748124,
      "eval_loss": 1.122319221496582,
      "eval_runtime": 54.2173,
      "eval_samples_per_second": 16.821,
      "eval_steps_per_second": 8.411,
      "step": 30
    },
    {
      "epoch": 0.01616068336603948,
      "grad_norm": 3.425913095474243,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.238,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6352063155929088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}