{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03350515463917526,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "eval_loss": 11.346135139465332,
      "eval_runtime": 74.0826,
      "eval_samples_per_second": 6.628,
      "eval_steps_per_second": 3.321,
      "step": 1
    },
    {
      "epoch": 0.00429553264604811,
      "grad_norm": 143.0156707763672,
      "learning_rate": 5e-05,
      "loss": 44.7211,
      "step": 5
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 110.60596466064453,
      "learning_rate": 0.0001,
      "loss": 25.5207,
      "step": 10
    },
    {
      "epoch": 0.00859106529209622,
      "eval_loss": 2.024148941040039,
      "eval_runtime": 74.3702,
      "eval_samples_per_second": 6.602,
      "eval_steps_per_second": 3.308,
      "step": 10
    },
    {
      "epoch": 0.01288659793814433,
      "grad_norm": 63.61037826538086,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.2074,
      "step": 15
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 57.09468078613281,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4869,
      "step": 20
    },
    {
      "epoch": 0.01718213058419244,
      "eval_loss": 0.79156494140625,
      "eval_runtime": 75.4961,
      "eval_samples_per_second": 6.504,
      "eval_steps_per_second": 3.258,
      "step": 20
    },
    {
      "epoch": 0.02147766323024055,
      "grad_norm": 65.97125244140625,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.9544,
      "step": 25
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 39.98679733276367,
      "learning_rate": 5e-05,
      "loss": 2.3217,
      "step": 30
    },
    {
      "epoch": 0.02577319587628866,
      "eval_loss": 0.5785247087478638,
      "eval_runtime": 73.9753,
      "eval_samples_per_second": 6.637,
      "eval_steps_per_second": 3.325,
      "step": 30
    },
    {
      "epoch": 0.03006872852233677,
      "grad_norm": 52.07625198364258,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.4132,
      "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": 8544265206497280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}