{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026689478186484174,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.843455945252352e-05,
      "eval_loss": 4.274598598480225,
      "eval_runtime": 207.9386,
      "eval_samples_per_second": 29.59,
      "eval_steps_per_second": 14.798,
      "step": 1
    },
    {
      "epoch": 0.00034217279726261765,
      "grad_norm": 5.358638763427734,
      "learning_rate": 5e-05,
      "loss": 3.9299,
      "step": 5
    },
    {
      "epoch": 0.0006843455945252353,
      "grad_norm": 3.2354540824890137,
      "learning_rate": 0.0001,
      "loss": 2.5334,
      "step": 10
    },
    {
      "epoch": 0.0006843455945252353,
      "eval_loss": 2.817838430404663,
      "eval_runtime": 208.4384,
      "eval_samples_per_second": 29.52,
      "eval_steps_per_second": 14.762,
      "step": 10
    },
    {
      "epoch": 0.001026518391787853,
      "grad_norm": 2.3510193824768066,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4891,
      "step": 15
    },
    {
      "epoch": 0.0013686911890504706,
      "grad_norm": 3.4666836261749268,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7616,
      "step": 20
    },
    {
      "epoch": 0.0013686911890504706,
      "eval_loss": 0.4284217357635498,
      "eval_runtime": 210.0757,
      "eval_samples_per_second": 29.289,
      "eval_steps_per_second": 14.647,
      "step": 20
    },
    {
      "epoch": 0.001710863986313088,
      "grad_norm": 2.8414981365203857,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.332,
      "step": 25
    },
    {
      "epoch": 0.002053036783575706,
      "grad_norm": 1.8734856843948364,
      "learning_rate": 5e-05,
      "loss": 0.2611,
      "step": 30
    },
    {
      "epoch": 0.002053036783575706,
      "eval_loss": 0.11418327689170837,
      "eval_runtime": 210.3356,
      "eval_samples_per_second": 29.253,
      "eval_steps_per_second": 14.629,
      "step": 30
    },
    {
      "epoch": 0.0023952095808383233,
      "grad_norm": 1.3314682245254517,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1127,
      "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": 1469478114164736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}