{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0030470618705912824,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.094123741182565e-05,
      "eval_loss": 1.1116701364517212,
      "eval_runtime": 444.2029,
      "eval_samples_per_second": 15.556,
      "eval_steps_per_second": 7.778,
      "step": 1
    },
    {
      "epoch": 0.00030470618705912824,
      "grad_norm": 11.430123329162598,
      "learning_rate": 5e-05,
      "loss": 4.1185,
      "step": 5
    },
    {
      "epoch": 0.0006094123741182565,
      "grad_norm": 11.45081615447998,
      "learning_rate": 0.0001,
      "loss": 3.9627,
      "step": 10
    },
    {
      "epoch": 0.0006094123741182565,
      "eval_loss": 0.7257492542266846,
      "eval_runtime": 447.4052,
      "eval_samples_per_second": 15.445,
      "eval_steps_per_second": 7.722,
      "step": 10
    },
    {
      "epoch": 0.0009141185611773847,
      "grad_norm": 20.893524169921875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6412,
      "step": 15
    },
    {
      "epoch": 0.001218824748236513,
      "grad_norm": 11.350746154785156,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5286,
      "step": 20
    },
    {
      "epoch": 0.001218824748236513,
      "eval_loss": 0.6027580499649048,
      "eval_runtime": 446.9736,
      "eval_samples_per_second": 15.46,
      "eval_steps_per_second": 7.73,
      "step": 20
    },
    {
      "epoch": 0.0015235309352956412,
      "grad_norm": 14.427254676818848,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2457,
      "step": 25
    },
    {
      "epoch": 0.0018282371223547695,
      "grad_norm": 14.359031677246094,
      "learning_rate": 5e-05,
      "loss": 2.4489,
      "step": 30
    },
    {
      "epoch": 0.0018282371223547695,
      "eval_loss": 0.5545990467071533,
      "eval_runtime": 447.3015,
      "eval_samples_per_second": 15.448,
      "eval_steps_per_second": 7.724,
      "step": 30
    },
    {
      "epoch": 0.0021329433094138977,
      "grad_norm": 11.400191307067871,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.4478,
      "step": 35
    },
    {
      "epoch": 0.002437649496473026,
      "grad_norm": 12.58128833770752,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3479,
      "step": 40
    },
    {
      "epoch": 0.002437649496473026,
      "eval_loss": 0.5402848720550537,
      "eval_runtime": 446.3571,
      "eval_samples_per_second": 15.481,
      "eval_steps_per_second": 7.74,
      "step": 40
    },
    {
      "epoch": 0.002742355683532154,
      "grad_norm": 10.086579322814941,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0741,
      "step": 45
    },
    {
      "epoch": 0.0030470618705912824,
      "grad_norm": 13.44519329071045,
      "learning_rate": 0.0,
      "loss": 2.0932,
      "step": 50
    },
    {
      "epoch": 0.0030470618705912824,
      "eval_loss": 0.5375238060951233,
      "eval_runtime": 445.8274,
      "eval_samples_per_second": 15.499,
      "eval_steps_per_second": 7.75,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8763348929740800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}