{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018195050946142648,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009097525473071324,
      "grad_norm": 1.0602493286132812,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 1.7156932830810547,
      "step": 5
    },
    {
      "epoch": 0.001819505094614265,
      "grad_norm": 1.1577719449996948,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.6629371643066406,
      "step": 10
    },
    {
      "epoch": 0.0027292576419213972,
      "grad_norm": 1.0288419723510742,
      "learning_rate": 4.242424242424243e-06,
      "loss": 1.6706295013427734,
      "step": 15
    },
    {
      "epoch": 0.00363901018922853,
      "grad_norm": 2.129403829574585,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 1.7363752365112304,
      "step": 20
    },
    {
      "epoch": 0.004548762736535662,
      "grad_norm": 1.9468326568603516,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.7111135482788087,
      "step": 25
    },
    {
      "epoch": 0.0054585152838427945,
      "grad_norm": 1.1269357204437256,
      "learning_rate": 8.787878787878788e-06,
      "loss": 1.6924203872680663,
      "step": 30
    },
    {
      "epoch": 0.006368267831149927,
      "grad_norm": 1.4021248817443848,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 1.658310317993164,
      "step": 35
    },
    {
      "epoch": 0.00727802037845706,
      "grad_norm": 1.313381314277649,
      "learning_rate": 1.1818181818181819e-05,
      "loss": 1.5383296012878418,
      "step": 40
    },
    {
      "epoch": 0.008187772925764192,
      "grad_norm": 2.4359891414642334,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.4302565574645996,
      "step": 45
    },
    {
      "epoch": 0.009097525473071324,
      "grad_norm": 1.6459542512893677,
      "learning_rate": 1.484848484848485e-05,
      "loss": 1.2602953910827637,
      "step": 50
    },
    {
      "epoch": 0.010007278020378457,
      "grad_norm": 0.7953159213066101,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 1.204326343536377,
      "step": 55
    },
    {
      "epoch": 0.010917030567685589,
      "grad_norm": 0.5824465155601501,
      "learning_rate": 1.787878787878788e-05,
      "loss": 1.068561840057373,
      "step": 60
    },
    {
      "epoch": 0.011826783114992722,
      "grad_norm": 0.39265626668930054,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 0.9570062637329102,
      "step": 65
    },
    {
      "epoch": 0.012736535662299854,
      "grad_norm": 0.3387283384799957,
      "learning_rate": 2.090909090909091e-05,
      "loss": 0.9454713821411133,
      "step": 70
    },
    {
      "epoch": 0.013646288209606987,
      "grad_norm": 0.3182811141014099,
      "learning_rate": 2.2424242424242424e-05,
      "loss": 0.8901592254638672,
      "step": 75
    },
    {
      "epoch": 0.01455604075691412,
      "grad_norm": 0.2735312879085541,
      "learning_rate": 2.393939393939394e-05,
      "loss": 0.8491583824157715,
      "step": 80
    },
    {
      "epoch": 0.015465793304221253,
      "grad_norm": 0.2376435250043869,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.8109179496765136,
      "step": 85
    },
    {
      "epoch": 0.016375545851528384,
      "grad_norm": 0.2161586880683899,
      "learning_rate": 2.696969696969697e-05,
      "loss": 0.76962308883667,
      "step": 90
    },
    {
      "epoch": 0.017285298398835518,
      "grad_norm": 0.19587980210781097,
      "learning_rate": 2.8484848484848486e-05,
      "loss": 0.7301986694335938,
      "step": 95
    },
    {
      "epoch": 0.018195050946142648,
      "grad_norm": 0.20971694588661194,
      "learning_rate": 3e-05,
      "loss": 0.7269618034362793,
      "step": 100
    },
    {
      "epoch": 0.018195050946142648,
      "eval_loss": 2.605874538421631,
      "eval_runtime": 1120.0905,
      "eval_samples_per_second": 33.935,
      "eval_steps_per_second": 8.484,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 5500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.444622973392128e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}