{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03971405877680699,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015885623510722795,
      "grad_norm": 0.7588194012641907,
      "learning_rate": 1e-05,
      "loss": 2.0204,
      "step": 1
    },
    {
      "epoch": 0.0015885623510722795,
      "eval_loss": 2.1602227687835693,
      "eval_runtime": 25.7941,
      "eval_samples_per_second": 20.547,
      "eval_steps_per_second": 2.597,
      "step": 1
    },
    {
      "epoch": 0.003177124702144559,
      "grad_norm": 0.5876681208610535,
      "learning_rate": 2e-05,
      "loss": 2.0054,
      "step": 2
    },
    {
      "epoch": 0.004765687053216839,
      "grad_norm": 0.7118221521377563,
      "learning_rate": 3e-05,
      "loss": 2.1649,
      "step": 3
    },
    {
      "epoch": 0.006354249404289118,
      "grad_norm": 0.604448139667511,
      "learning_rate": 4e-05,
      "loss": 1.9918,
      "step": 4
    },
    {
      "epoch": 0.007942811755361398,
      "grad_norm": 1.1285226345062256,
      "learning_rate": 5e-05,
      "loss": 2.9166,
      "step": 5
    },
    {
      "epoch": 0.009531374106433678,
      "grad_norm": 0.7710039019584656,
      "learning_rate": 6e-05,
      "loss": 2.0509,
      "step": 6
    },
    {
      "epoch": 0.011119936457505957,
      "grad_norm": 0.731193482875824,
      "learning_rate": 7e-05,
      "loss": 1.8467,
      "step": 7
    },
    {
      "epoch": 0.012708498808578236,
      "grad_norm": 0.6948415040969849,
      "learning_rate": 8e-05,
      "loss": 1.7287,
      "step": 8
    },
    {
      "epoch": 0.014297061159650517,
      "grad_norm": 0.6710980534553528,
      "learning_rate": 9e-05,
      "loss": 2.1689,
      "step": 9
    },
    {
      "epoch": 0.014297061159650517,
      "eval_loss": 2.0491185188293457,
      "eval_runtime": 25.1257,
      "eval_samples_per_second": 21.094,
      "eval_steps_per_second": 2.667,
      "step": 9
    },
    {
      "epoch": 0.015885623510722795,
      "grad_norm": 0.6445783376693726,
      "learning_rate": 0.0001,
      "loss": 1.8429,
      "step": 10
    },
    {
      "epoch": 0.017474185861795076,
      "grad_norm": 0.6626678109169006,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.0179,
      "step": 11
    },
    {
      "epoch": 0.019062748212867357,
      "grad_norm": 0.6601588726043701,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.6245,
      "step": 12
    },
    {
      "epoch": 0.020651310563939634,
      "grad_norm": 0.8181198239326477,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.42,
      "step": 13
    },
    {
      "epoch": 0.022239872915011914,
      "grad_norm": 0.7023542523384094,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.3644,
      "step": 14
    },
    {
      "epoch": 0.023828435266084195,
      "grad_norm": 0.7344656586647034,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.4728,
      "step": 15
    },
    {
      "epoch": 0.025416997617156472,
      "grad_norm": 1.249544382095337,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.8716,
      "step": 16
    },
    {
      "epoch": 0.027005559968228753,
      "grad_norm": 0.8132469058036804,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.0647,
      "step": 17
    },
    {
      "epoch": 0.028594122319301033,
      "grad_norm": 0.9918925166130066,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0602,
      "step": 18
    },
    {
      "epoch": 0.028594122319301033,
      "eval_loss": 1.6575732231140137,
      "eval_runtime": 25.1955,
      "eval_samples_per_second": 21.036,
      "eval_steps_per_second": 2.659,
      "step": 18
    },
    {
      "epoch": 0.030182684670373314,
      "grad_norm": 0.9467197060585022,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.515,
      "step": 19
    },
    {
      "epoch": 0.03177124702144559,
      "grad_norm": 0.8416855931282043,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4362,
      "step": 20
    },
    {
      "epoch": 0.03335980937251787,
      "grad_norm": 2.2242186069488525,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.9894,
      "step": 21
    },
    {
      "epoch": 0.03494837172359015,
      "grad_norm": 1.3053258657455444,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.5462,
      "step": 22
    },
    {
      "epoch": 0.03653693407466243,
      "grad_norm": 1.1135425567626953,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.4904,
      "step": 23
    },
    {
      "epoch": 0.03812549642573471,
      "grad_norm": 1.121027946472168,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9785,
      "step": 24
    },
    {
      "epoch": 0.03971405877680699,
      "grad_norm": 0.9957679510116577,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1314,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3435415121952768.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}