{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18691588785046728,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003738317757009346,
      "eval_loss": 3.356201171875,
      "eval_runtime": 39.4512,
      "eval_samples_per_second": 11.432,
      "eval_steps_per_second": 1.445,
      "step": 1
    },
    {
      "epoch": 0.011214953271028037,
      "grad_norm": 10.225142478942871,
      "learning_rate": 3e-05,
      "loss": 3.4561,
      "step": 3
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 2.506544589996338,
      "eval_runtime": 40.0711,
      "eval_samples_per_second": 11.255,
      "eval_steps_per_second": 1.422,
      "step": 5
    },
    {
      "epoch": 0.022429906542056073,
      "grad_norm": 6.831135272979736,
      "learning_rate": 6e-05,
      "loss": 2.8683,
      "step": 6
    },
    {
      "epoch": 0.03364485981308411,
      "grad_norm": 6.806216716766357,
      "learning_rate": 9e-05,
      "loss": 2.2714,
      "step": 9
    },
    {
      "epoch": 0.037383177570093455,
      "eval_loss": 1.89436936378479,
      "eval_runtime": 40.0997,
      "eval_samples_per_second": 11.247,
      "eval_steps_per_second": 1.421,
      "step": 10
    },
    {
      "epoch": 0.044859813084112146,
      "grad_norm": 5.123374938964844,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.986,
      "step": 12
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 4.615382671356201,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7308,
      "step": 15
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 1.6895991563796997,
      "eval_runtime": 40.1021,
      "eval_samples_per_second": 11.246,
      "eval_steps_per_second": 1.421,
      "step": 15
    },
    {
      "epoch": 0.06728971962616823,
      "grad_norm": 4.685133457183838,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6272,
      "step": 18
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 1.5995190143585205,
      "eval_runtime": 40.0882,
      "eval_samples_per_second": 11.25,
      "eval_steps_per_second": 1.422,
      "step": 20
    },
    {
      "epoch": 0.07850467289719626,
      "grad_norm": 4.204235553741455,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.6219,
      "step": 21
    },
    {
      "epoch": 0.08971962616822429,
      "grad_norm": 3.952303647994995,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.5429,
      "step": 24
    },
    {
      "epoch": 0.09345794392523364,
      "eval_loss": 1.5367388725280762,
      "eval_runtime": 40.085,
      "eval_samples_per_second": 11.251,
      "eval_steps_per_second": 1.422,
      "step": 25
    },
    {
      "epoch": 0.10093457943925234,
      "grad_norm": 3.8612864017486572,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.5595,
      "step": 27
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 5.475238800048828,
      "learning_rate": 5e-05,
      "loss": 1.4384,
      "step": 30
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 1.50581693649292,
      "eval_runtime": 40.1174,
      "eval_samples_per_second": 11.242,
      "eval_steps_per_second": 1.421,
      "step": 30
    },
    {
      "epoch": 0.1233644859813084,
      "grad_norm": 4.102995872497559,
      "learning_rate": 3.832773180720475e-05,
      "loss": 1.5612,
      "step": 33
    },
    {
      "epoch": 0.1308411214953271,
      "eval_loss": 1.483141303062439,
      "eval_runtime": 40.2029,
      "eval_samples_per_second": 11.218,
      "eval_steps_per_second": 1.418,
      "step": 35
    },
    {
      "epoch": 0.13457943925233645,
      "grad_norm": 3.9326908588409424,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.4843,
      "step": 36
    },
    {
      "epoch": 0.14579439252336449,
      "grad_norm": 3.5036063194274902,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 1.4234,
      "step": 39
    },
    {
      "epoch": 0.14953271028037382,
      "eval_loss": 1.4650609493255615,
      "eval_runtime": 40.1268,
      "eval_samples_per_second": 11.239,
      "eval_steps_per_second": 1.42,
      "step": 40
    },
    {
      "epoch": 0.15700934579439252,
      "grad_norm": 3.635544538497925,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4576,
      "step": 42
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 3.66231632232666,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.3813,
      "step": 45
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 1.4580384492874146,
      "eval_runtime": 40.1352,
      "eval_samples_per_second": 11.237,
      "eval_steps_per_second": 1.42,
      "step": 45
    },
    {
      "epoch": 0.17943925233644858,
      "grad_norm": 4.305198669433594,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.4448,
      "step": 48
    },
    {
      "epoch": 0.18691588785046728,
      "eval_loss": 1.4549893140792847,
      "eval_runtime": 40.1439,
      "eval_samples_per_second": 11.235,
      "eval_steps_per_second": 1.42,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.81641131753472e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}