{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016680567139282735,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.336113427856547e-05,
      "eval_loss": 1.107438325881958,
      "eval_runtime": 1718.9524,
      "eval_samples_per_second": 7.343,
      "eval_steps_per_second": 3.671,
      "step": 1
    },
    {
      "epoch": 0.00016680567139282736,
      "grad_norm": 1.0560085773468018,
      "learning_rate": 5e-05,
      "loss": 1.062,
      "step": 5
    },
    {
      "epoch": 0.0003336113427856547,
      "grad_norm": 0.9505082368850708,
      "learning_rate": 0.0001,
      "loss": 0.9234,
      "step": 10
    },
    {
      "epoch": 0.0003336113427856547,
      "eval_loss": 0.9549250602722168,
      "eval_runtime": 1744.1048,
      "eval_samples_per_second": 7.237,
      "eval_steps_per_second": 3.618,
      "step": 10
    },
    {
      "epoch": 0.000500417014178482,
      "grad_norm": 1.028267741203308,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9017,
      "step": 15
    },
    {
      "epoch": 0.0006672226855713094,
      "grad_norm": 1.0977561473846436,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8243,
      "step": 20
    },
    {
      "epoch": 0.0006672226855713094,
      "eval_loss": 0.8327227830886841,
      "eval_runtime": 1743.8221,
      "eval_samples_per_second": 7.238,
      "eval_steps_per_second": 3.619,
      "step": 20
    },
    {
      "epoch": 0.0008340283569641367,
      "grad_norm": 1.179917812347412,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8459,
      "step": 25
    },
    {
      "epoch": 0.001000834028356964,
      "grad_norm": 1.220489740371704,
      "learning_rate": 5e-05,
      "loss": 0.7362,
      "step": 30
    },
    {
      "epoch": 0.001000834028356964,
      "eval_loss": 0.7774187326431274,
      "eval_runtime": 1745.7698,
      "eval_samples_per_second": 7.23,
      "eval_steps_per_second": 3.615,
      "step": 30
    },
    {
      "epoch": 0.0011676396997497916,
      "grad_norm": 1.155003547668457,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8172,
      "step": 35
    },
    {
      "epoch": 0.0013344453711426189,
      "grad_norm": 1.0777671337127686,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7301,
      "step": 40
    },
    {
      "epoch": 0.0013344453711426189,
      "eval_loss": 0.7576377391815186,
      "eval_runtime": 1747.0451,
      "eval_samples_per_second": 7.225,
      "eval_steps_per_second": 3.612,
      "step": 40
    },
    {
      "epoch": 0.0015012510425354462,
      "grad_norm": 1.1099690198898315,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7626,
      "step": 45
    },
    {
      "epoch": 0.0016680567139282735,
      "grad_norm": 1.361476182937622,
      "learning_rate": 0.0,
      "loss": 0.7898,
      "step": 50
    },
    {
      "epoch": 0.0016680567139282735,
      "eval_loss": 0.7537627816200256,
      "eval_runtime": 1745.7828,
      "eval_samples_per_second": 7.23,
      "eval_steps_per_second": 3.615,
      "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": 1.433412292313088e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}