{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007751937984496124,
      "grad_norm": 18.670406341552734,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.7022,
      "step": 1
    },
    {
      "epoch": 0.03875968992248062,
      "grad_norm": 27.956096649169922,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.6412,
      "step": 5
    },
    {
      "epoch": 0.07751937984496124,
      "grad_norm": 6.442818641662598,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.5704,
      "step": 10
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 5.311695098876953,
      "learning_rate": 1.998533413851124e-05,
      "loss": 0.5628,
      "step": 15
    },
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 2.338909149169922,
      "learning_rate": 1.982083682742156e-05,
      "loss": 0.5298,
      "step": 20
    },
    {
      "epoch": 0.1937984496124031,
      "grad_norm": 3.053166151046753,
      "learning_rate": 1.9476531711828027e-05,
      "loss": 0.5377,
      "step": 25
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 1.823050618171692,
      "learning_rate": 1.8958722607586883e-05,
      "loss": 0.5015,
      "step": 30
    },
    {
      "epoch": 0.2713178294573643,
      "grad_norm": 2.082890033721924,
      "learning_rate": 1.827688998156891e-05,
      "loss": 0.5019,
      "step": 35
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.6335759162902832,
      "learning_rate": 1.7443517375622706e-05,
      "loss": 0.4828,
      "step": 40
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 1.522133469581604,
      "learning_rate": 1.647386284781828e-05,
      "loss": 0.4751,
      "step": 45
    },
    {
      "epoch": 0.3875968992248062,
      "grad_norm": 1.3869783878326416,
      "learning_rate": 1.5385679615609045e-05,
      "loss": 0.4726,
      "step": 50
    },
    {
      "epoch": 0.4263565891472868,
      "grad_norm": 1.2799592018127441,
      "learning_rate": 1.4198891015602648e-05,
      "loss": 0.4608,
      "step": 55
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.2317698001861572,
      "learning_rate": 1.2935225731039349e-05,
      "loss": 0.4507,
      "step": 60
    },
    {
      "epoch": 0.5038759689922481,
      "grad_norm": 13.605137825012207,
      "learning_rate": 1.161781996552765e-05,
      "loss": 0.4503,
      "step": 65
    },
    {
      "epoch": 0.5426356589147286,
      "grad_norm": 1.201204776763916,
      "learning_rate": 1.0270793846761347e-05,
      "loss": 0.4423,
      "step": 70
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 1.115617036819458,
      "learning_rate": 8.918809815760585e-06,
      "loss": 0.4404,
      "step": 75
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.1243541240692139,
      "learning_rate": 7.586621087002945e-06,
      "loss": 0.4309,
      "step": 80
    },
    {
      "epoch": 0.6589147286821705,
      "grad_norm": 1.0983189344406128,
      "learning_rate": 6.298618446600856e-06,
      "loss": 0.4217,
      "step": 85
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.9838166832923889,
      "learning_rate": 5.078383686109927e-06,
      "loss": 0.4165,
      "step": 90
    },
    {
      "epoch": 0.7364341085271318,
      "grad_norm": 1.0262510776519775,
      "learning_rate": 3.948257848062351e-06,
      "loss": 0.4057,
      "step": 95
    },
    {
      "epoch": 0.7751937984496124,
      "grad_norm": 1.020778775215149,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.3977,
      "step": 100
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.9869725108146667,
      "learning_rate": 2.0390693429435626e-06,
      "loss": 0.4028,
      "step": 105
    },
    {
      "epoch": 0.8527131782945736,
      "grad_norm": 0.9537738561630249,
      "learning_rate": 1.2949616394382802e-06,
      "loss": 0.3927,
      "step": 110
    },
    {
      "epoch": 0.8914728682170543,
      "grad_norm": 0.9723293781280518,
      "learning_rate": 7.102328018320859e-07,
      "loss": 0.3931,
      "step": 115
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.9556717872619629,
      "learning_rate": 2.955885174678852e-07,
      "loss": 0.3904,
      "step": 120
    },
    {
      "epoch": 0.9689922480620154,
      "grad_norm": 0.9231972694396973,
      "learning_rate": 5.862042845640403e-08,
      "loss": 0.3911,
      "step": 125
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.30268725752830505,
      "eval_runtime": 1.3209,
      "eval_samples_per_second": 0.757,
      "eval_steps_per_second": 0.757,
      "step": 129
    },
    {
      "epoch": 1.0,
      "step": 129,
      "total_flos": 54019951165440.0,
      "train_loss": 0.46054963455643766,
      "train_runtime": 2340.6782,
      "train_samples_per_second": 7.036,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 5,
  "max_steps": 129,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 54019951165440.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}