{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 2.2969371386238957,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.1002,
      "mean_token_accuracy": 0.7101446067721007,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 1.599655882409858,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.0326,
      "mean_token_accuracy": 0.720217587158131,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.8591737911535225,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.9517,
      "mean_token_accuracy": 0.7325624782557657,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.6537620090945541,
      "learning_rate": 1.9980782984658682e-05,
      "loss": 0.8804,
      "mean_token_accuracy": 0.747315623486313,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.5626159743908715,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.8535,
      "mean_token_accuracy": 0.7518164318158592,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.45239186672420045,
      "learning_rate": 1.9641197940012136e-05,
      "loss": 0.8403,
      "mean_token_accuracy": 0.754492059756761,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.4065940873665812,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.8211,
      "mean_token_accuracy": 0.7580338271214584,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.39452821445326464,
      "learning_rate": 1.8891222681391853e-05,
      "loss": 0.805,
      "mean_token_accuracy": 0.7621366468999315,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.43615140436248484,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.7984,
      "mean_token_accuracy": 0.7634534915718657,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.40897882052169277,
      "learning_rate": 1.7762780887657576e-05,
      "loss": 0.7937,
      "mean_token_accuracy": 0.7642631825866457,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.3934056939935861,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7894,
      "mean_token_accuracy": 0.7648874822587992,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.3835818684618293,
      "learning_rate": 1.6303906161279554e-05,
      "loss": 0.7999,
      "mean_token_accuracy": 0.7618815283957869,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.41676578966955,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.7868,
      "mean_token_accuracy": 0.7646762189415368,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.38604208282767477,
      "learning_rate": 1.4576697415156818e-05,
      "loss": 0.7782,
      "mean_token_accuracy": 0.7674216701876162,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.34491198371865256,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.777,
      "mean_token_accuracy": 0.76739472582752,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.3545713954868883,
      "learning_rate": 1.2654675551080724e-05,
      "loss": 0.7783,
      "mean_token_accuracy": 0.7666177428258865,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.34818148060045734,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.7786,
      "mean_token_accuracy": 0.7669220020236132,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.3565736849035567,
      "learning_rate": 1.0619653946285948e-05,
      "loss": 0.7723,
      "mean_token_accuracy": 0.7682009980189979,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.3537178699761323,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.7669,
      "mean_token_accuracy": 0.7697011663272294,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.3531080062917971,
      "learning_rate": 8.558255959926533e-06,
      "loss": 0.7583,
      "mean_token_accuracy": 0.7714170831326739,
      "step": 100
    },
    {
      "epoch": 0.591715976331361,
      "eval_loss": 0.78866046667099,
      "eval_mean_token_accuracy": 0.7461942087555458,
      "eval_runtime": 7.5243,
      "eval_samples_per_second": 17.145,
      "eval_steps_per_second": 0.665,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.36738387583651133,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.7591,
      "mean_token_accuracy": 0.7714642960757494,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.32538447874883847,
      "learning_rate": 6.558227696373617e-06,
      "loss": 0.7776,
      "mean_token_accuracy": 0.7664523090217555,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.3179989412846765,
      "learning_rate": 5.608034111526298e-06,
      "loss": 0.7636,
      "mean_token_accuracy": 0.770315125879508,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.3052106277563726,
      "learning_rate": 4.704702977392914e-06,
      "loss": 0.7511,
      "mean_token_accuracy": 0.7742495275883904,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.32605995739738175,
      "learning_rate": 3.857872873103322e-06,
      "loss": 0.7595,
      "mean_token_accuracy": 0.7716744486118571,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.3282824225556175,
      "learning_rate": 3.0765795095517026e-06,
      "loss": 0.7624,
      "mean_token_accuracy": 0.77055823269281,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.30913277591910504,
      "learning_rate": 2.369159318001937e-06,
      "loss": 0.7685,
      "mean_token_accuracy": 0.7688454319463202,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.2996201823780971,
      "learning_rate": 1.743160500034443e-06,
      "loss": 0.7597,
      "mean_token_accuracy": 0.7716544765230906,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.32224112388752324,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.7595,
      "mean_token_accuracy": 0.771391836420342,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.296138773442598,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.7506,
      "mean_token_accuracy": 0.7738967549477684,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.28618930010153404,
      "learning_rate": 4.1572517541747294e-07,
      "loss": 0.7411,
      "mean_token_accuracy": 0.7766712678094867,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.30142507408078706,
      "learning_rate": 1.7251026952640583e-07,
      "loss": 0.7541,
      "mean_token_accuracy": 0.7731741454593504,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.2822294261720235,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 0.7468,
      "mean_token_accuracy": 0.7749281821231958,
      "step": 165
    },
    {
      "epoch": 1.0,
      "mean_token_accuracy": 0.7704734585204958,
      "step": 169,
      "total_flos": 76973799899136.0,
      "train_loss": 0.8025316867602648,
      "train_runtime": 1272.0859,
      "train_samples_per_second": 16.998,
      "train_steps_per_second": 0.133
    }
  ],
  "logging_steps": 5,
  "max_steps": 169,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 76973799899136.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}