{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9977046671767407,
  "eval_steps": 100,
  "global_step": 163,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030604437643458302,
      "grad_norm": 3.3970731376928125,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.1112,
      "mean_token_accuracy": 0.7094654304029304,
      "step": 5
    },
    {
      "epoch": 0.061208875286916604,
      "grad_norm": 2.2804120824280973,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.0241,
      "mean_token_accuracy": 0.7180391483516483,
      "step": 10
    },
    {
      "epoch": 0.09181331293037491,
      "grad_norm": 1.9855849826774905,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8944,
      "mean_token_accuracy": 0.7411423992673991,
      "step": 15
    },
    {
      "epoch": 0.12241775057383321,
      "grad_norm": 1.9940429715066923,
      "learning_rate": 1.9979171608653926e-05,
      "loss": 0.8475,
      "mean_token_accuracy": 0.7502967182160716,
      "step": 20
    },
    {
      "epoch": 0.1530221882172915,
      "grad_norm": 1.7332254737436643,
      "learning_rate": 1.9852201067560607e-05,
      "loss": 0.8153,
      "mean_token_accuracy": 0.7577415293040294,
      "step": 25
    },
    {
      "epoch": 0.18362662586074982,
      "grad_norm": 1.1703063823859854,
      "learning_rate": 1.961129783872301e-05,
      "loss": 0.792,
      "mean_token_accuracy": 0.761659355685117,
      "step": 30
    },
    {
      "epoch": 0.21423106350420812,
      "grad_norm": 1.1837957959878118,
      "learning_rate": 1.92592477719385e-05,
      "loss": 0.7892,
      "mean_token_accuracy": 0.7606551434676435,
      "step": 35
    },
    {
      "epoch": 0.24483550114766642,
      "grad_norm": 1.132990595514252,
      "learning_rate": 1.880012203973536e-05,
      "loss": 0.7635,
      "mean_token_accuracy": 0.7672126831501831,
      "step": 40
    },
    {
      "epoch": 0.2754399387911247,
      "grad_norm": 0.8516933474943562,
      "learning_rate": 1.8239230057575542e-05,
      "loss": 0.7617,
      "mean_token_accuracy": 0.7670692155067157,
      "step": 45
    },
    {
      "epoch": 0.306044376434583,
      "grad_norm": 1.1031293443296253,
      "learning_rate": 1.7583058084785626e-05,
      "loss": 0.7442,
      "mean_token_accuracy": 0.771615533720253,
      "step": 50
    },
    {
      "epoch": 0.3366488140780413,
      "grad_norm": 0.9798666345967171,
      "learning_rate": 1.683919421624611e-05,
      "loss": 0.7453,
      "mean_token_accuracy": 0.7706131715506717,
      "step": 55
    },
    {
      "epoch": 0.36725325172149964,
      "grad_norm": 0.9485977354813016,
      "learning_rate": 1.6016240632249224e-05,
      "loss": 0.7368,
      "mean_token_accuracy": 0.7730052262013065,
      "step": 60
    },
    {
      "epoch": 0.3978576893649579,
      "grad_norm": 1.2694193605736983,
      "learning_rate": 1.512371412128424e-05,
      "loss": 0.7269,
      "mean_token_accuracy": 0.7752823565323563,
      "step": 65
    },
    {
      "epoch": 0.42846212700841624,
      "grad_norm": 0.8782855813281154,
      "learning_rate": 1.417193602612317e-05,
      "loss": 0.7151,
      "mean_token_accuracy": 0.7783085317460319,
      "step": 70
    },
    {
      "epoch": 0.4590665646518745,
      "grad_norm": 0.9272505638148284,
      "learning_rate": 1.3171912885891063e-05,
      "loss": 0.7196,
      "mean_token_accuracy": 0.7768939379325206,
      "step": 75
    },
    {
      "epoch": 0.48967100229533284,
      "grad_norm": 0.8935996954920208,
      "learning_rate": 1.2135209154397962e-05,
      "loss": 0.7115,
      "mean_token_accuracy": 0.7788835470085467,
      "step": 80
    },
    {
      "epoch": 0.5202754399387911,
      "grad_norm": 0.8470942739749459,
      "learning_rate": 1.1073813466641633e-05,
      "loss": 0.7077,
      "mean_token_accuracy": 0.7794299142529088,
      "step": 85
    },
    {
      "epoch": 0.5508798775822494,
      "grad_norm": 0.6942488142992079,
      "learning_rate": 1e-05,
      "loss": 0.7024,
      "mean_token_accuracy": 0.7809472751579388,
      "step": 90
    },
    {
      "epoch": 0.5814843152257078,
      "grad_norm": 0.6553271130090998,
      "learning_rate": 8.92618653335837e-06,
      "loss": 0.7029,
      "mean_token_accuracy": 0.7801850579975582,
      "step": 95
    },
    {
      "epoch": 0.612088752869166,
      "grad_norm": 0.7187580814482785,
      "learning_rate": 7.86479084560204e-06,
      "loss": 0.6952,
      "mean_token_accuracy": 0.7828430250305252,
      "step": 100
    },
    {
      "epoch": 0.612088752869166,
      "eval_loss": 0.7106685042381287,
      "eval_mean_token_accuracy": 0.7772175072801721,
      "eval_runtime": 3.2738,
      "eval_samples_per_second": 38.182,
      "eval_steps_per_second": 1.222,
      "step": 100
    },
    {
      "epoch": 0.6426931905126243,
      "grad_norm": 0.723936178395319,
      "learning_rate": 6.8280871141089415e-06,
      "loss": 0.6941,
      "mean_token_accuracy": 0.7826800002597876,
      "step": 105
    },
    {
      "epoch": 0.6732976281560826,
      "grad_norm": 0.6017745589094783,
      "learning_rate": 5.828063973876834e-06,
      "loss": 0.6882,
      "mean_token_accuracy": 0.7841101953601955,
      "step": 110
    },
    {
      "epoch": 0.703902065799541,
      "grad_norm": 0.6582719896847987,
      "learning_rate": 4.876285878715764e-06,
      "loss": 0.687,
      "mean_token_accuracy": 0.7845272435897437,
      "step": 115
    },
    {
      "epoch": 0.7345065034429993,
      "grad_norm": 0.5705645680946995,
      "learning_rate": 3.983759367750772e-06,
      "loss": 0.6929,
      "mean_token_accuracy": 0.7826304945054946,
      "step": 120
    },
    {
      "epoch": 0.7651109410864575,
      "grad_norm": 0.5372931015149021,
      "learning_rate": 3.1608057837538976e-06,
      "loss": 0.6901,
      "mean_token_accuracy": 0.7830860805860805,
      "step": 125
    },
    {
      "epoch": 0.7957153787299158,
      "grad_norm": 0.5211541425317051,
      "learning_rate": 2.416941915214377e-06,
      "loss": 0.6777,
      "mean_token_accuracy": 0.7878136446886447,
      "step": 130
    },
    {
      "epoch": 0.8263198163733741,
      "grad_norm": 0.5122826773929277,
      "learning_rate": 1.7607699424244583e-06,
      "loss": 0.6719,
      "mean_token_accuracy": 0.7880757783882787,
      "step": 135
    },
    {
      "epoch": 0.8569242540168325,
      "grad_norm": 0.48988270079315005,
      "learning_rate": 1.1998779602646438e-06,
      "loss": 0.6796,
      "mean_token_accuracy": 0.7866094322344324,
      "step": 140
    },
    {
      "epoch": 0.8875286916602907,
      "grad_norm": 0.49332634423273786,
      "learning_rate": 7.40752228061502e-07,
      "loss": 0.6764,
      "mean_token_accuracy": 0.7869864163614164,
      "step": 145
    },
    {
      "epoch": 0.918133129303749,
      "grad_norm": 0.49318593154509593,
      "learning_rate": 3.887021612769937e-07,
      "loss": 0.6765,
      "mean_token_accuracy": 0.7870028235653235,
      "step": 150
    },
    {
      "epoch": 0.9487375669472073,
      "grad_norm": 0.48631784015910273,
      "learning_rate": 1.4779893243939358e-07,
      "loss": 0.6738,
      "mean_token_accuracy": 0.7884276890128243,
      "step": 155
    },
    {
      "epoch": 0.9793420045906657,
      "grad_norm": 0.4834304838874901,
      "learning_rate": 2.082839134607828e-08,
      "loss": 0.6821,
      "mean_token_accuracy": 0.78588134204449,
      "step": 160
    },
    {
      "epoch": 0.9977046671767407,
      "mean_token_accuracy": 0.7896611954409772,
      "step": 163,
      "total_flos": 136410845675520.0,
      "train_loss": 0.7452732097883166,
      "train_runtime": 1860.6281,
      "train_samples_per_second": 11.237,
      "train_steps_per_second": 0.088
    }
  ],
  "logging_steps": 5,
  "max_steps": 163,
  "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": 136410845675520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}