{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.332671670988202,
      "epoch": 0.05952380952380952,
      "grad_norm": 0.0262451171875,
      "learning_rate": 0.00019963974885425266,
      "loss": 1.357326202392578,
      "mean_token_accuracy": 0.6980717657506466,
      "num_tokens": 321132.0,
      "step": 25
    },
    {
      "entropy": 0.8512209014082327,
      "epoch": 0.11904761904761904,
      "grad_norm": 0.0301513671875,
      "learning_rate": 0.00019616390338572803,
      "loss": 0.7703800964355468,
      "mean_token_accuracy": 0.8097343430668116,
      "num_tokens": 638731.0,
      "step": 50
    },
    {
      "entropy": 0.5118487819307483,
      "epoch": 0.17857142857142858,
      "grad_norm": 0.0302734375,
      "learning_rate": 0.00018911816732078575,
      "loss": 0.458189582824707,
      "mean_token_accuracy": 0.8848111309111119,
      "num_tokens": 965339.0,
      "step": 75
    },
    {
      "entropy": 0.40199978921795265,
      "epoch": 0.23809523809523808,
      "grad_norm": 0.02734375,
      "learning_rate": 0.00017876409937363677,
      "loss": 0.34101554870605466,
      "mean_token_accuracy": 0.9092474629729986,
      "num_tokens": 1281078.0,
      "step": 100
    },
    {
      "entropy": 0.3150568036455661,
      "epoch": 0.2976190476190476,
      "grad_norm": 0.0264892578125,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.28272697448730466,
      "mean_token_accuracy": 0.9293849968910217,
      "num_tokens": 1604264.0,
      "step": 125
    },
    {
      "entropy": 0.2919187840796076,
      "epoch": 0.35714285714285715,
      "grad_norm": 0.017333984375,
      "learning_rate": 0.0001497770092672523,
      "loss": 0.2694875907897949,
      "mean_token_accuracy": 0.9351034124195575,
      "num_tokens": 1924368.0,
      "step": 150
    },
    {
      "entropy": 0.2333611233229749,
      "epoch": 0.4166666666666667,
      "grad_norm": 0.0240478515625,
      "learning_rate": 0.00013222007425449234,
      "loss": 0.20119295120239258,
      "mean_token_accuracy": 0.9475092954933644,
      "num_tokens": 2246081.0,
      "step": 175
    },
    {
      "entropy": 0.205037326667225,
      "epoch": 0.47619047619047616,
      "grad_norm": 0.0203857421875,
      "learning_rate": 0.00011346703409159493,
      "loss": 0.17668973922729492,
      "mean_token_accuracy": 0.9551502335071563,
      "num_tokens": 2571829.0,
      "step": 200
    },
    {
      "entropy": 0.18503024196485057,
      "epoch": 0.5357142857142857,
      "grad_norm": 0.03271484375,
      "learning_rate": 9.42140575006557e-05,
      "loss": 0.1600056266784668,
      "mean_token_accuracy": 0.958263601064682,
      "num_tokens": 2895417.0,
      "step": 225
    },
    {
      "entropy": 0.1711997418361716,
      "epoch": 0.5952380952380952,
      "grad_norm": 0.032958984375,
      "learning_rate": 7.517587233344819e-05,
      "loss": 0.14275954246520997,
      "mean_token_accuracy": 0.9637392294406891,
      "num_tokens": 3215552.0,
      "step": 250
    },
    {
      "entropy": 0.11889096346101724,
      "epoch": 0.6547619047619048,
      "grad_norm": 0.0157470703125,
      "learning_rate": 5.705923274416536e-05,
      "loss": 0.09899996757507325,
      "mean_token_accuracy": 0.9744510489702225,
      "num_tokens": 3533171.0,
      "step": 275
    },
    {
      "entropy": 0.1307608083053492,
      "epoch": 0.7142857142857143,
      "grad_norm": 0.019287109375,
      "learning_rate": 4.053668236957134e-05,
      "loss": 0.11216662406921386,
      "mean_token_accuracy": 0.9716260093450546,
      "num_tokens": 3855527.0,
      "step": 300
    },
    {
      "entropy": 0.09693527189898304,
      "epoch": 0.7738095238095238,
      "grad_norm": 0.024169921875,
      "learning_rate": 2.622158750548407e-05,
      "loss": 0.0746759843826294,
      "mean_token_accuracy": 0.9791817248612642,
      "num_tokens": 4175186.0,
      "step": 325
    },
    {
      "entropy": 0.11735842643654905,
      "epoch": 0.8333333333333334,
      "grad_norm": 0.023681640625,
      "learning_rate": 1.464536712246205e-05,
      "loss": 0.09223504066467285,
      "mean_token_accuracy": 0.9757675264775753,
      "num_tokens": 4494938.0,
      "step": 350
    },
    {
      "entropy": 0.13420835086144506,
      "epoch": 0.8928571428571429,
      "grad_norm": 0.0198974609375,
      "learning_rate": 6.237765010351715e-06,
      "loss": 0.11509725570678711,
      "mean_token_accuracy": 0.970939118117094,
      "num_tokens": 4814346.0,
      "step": 375
    },
    {
      "entropy": 0.0992763233173173,
      "epoch": 0.9523809523809523,
      "grad_norm": 0.016357421875,
      "learning_rate": 1.3108964084654007e-06,
      "loss": 0.07517051219940185,
      "mean_token_accuracy": 0.979534283131361,
      "num_tokens": 5135067.0,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 420,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.303146897690921e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}