{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 275,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 3.3212404251098633,
      "learning_rate": 0.00019345454545454546,
      "loss": 1.5788,
      "mean_token_accuracy": 0.6589842185378074,
      "num_tokens": 11127.0,
      "step": 10
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 2.2878754138946533,
      "learning_rate": 0.0001861818181818182,
      "loss": 1.2084,
      "mean_token_accuracy": 0.7237757340073585,
      "num_tokens": 22177.0,
      "step": 20
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 3.08931303024292,
      "learning_rate": 0.00017890909090909093,
      "loss": 0.9623,
      "mean_token_accuracy": 0.7773568660020829,
      "num_tokens": 33167.0,
      "step": 30
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 3.2146613597869873,
      "learning_rate": 0.00017163636363636364,
      "loss": 0.6221,
      "mean_token_accuracy": 0.8660929881036281,
      "num_tokens": 44818.0,
      "step": 40
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 2.5239977836608887,
      "learning_rate": 0.00016436363636363637,
      "loss": 0.7484,
      "mean_token_accuracy": 0.8272845461964607,
      "num_tokens": 55735.0,
      "step": 50
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 2.0953986644744873,
      "learning_rate": 0.00015709090909090908,
      "loss": 0.4557,
      "mean_token_accuracy": 0.9092939600348473,
      "num_tokens": 66765.0,
      "step": 60
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 2.588249444961548,
      "learning_rate": 0.00014981818181818184,
      "loss": 0.6584,
      "mean_token_accuracy": 0.8400282755494117,
      "num_tokens": 77331.0,
      "step": 70
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 2.2984700202941895,
      "learning_rate": 0.00014254545454545455,
      "loss": 0.6106,
      "mean_token_accuracy": 0.8571661487221718,
      "num_tokens": 88227.0,
      "step": 80
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 2.475771427154541,
      "learning_rate": 0.00013527272727272729,
      "loss": 0.5752,
      "mean_token_accuracy": 0.8697961375117302,
      "num_tokens": 98777.0,
      "step": 90
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.535799980163574,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.4911,
      "mean_token_accuracy": 0.89216850399971,
      "num_tokens": 109773.0,
      "step": 100
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.4313271045684814,
      "learning_rate": 0.00012072727272727273,
      "loss": 0.6944,
      "mean_token_accuracy": 0.8319280952215194,
      "num_tokens": 120110.0,
      "step": 110
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 2.3609564304351807,
      "learning_rate": 0.00011345454545454545,
      "loss": 0.568,
      "mean_token_accuracy": 0.8562197998166085,
      "num_tokens": 130750.0,
      "step": 120
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 2.44640851020813,
      "learning_rate": 0.00010618181818181819,
      "loss": 0.452,
      "mean_token_accuracy": 0.8784870430827141,
      "num_tokens": 141506.0,
      "step": 130
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 2.0682320594787598,
      "learning_rate": 9.890909090909092e-05,
      "loss": 0.6779,
      "mean_token_accuracy": 0.8436270222067833,
      "num_tokens": 152717.0,
      "step": 140
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.1546458005905151,
      "learning_rate": 9.163636363636364e-05,
      "loss": 0.4282,
      "mean_token_accuracy": 0.8993956357240677,
      "num_tokens": 164030.0,
      "step": 150
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 1.2640266418457031,
      "learning_rate": 8.436363636363637e-05,
      "loss": 0.538,
      "mean_token_accuracy": 0.8718804702162742,
      "num_tokens": 175458.0,
      "step": 160
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 1.5814223289489746,
      "learning_rate": 7.709090909090909e-05,
      "loss": 0.4352,
      "mean_token_accuracy": 0.8879004895687104,
      "num_tokens": 186778.0,
      "step": 170
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 1.8492006063461304,
      "learning_rate": 6.981818181818182e-05,
      "loss": 0.5202,
      "mean_token_accuracy": 0.8709954559803009,
      "num_tokens": 197630.0,
      "step": 180
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 1.8375712633132935,
      "learning_rate": 6.254545454545456e-05,
      "loss": 0.4214,
      "mean_token_accuracy": 0.8964368030428886,
      "num_tokens": 208414.0,
      "step": 190
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.5674086809158325,
      "learning_rate": 5.527272727272727e-05,
      "loss": 0.5739,
      "mean_token_accuracy": 0.8617855116724968,
      "num_tokens": 219498.0,
      "step": 200
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 1.284372329711914,
      "learning_rate": 4.8e-05,
      "loss": 0.4049,
      "mean_token_accuracy": 0.8968110710382462,
      "num_tokens": 229984.0,
      "step": 210
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6603507995605469,
      "learning_rate": 4.072727272727273e-05,
      "loss": 0.3727,
      "mean_token_accuracy": 0.9041761666536331,
      "num_tokens": 241090.0,
      "step": 220
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 1.6871552467346191,
      "learning_rate": 3.345454545454546e-05,
      "loss": 0.421,
      "mean_token_accuracy": 0.8905564934015274,
      "num_tokens": 252564.0,
      "step": 230
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 1.2738430500030518,
      "learning_rate": 2.6181818181818187e-05,
      "loss": 0.4663,
      "mean_token_accuracy": 0.884245416522026,
      "num_tokens": 263652.0,
      "step": 240
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.5028655529022217,
      "learning_rate": 1.890909090909091e-05,
      "loss": 0.2951,
      "mean_token_accuracy": 0.9238881275057793,
      "num_tokens": 274892.0,
      "step": 250
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 1.8719642162322998,
      "learning_rate": 1.1636363636363637e-05,
      "loss": 0.624,
      "mean_token_accuracy": 0.8429773986339569,
      "num_tokens": 285890.0,
      "step": 260
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.8801164031028748,
      "learning_rate": 4.363636363636364e-06,
      "loss": 0.4423,
      "mean_token_accuracy": 0.888069073855877,
      "num_tokens": 297643.0,
      "step": 270
    }
  ],
  "logging_steps": 10,
  "max_steps": 275,
  "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": 1.4648058643857408e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}