{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 208,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12062726176115803,
      "grad_norm": 0.21568018198013306,
      "learning_rate": 0.00027872727272727267,
      "loss": 1.5868,
      "mean_token_accuracy": 0.6624862551689148,
      "num_tokens": 281912.0,
      "step": 25
    },
    {
      "epoch": 0.24125452352231605,
      "grad_norm": 0.18077188730239868,
      "learning_rate": 0.0005109841901849095,
      "loss": 0.6885,
      "mean_token_accuracy": 0.814376802444458,
      "num_tokens": 567502.0,
      "step": 50
    },
    {
      "epoch": 0.3618817852834741,
      "grad_norm": 0.21275386214256287,
      "learning_rate": 0.0005104310520681908,
      "loss": 0.4572,
      "mean_token_accuracy": 0.8698280012607574,
      "num_tokens": 851707.0,
      "step": 75
    },
    {
      "epoch": 0.4825090470446321,
      "grad_norm": 0.21209321916103363,
      "learning_rate": 0.0005090893786665853,
      "loss": 0.2886,
      "mean_token_accuracy": 0.9166975712776184,
      "num_tokens": 1136836.0,
      "step": 100
    },
    {
      "epoch": 0.6031363088057901,
      "grad_norm": 0.21541441977024078,
      "learning_rate": 0.0005069633199524458,
      "loss": 0.2088,
      "mean_token_accuracy": 0.9403706526756287,
      "num_tokens": 1421665.0,
      "step": 125
    },
    {
      "epoch": 0.7237635705669482,
      "grad_norm": 0.2024364322423935,
      "learning_rate": 0.000504059452105097,
      "loss": 0.1676,
      "mean_token_accuracy": 0.9520682036876679,
      "num_tokens": 1707215.0,
      "step": 150
    },
    {
      "epoch": 0.8443908323281062,
      "grad_norm": 0.15191498398780823,
      "learning_rate": 0.0005003867571698477,
      "loss": 0.1272,
      "mean_token_accuracy": 0.9645591104030609,
      "num_tokens": 1990889.0,
      "step": 175
    },
    {
      "epoch": 0.9650180940892642,
      "grad_norm": 0.16032542288303375,
      "learning_rate": 0.0004959565952753427,
      "loss": 0.1091,
      "mean_token_accuracy": 0.9695405942201615,
      "num_tokens": 2274523.0,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.09917861223220825,
      "eval_mean_token_accuracy": 0.9725541690344451,
      "eval_num_tokens": 2355152.0,
      "eval_runtime": 14.4426,
      "eval_samples_per_second": 25.549,
      "eval_steps_per_second": 6.439,
      "step": 208
    }
  ],
  "logging_steps": 25,
  "max_steps": 1456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0243795018003251e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}