{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 416,
  "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
    },
    {
      "epoch": 1.0820265379975875,
      "grad_norm": 0.08378228545188904,
      "learning_rate": 0.0004907826694951906,
      "loss": 0.0898,
      "mean_token_accuracy": 0.9755665328084808,
      "num_tokens": 2562109.0,
      "step": 225
    },
    {
      "epoch": 1.2026537997587454,
      "grad_norm": 0.10287031531333923,
      "learning_rate": 0.0004848809834625538,
      "loss": 0.0713,
      "mean_token_accuracy": 0.9797296553850174,
      "num_tokens": 2845938.0,
      "step": 250
    },
    {
      "epoch": 1.3232810615199035,
      "grad_norm": 0.06548517942428589,
      "learning_rate": 0.00047826979186880607,
      "loss": 0.0673,
      "mean_token_accuracy": 0.9813395547866821,
      "num_tokens": 3129801.0,
      "step": 275
    },
    {
      "epoch": 1.4439083232810614,
      "grad_norm": 0.10134833306074142,
      "learning_rate": 0.00047096954399936976,
      "loss": 0.0597,
      "mean_token_accuracy": 0.9829099756479264,
      "num_tokens": 3412051.0,
      "step": 300
    },
    {
      "epoch": 1.5645355850422196,
      "grad_norm": 0.09496472030878067,
      "learning_rate": 0.00046300282048138635,
      "loss": 0.0608,
      "mean_token_accuracy": 0.9829603230953217,
      "num_tokens": 3697161.0,
      "step": 325
    },
    {
      "epoch": 1.6851628468033777,
      "grad_norm": 0.07210717350244522,
      "learning_rate": 0.0004543942634388648,
      "loss": 0.0574,
      "mean_token_accuracy": 0.9837546187639237,
      "num_tokens": 3980794.0,
      "step": 350
    },
    {
      "epoch": 1.8057901085645356,
      "grad_norm": 0.07639794051647186,
      "learning_rate": 0.00044517050027135087,
      "loss": 0.055,
      "mean_token_accuracy": 0.9842740440368652,
      "num_tokens": 4265160.0,
      "step": 375
    },
    {
      "epoch": 1.9264173703256935,
      "grad_norm": 0.06361191719770432,
      "learning_rate": 0.00043536006129187623,
      "loss": 0.0483,
      "mean_token_accuracy": 0.9864062821865082,
      "num_tokens": 4549538.0,
      "step": 400
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.054612528532743454,
      "eval_mean_token_accuracy": 0.9850417369155473,
      "eval_num_tokens": 4710428.0,
      "eval_runtime": 14.4072,
      "eval_samples_per_second": 25.612,
      "eval_steps_per_second": 6.455,
      "step": 416
    }
  ],
  "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": 2.0488293068465766e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}