{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 185,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005405405405405406,
      "grad_norm": 1.7116371393203735,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 1.4457,
      "step": 1
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.6178371906280518,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 1.4317,
      "step": 5
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.0490155220031738,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.4017,
      "step": 10
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.015197992324829,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.3362,
      "step": 15
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.8447503447532654,
      "learning_rate": 0.00019998209226697376,
      "loss": 1.2393,
      "step": 20
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 0.7622084617614746,
      "learning_rate": 0.0001993559947963185,
      "loss": 1.1269,
      "step": 25
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 0.4874676764011383,
      "learning_rate": 0.00019784091409455728,
      "loss": 1.0469,
      "step": 30
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 0.4265550374984741,
      "learning_rate": 0.0001954504062771555,
      "loss": 0.9981,
      "step": 35
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.2609158754348755,
      "learning_rate": 0.00019220586030376134,
      "loss": 0.9822,
      "step": 40
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.21494942903518677,
      "learning_rate": 0.00018813630660146488,
      "loss": 0.9561,
      "step": 45
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.22001613676548004,
      "learning_rate": 0.00018327815731637612,
      "loss": 0.9534,
      "step": 50
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 0.17728982865810394,
      "learning_rate": 0.00017767488051760857,
      "loss": 0.9442,
      "step": 55
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.24004819989204407,
      "learning_rate": 0.0001713766112687139,
      "loss": 0.9395,
      "step": 60
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 0.18783989548683167,
      "learning_rate": 0.0001644397030464877,
      "loss": 0.9387,
      "step": 65
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.2297225445508957,
      "learning_rate": 0.00015692622352080662,
      "loss": 0.9212,
      "step": 70
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.19587929546833038,
      "learning_rate": 0.00014890339920698334,
      "loss": 0.9379,
      "step": 75
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.17770881950855255,
      "learning_rate": 0.0001404430139595877,
      "loss": 0.9233,
      "step": 80
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 0.1968083679676056,
      "learning_rate": 0.0001316207666896824,
      "loss": 0.9277,
      "step": 85
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.2078552544116974,
      "learning_rate": 0.00012251559405226941,
      "loss": 0.9141,
      "step": 90
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 0.217142254114151,
      "learning_rate": 0.00011320896416417026,
      "loss": 0.9178,
      "step": 95
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.21711134910583496,
      "learning_rate": 0.00010378414767176705,
      "loss": 0.9074,
      "step": 100
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 0.2110918015241623,
      "learning_rate": 9.432547269069261e-05,
      "loss": 0.9109,
      "step": 105
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.19920781254768372,
      "learning_rate": 8.491757028386263e-05,
      "loss": 0.9087,
      "step": 110
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 0.19524553418159485,
      "learning_rate": 7.564461722890081e-05,
      "loss": 0.916,
      "step": 115
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.1919243484735489,
      "learning_rate": 6.658958285026102e-05,
      "loss": 0.9086,
      "step": 120
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 0.1887766569852829,
      "learning_rate": 5.7833486654981606e-05,
      "loss": 0.9115,
      "step": 125
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 0.19857022166252136,
      "learning_rate": 4.945467341434195e-05,
      "loss": 0.9091,
      "step": 130
    },
    {
      "epoch": 0.7297297297297297,
      "grad_norm": 0.18941636383533478,
      "learning_rate": 4.152811217759529e-05,
      "loss": 0.9086,
      "step": 135
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.1900327503681183,
      "learning_rate": 3.4124725489820645e-05,
      "loss": 0.8949,
      "step": 140
    },
    {
      "epoch": 0.7837837837837838,
      "grad_norm": 0.2118791937828064,
      "learning_rate": 2.7310754815685624e-05,
      "loss": 0.9032,
      "step": 145
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.1908016800880432,
      "learning_rate": 2.1147167846963422e-05,
      "loss": 0.9004,
      "step": 150
    },
    {
      "epoch": 0.8378378378378378,
      "grad_norm": 0.18138864636421204,
      "learning_rate": 1.5689112996891576e-05,
      "loss": 0.9078,
      "step": 155
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.17937543988227844,
      "learning_rate": 1.0985425962260343e-05,
      "loss": 0.9048,
      "step": 160
    },
    {
      "epoch": 0.8918918918918919,
      "grad_norm": 0.17949175834655762,
      "learning_rate": 7.078192768243486e-06,
      "loss": 0.8973,
      "step": 165
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 0.18442046642303467,
      "learning_rate": 4.002373205607723e-06,
      "loss": 0.9025,
      "step": 170
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 0.1833404004573822,
      "learning_rate": 1.7854880295797405e-06,
      "loss": 0.888,
      "step": 175
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.18067924678325653,
      "learning_rate": 4.4737271914411236e-07,
      "loss": 0.8983,
      "step": 180
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20572535693645477,
      "learning_rate": 0.0,
      "loss": 0.8994,
      "step": 185
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.3997735977172852,
      "eval_runtime": 0.6709,
      "eval_samples_per_second": 16.396,
      "eval_steps_per_second": 1.491,
      "step": 185
    },
    {
      "epoch": 1.0,
      "step": 185,
      "total_flos": 9.060485625492275e+17,
      "train_loss": 0.9761296278721577,
      "train_runtime": 715.1184,
      "train_samples_per_second": 57.936,
      "train_steps_per_second": 0.259
    }
  ],
  "logging_steps": 5,
  "max_steps": 185,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.060485625492275e+17,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}