{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 7840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.5211859610345628,
      "las": 67.4814491488433,
      "step": 392,
      "uas": 78.04452204277608
    },
    {
      "epoch": 1.2755102040816326,
      "grad_norm": 11.628578186035156,
      "learning_rate": 0.00018724489795918367,
      "loss": 271.7516,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4270889030562506,
      "las": 69.53295504146661,
      "step": 784,
      "uas": 79.79048450458315
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 6.459884166717529,
      "learning_rate": 0.00017448979591836735,
      "loss": 271.7582,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.7154893933071031,
      "las": 72.28284591881274,
      "step": 1176,
      "uas": 81.53644696639022
    },
    {
      "epoch": 3.826530612244898,
      "grad_norm": 3.9133880138397217,
      "learning_rate": 0.00016173469387755103,
      "loss": 268.2068,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.7123144169648488,
      "las": 73.63596682671323,
      "step": 1568,
      "uas": 81.97293758184199
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.9232268912924662,
      "las": 72.98123090353558,
      "step": 1960,
      "uas": 82.1475338280227
    },
    {
      "epoch": 5.1020408163265305,
      "grad_norm": 2.6702146530151367,
      "learning_rate": 0.00014897959183673472,
      "loss": 267.1583,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.1728447212113275,
      "las": 73.06852902662592,
      "step": 2352,
      "uas": 81.36185072020952
    },
    {
      "epoch": 6.377551020408164,
      "grad_norm": 2.6859347820281982,
      "learning_rate": 0.00013622448979591837,
      "loss": 266.0369,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.3242934031618967,
      "las": 74.11610650371017,
      "step": 2744,
      "uas": 83.02051505892624
    },
    {
      "epoch": 7.653061224489796,
      "grad_norm": 1.6134849786758423,
      "learning_rate": 0.00012346938775510203,
      "loss": 265.9112,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.5794437726338706,
      "las": 73.24312527280664,
      "step": 3136,
      "uas": 82.5403753819293
    },
    {
      "epoch": 8.928571428571429,
      "grad_norm": 1.1696821451187134,
      "learning_rate": 0.00011071428571428572,
      "loss": 267.02,
      "step": 3500
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.7259935074382358,
      "las": 73.24312527280664,
      "step": 3528,
      "uas": 82.1475338280227
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.6596836613284216,
      "las": 73.5050196420777,
      "step": 3920,
      "uas": 82.67132256656483
    },
    {
      "epoch": 10.204081632653061,
      "grad_norm": 2.175758123397827,
      "learning_rate": 9.79591836734694e-05,
      "loss": 266.0427,
      "step": 4000
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.5932833121882544,
      "las": 74.07245744216499,
      "step": 4312,
      "uas": 83.50065473592318
    },
    {
      "epoch": 11.479591836734693,
      "grad_norm": 1.4794198274612427,
      "learning_rate": 8.520408163265306e-05,
      "loss": 265.7745,
      "step": 4500
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.7420518745978675,
      "las": 74.37800087298123,
      "step": 4704,
      "uas": 83.2824094281973
    },
    {
      "epoch": 12.755102040816327,
      "grad_norm": 1.8547543287277222,
      "learning_rate": 7.244897959183675e-05,
      "loss": 265.777,
      "step": 5000
    },
    {
      "epoch": 13.0,
      "eval_loss": 2.854385713736216,
      "las": 74.59624618070711,
      "step": 5096,
      "uas": 83.15146224356177
    },
    {
      "epoch": 14.0,
      "eval_loss": 3.256368252966139,
      "las": 74.77084242688782,
      "step": 5488,
      "uas": 82.97686599738105
    },
    {
      "epoch": 14.03061224489796,
      "grad_norm": 1.382800817489624,
      "learning_rate": 5.9693877551020416e-05,
      "loss": 266.4641,
      "step": 5500
    },
    {
      "epoch": 15.0,
      "eval_loss": 3.261543388168017,
      "las": 74.15975556525535,
      "step": 5880,
      "uas": 82.8895678742907
    },
    {
      "epoch": 15.306122448979592,
      "grad_norm": 0.6841826438903809,
      "learning_rate": 4.6938775510204086e-05,
      "loss": 267.6857,
      "step": 6000
    },
    {
      "epoch": 16.0,
      "eval_loss": 3.268537084261576,
      "las": 73.63596682671323,
      "step": 6272,
      "uas": 82.67132256656483
    },
    {
      "epoch": 16.581632653061224,
      "grad_norm": 0.8982020020484924,
      "learning_rate": 3.4183673469387755e-05,
      "loss": 265.4994,
      "step": 6500
    },
    {
      "epoch": 17.0,
      "eval_loss": 3.46340329779519,
      "las": 74.68354430379746,
      "step": 6664,
      "uas": 83.02051505892624
    },
    {
      "epoch": 17.857142857142858,
      "grad_norm": 0.9878342151641846,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 265.6774,
      "step": 7000
    },
    {
      "epoch": 18.0,
      "eval_loss": 3.7613406744268207,
      "las": 74.42164993452641,
      "step": 7056,
      "uas": 83.2824094281973
    },
    {
      "epoch": 19.0,
      "eval_loss": 3.8515510294172497,
      "las": 74.6398952422523,
      "step": 7448,
      "uas": 83.32605848974246
    },
    {
      "epoch": 19.132653061224488,
      "grad_norm": 1.085435390472412,
      "learning_rate": 8.673469387755103e-06,
      "loss": 266.1408,
      "step": 7500
    },
    {
      "epoch": 20.0,
      "eval_loss": 3.952014442947176,
      "las": 74.72719336534264,
      "step": 7840,
      "uas": 83.54430379746836
    },
    {
      "epoch": 20.0,
      "step": 7840,
      "total_flos": 8.698923198185472e+16,
      "train_loss": 267.07814692283165,
      "train_runtime": 7682.2301,
      "train_samples_per_second": 65.314,
      "train_steps_per_second": 1.021
    }
  ],
  "logging_steps": 500,
  "max_steps": 7840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 8.698923198185472e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}