{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99775617053104,
  "eval_steps": 100,
  "global_step": 501,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05983545250560957,
      "grad_norm": 7.40893212326487,
      "learning_rate": 1.96078431372549e-06,
      "loss": 0.6407,
      "step": 10
    },
    {
      "epoch": 0.11967090501121914,
      "grad_norm": 2.443879636951024,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.3887,
      "step": 20
    },
    {
      "epoch": 0.17950635751682872,
      "grad_norm": 2.182405695242156,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.2616,
      "step": 30
    },
    {
      "epoch": 0.2393418100224383,
      "grad_norm": 2.01489573168189,
      "learning_rate": 7.84313725490196e-06,
      "loss": 0.2571,
      "step": 40
    },
    {
      "epoch": 0.2991772625280479,
      "grad_norm": 1.979013183070111,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.2477,
      "step": 50
    },
    {
      "epoch": 0.35901271503365745,
      "grad_norm": 1.549355728093093,
      "learning_rate": 9.990133642141359e-06,
      "loss": 0.2176,
      "step": 60
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 1.4426481204872057,
      "learning_rate": 9.95607770125771e-06,
      "loss": 0.2273,
      "step": 70
    },
    {
      "epoch": 0.4786836200448766,
      "grad_norm": 1.7789832633152836,
      "learning_rate": 9.89787624799672e-06,
      "loss": 0.2125,
      "step": 80
    },
    {
      "epoch": 0.5385190725504861,
      "grad_norm": 1.529318217095282,
      "learning_rate": 9.815812833988292e-06,
      "loss": 0.2229,
      "step": 90
    },
    {
      "epoch": 0.5983545250560958,
      "grad_norm": 1.6259265112226373,
      "learning_rate": 9.710287263936485e-06,
      "loss": 0.2062,
      "step": 100
    },
    {
      "epoch": 0.5983545250560958,
      "eval_loss": 0.2123425155878067,
      "eval_runtime": 33.4729,
      "eval_samples_per_second": 17.776,
      "eval_steps_per_second": 8.903,
      "step": 100
    },
    {
      "epoch": 0.6581899775617053,
      "grad_norm": 1.6245243576341002,
      "learning_rate": 9.581813647811199e-06,
      "loss": 0.2105,
      "step": 110
    },
    {
      "epoch": 0.7180254300673149,
      "grad_norm": 1.731561075586601,
      "learning_rate": 9.431017896156074e-06,
      "loss": 0.2048,
      "step": 120
    },
    {
      "epoch": 0.7778608825729244,
      "grad_norm": 1.7874480467541498,
      "learning_rate": 9.25863467071524e-06,
      "loss": 0.2113,
      "step": 130
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 1.3708463663991368,
      "learning_rate": 9.065503805235139e-06,
      "loss": 0.1988,
      "step": 140
    },
    {
      "epoch": 0.8975317875841436,
      "grad_norm": 1.3567660521800535,
      "learning_rate": 8.852566213878947e-06,
      "loss": 0.2038,
      "step": 150
    },
    {
      "epoch": 0.9573672400897532,
      "grad_norm": 1.8281708498422444,
      "learning_rate": 8.620859307187339e-06,
      "loss": 0.2196,
      "step": 160
    },
    {
      "epoch": 1.0172026925953628,
      "grad_norm": 1.2318054900550177,
      "learning_rate": 8.371511937918616e-06,
      "loss": 0.1762,
      "step": 170
    },
    {
      "epoch": 1.0770381451009723,
      "grad_norm": 1.568321912319435,
      "learning_rate": 8.105738901391553e-06,
      "loss": 0.1288,
      "step": 180
    },
    {
      "epoch": 1.136873597606582,
      "grad_norm": 1.3819346363939895,
      "learning_rate": 7.82483501712469e-06,
      "loss": 0.1214,
      "step": 190
    },
    {
      "epoch": 1.1967090501121915,
      "grad_norm": 1.2680685647450163,
      "learning_rate": 7.530168820605819e-06,
      "loss": 0.1256,
      "step": 200
    },
    {
      "epoch": 1.1967090501121915,
      "eval_loss": 0.20358169078826904,
      "eval_runtime": 32.7594,
      "eval_samples_per_second": 18.163,
      "eval_steps_per_second": 9.097,
      "step": 200
    },
    {
      "epoch": 1.256544502617801,
      "grad_norm": 1.2942802177914767,
      "learning_rate": 7.223175895924638e-06,
      "loss": 0.1241,
      "step": 210
    },
    {
      "epoch": 1.3163799551234106,
      "grad_norm": 1.4364370392498633,
      "learning_rate": 6.905351881751372e-06,
      "loss": 0.1254,
      "step": 220
    },
    {
      "epoch": 1.37621540762902,
      "grad_norm": 1.330811194933078,
      "learning_rate": 6.578245184735513e-06,
      "loss": 0.1229,
      "step": 230
    },
    {
      "epoch": 1.4360508601346298,
      "grad_norm": 1.304831888309303,
      "learning_rate": 6.243449435824276e-06,
      "loss": 0.1147,
      "step": 240
    },
    {
      "epoch": 1.4958863126402393,
      "grad_norm": 1.2398683599838292,
      "learning_rate": 5.902595726252801e-06,
      "loss": 0.1345,
      "step": 250
    },
    {
      "epoch": 1.555721765145849,
      "grad_norm": 1.3240317320353998,
      "learning_rate": 5.557344661031628e-06,
      "loss": 0.1236,
      "step": 260
    },
    {
      "epoch": 1.6155572176514585,
      "grad_norm": 1.518581095835922,
      "learning_rate": 5.209378268645998e-06,
      "loss": 0.1218,
      "step": 270
    },
    {
      "epoch": 1.675392670157068,
      "grad_norm": 1.5653129689570715,
      "learning_rate": 4.860391806382157e-06,
      "loss": 0.1246,
      "step": 280
    },
    {
      "epoch": 1.7352281226626776,
      "grad_norm": 1.4836280079781416,
      "learning_rate": 4.512085501204254e-06,
      "loss": 0.1156,
      "step": 290
    },
    {
      "epoch": 1.795063575168287,
      "grad_norm": 1.4998045733125407,
      "learning_rate": 4.166156266419489e-06,
      "loss": 0.1296,
      "step": 300
    },
    {
      "epoch": 1.795063575168287,
      "eval_loss": 0.19370371103286743,
      "eval_runtime": 33.117,
      "eval_samples_per_second": 17.967,
      "eval_steps_per_second": 8.998,
      "step": 300
    },
    {
      "epoch": 1.8548990276738968,
      "grad_norm": 1.426847361331521,
      "learning_rate": 3.82428943448705e-06,
      "loss": 0.1294,
      "step": 310
    },
    {
      "epoch": 1.9147344801795063,
      "grad_norm": 1.1812939999353123,
      "learning_rate": 3.488150546247778e-06,
      "loss": 0.1219,
      "step": 320
    },
    {
      "epoch": 1.974569932685116,
      "grad_norm": 1.071812010046448,
      "learning_rate": 3.1593772365766107e-06,
      "loss": 0.1106,
      "step": 330
    },
    {
      "epoch": 2.0344053851907256,
      "grad_norm": 0.9913151474800547,
      "learning_rate": 2.839571255990088e-06,
      "loss": 0.0851,
      "step": 340
    },
    {
      "epoch": 2.094240837696335,
      "grad_norm": 1.0937548000001698,
      "learning_rate": 2.5302906670788463e-06,
      "loss": 0.0621,
      "step": 350
    },
    {
      "epoch": 2.1540762902019446,
      "grad_norm": 1.1416547973943143,
      "learning_rate": 2.23304225378328e-06,
      "loss": 0.0662,
      "step": 360
    },
    {
      "epoch": 2.213911742707554,
      "grad_norm": 1.2971227147360092,
      "learning_rate": 1.9492741804936623e-06,
      "loss": 0.0623,
      "step": 370
    },
    {
      "epoch": 2.273747195213164,
      "grad_norm": 1.0599796926376819,
      "learning_rate": 1.680368936738792e-06,
      "loss": 0.0604,
      "step": 380
    },
    {
      "epoch": 2.3335826477187736,
      "grad_norm": 1.0516418140346255,
      "learning_rate": 1.4276366018359845e-06,
      "loss": 0.0605,
      "step": 390
    },
    {
      "epoch": 2.393418100224383,
      "grad_norm": 1.1322674065288456,
      "learning_rate": 1.1923084623163172e-06,
      "loss": 0.0592,
      "step": 400
    },
    {
      "epoch": 2.393418100224383,
      "eval_loss": 0.21845205128192902,
      "eval_runtime": 33.1015,
      "eval_samples_per_second": 17.975,
      "eval_steps_per_second": 9.003,
      "step": 400
    },
    {
      "epoch": 2.4532535527299926,
      "grad_norm": 1.070168334944103,
      "learning_rate": 9.7553101322043e-07,
      "loss": 0.0595,
      "step": 410
    },
    {
      "epoch": 2.513089005235602,
      "grad_norm": 1.1779521251420957,
      "learning_rate": 7.783603724899258e-07,
      "loss": 0.0593,
      "step": 420
    },
    {
      "epoch": 2.5729244577412116,
      "grad_norm": 1.0392248842745917,
      "learning_rate": 6.017571356669183e-07,
      "loss": 0.0588,
      "step": 430
    },
    {
      "epoch": 2.632759910246821,
      "grad_norm": 1.1454410326378197,
      "learning_rate": 4.4658169596911493e-07,
      "loss": 0.0599,
      "step": 440
    },
    {
      "epoch": 2.6925953627524306,
      "grad_norm": 1.2414977662809759,
      "learning_rate": 3.135900525405428e-07,
      "loss": 0.0596,
      "step": 450
    },
    {
      "epoch": 2.75243081525804,
      "grad_norm": 0.9458175216720401,
      "learning_rate": 2.0343012729971244e-07,
      "loss": 0.0561,
      "step": 460
    },
    {
      "epoch": 2.81226626776365,
      "grad_norm": 1.2677156882489358,
      "learning_rate": 1.166386083291604e-07,
      "loss": 0.0566,
      "step": 470
    },
    {
      "epoch": 2.8721017202692596,
      "grad_norm": 1.0894838908576727,
      "learning_rate": 5.363833518505834e-08,
      "loss": 0.0608,
      "step": 480
    },
    {
      "epoch": 2.931937172774869,
      "grad_norm": 0.8300865767642356,
      "learning_rate": 1.4736238865398766e-08,
      "loss": 0.0548,
      "step": 490
    },
    {
      "epoch": 2.9917726252804786,
      "grad_norm": 1.1224586519889344,
      "learning_rate": 1.2184647302626585e-10,
      "loss": 0.0646,
      "step": 500
    },
    {
      "epoch": 2.9917726252804786,
      "eval_loss": 0.21988336741924286,
      "eval_runtime": 33.0412,
      "eval_samples_per_second": 18.008,
      "eval_steps_per_second": 9.019,
      "step": 500
    },
    {
      "epoch": 2.99775617053104,
      "step": 501,
      "total_flos": 9861900926976.0,
      "train_loss": 0.14637824013353345,
      "train_runtime": 2877.8871,
      "train_samples_per_second": 5.575,
      "train_steps_per_second": 0.174
    }
  ],
  "logging_steps": 10,
  "max_steps": 501,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 9861900926976.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}