{
  "best_metric": 1.9433879852294922,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.7256894049346879,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001451378809869376,
      "eval_loss": 2.528571605682373,
      "eval_runtime": 24.4881,
      "eval_samples_per_second": 11.843,
      "eval_steps_per_second": 2.981,
      "step": 1
    },
    {
      "epoch": 0.01451378809869376,
      "grad_norm": 1.4596052169799805,
      "learning_rate": 4.1400000000000003e-05,
      "loss": 2.3431,
      "step": 10
    },
    {
      "epoch": 0.02902757619738752,
      "grad_norm": 1.2653985023498535,
      "learning_rate": 8.280000000000001e-05,
      "loss": 2.1844,
      "step": 20
    },
    {
      "epoch": 0.04354136429608128,
      "grad_norm": 1.5904498100280762,
      "learning_rate": 0.00012419999999999998,
      "loss": 2.2177,
      "step": 30
    },
    {
      "epoch": 0.05805515239477504,
      "grad_norm": 1.749571442604065,
      "learning_rate": 0.00016560000000000001,
      "loss": 2.2032,
      "step": 40
    },
    {
      "epoch": 0.07256894049346879,
      "grad_norm": 5.132608890533447,
      "learning_rate": 0.000207,
      "loss": 2.2296,
      "step": 50
    },
    {
      "epoch": 0.07256894049346879,
      "eval_loss": 2.383007764816284,
      "eval_runtime": 24.5963,
      "eval_samples_per_second": 11.79,
      "eval_steps_per_second": 2.968,
      "step": 50
    },
    {
      "epoch": 0.08708272859216255,
      "grad_norm": 1.2386906147003174,
      "learning_rate": 0.00020674787920189178,
      "loss": 2.2268,
      "step": 60
    },
    {
      "epoch": 0.10159651669085631,
      "grad_norm": 1.256988525390625,
      "learning_rate": 0.00020599274511475253,
      "loss": 2.1518,
      "step": 70
    },
    {
      "epoch": 0.11611030478955008,
      "grad_norm": 1.7277191877365112,
      "learning_rate": 0.00020473827667594888,
      "loss": 2.1788,
      "step": 80
    },
    {
      "epoch": 0.13062409288824384,
      "grad_norm": 1.7233295440673828,
      "learning_rate": 0.00020299058552961598,
      "loss": 2.1713,
      "step": 90
    },
    {
      "epoch": 0.14513788098693758,
      "grad_norm": 3.663735866546631,
      "learning_rate": 0.00020075818625134152,
      "loss": 2.1251,
      "step": 100
    },
    {
      "epoch": 0.14513788098693758,
      "eval_loss": 2.3279521465301514,
      "eval_runtime": 24.3674,
      "eval_samples_per_second": 11.901,
      "eval_steps_per_second": 2.996,
      "step": 100
    },
    {
      "epoch": 0.15965166908563136,
      "grad_norm": 1.2206093072891235,
      "learning_rate": 0.00019805195486600916,
      "loss": 2.1955,
      "step": 110
    },
    {
      "epoch": 0.1741654571843251,
      "grad_norm": 1.1765705347061157,
      "learning_rate": 0.00019488507586089894,
      "loss": 2.1238,
      "step": 120
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.411720871925354,
      "learning_rate": 0.00019127297795219008,
      "loss": 2.1084,
      "step": 130
    },
    {
      "epoch": 0.20319303338171263,
      "grad_norm": 1.5477889776229858,
      "learning_rate": 0.00018723325891780706,
      "loss": 2.1483,
      "step": 140
    },
    {
      "epoch": 0.21770682148040638,
      "grad_norm": 3.5689947605133057,
      "learning_rate": 0.0001827855998628142,
      "loss": 2.0485,
      "step": 150
    },
    {
      "epoch": 0.21770682148040638,
      "eval_loss": 2.181504249572754,
      "eval_runtime": 24.6073,
      "eval_samples_per_second": 11.785,
      "eval_steps_per_second": 2.967,
      "step": 150
    },
    {
      "epoch": 0.23222060957910015,
      "grad_norm": 1.0636928081512451,
      "learning_rate": 0.0001779516693350504,
      "loss": 2.1444,
      "step": 160
    },
    {
      "epoch": 0.2467343976777939,
      "grad_norm": 1.1345711946487427,
      "learning_rate": 0.00017275501775814182,
      "loss": 2.0798,
      "step": 170
    },
    {
      "epoch": 0.2612481857764877,
      "grad_norm": 1.450459361076355,
      "learning_rate": 0.00016722096269620562,
      "loss": 2.1037,
      "step": 180
    },
    {
      "epoch": 0.2757619738751814,
      "grad_norm": 1.63530695438385,
      "learning_rate": 0.00016137646550922228,
      "loss": 2.1009,
      "step": 190
    },
    {
      "epoch": 0.29027576197387517,
      "grad_norm": 4.483078479766846,
      "learning_rate": 0.00015525,
      "loss": 2.0577,
      "step": 200
    },
    {
      "epoch": 0.29027576197387517,
      "eval_loss": 2.118581533432007,
      "eval_runtime": 24.8624,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 2.936,
      "step": 200
    },
    {
      "epoch": 0.3047895500725689,
      "grad_norm": 1.1066410541534424,
      "learning_rate": 0.0001488714136926695,
      "loss": 2.1385,
      "step": 210
    },
    {
      "epoch": 0.3193033381712627,
      "grad_norm": 1.1471424102783203,
      "learning_rate": 0.0001422717824185469,
      "loss": 2.0349,
      "step": 220
    },
    {
      "epoch": 0.33381712626995647,
      "grad_norm": 1.2833964824676514,
      "learning_rate": 0.00013548325891780705,
      "loss": 2.0561,
      "step": 230
    },
    {
      "epoch": 0.3483309143686502,
      "grad_norm": 1.6310219764709473,
      "learning_rate": 0.0001285389161945656,
      "loss": 2.0573,
      "step": 240
    },
    {
      "epoch": 0.36284470246734396,
      "grad_norm": 2.8112406730651855,
      "learning_rate": 0.0001214725863885273,
      "loss": 2.0216,
      "step": 250
    },
    {
      "epoch": 0.36284470246734396,
      "eval_loss": 2.0795581340789795,
      "eval_runtime": 24.4537,
      "eval_samples_per_second": 11.859,
      "eval_steps_per_second": 2.985,
      "step": 250
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.0176899433135986,
      "learning_rate": 0.00011431869594820213,
      "loss": 2.0896,
      "step": 260
    },
    {
      "epoch": 0.3918722786647315,
      "grad_norm": 1.0335183143615723,
      "learning_rate": 0.00010711209790870886,
      "loss": 1.9858,
      "step": 270
    },
    {
      "epoch": 0.40638606676342526,
      "grad_norm": 1.2859773635864258,
      "learning_rate": 9.988790209129117e-05,
      "loss": 2.0391,
      "step": 280
    },
    {
      "epoch": 0.420899854862119,
      "grad_norm": 1.4198274612426758,
      "learning_rate": 9.268130405179787e-05,
      "loss": 1.9753,
      "step": 290
    },
    {
      "epoch": 0.43541364296081275,
      "grad_norm": 3.4623429775238037,
      "learning_rate": 8.55274136114727e-05,
      "loss": 1.9868,
      "step": 300
    },
    {
      "epoch": 0.43541364296081275,
      "eval_loss": 2.034973382949829,
      "eval_runtime": 24.5613,
      "eval_samples_per_second": 11.807,
      "eval_steps_per_second": 2.972,
      "step": 300
    },
    {
      "epoch": 0.44992743105950656,
      "grad_norm": 0.9694491624832153,
      "learning_rate": 7.84610838054344e-05,
      "loss": 2.0345,
      "step": 310
    },
    {
      "epoch": 0.4644412191582003,
      "grad_norm": 1.099524736404419,
      "learning_rate": 7.151674108219295e-05,
      "loss": 1.991,
      "step": 320
    },
    {
      "epoch": 0.47895500725689405,
      "grad_norm": 1.2441976070404053,
      "learning_rate": 6.472821758145309e-05,
      "loss": 2.0073,
      "step": 330
    },
    {
      "epoch": 0.4934687953555878,
      "grad_norm": 1.3850934505462646,
      "learning_rate": 5.8128586307330475e-05,
      "loss": 2.0145,
      "step": 340
    },
    {
      "epoch": 0.5079825834542816,
      "grad_norm": 3.0692977905273438,
      "learning_rate": 5.175000000000002e-05,
      "loss": 1.9566,
      "step": 350
    },
    {
      "epoch": 0.5079825834542816,
      "eval_loss": 1.9906885623931885,
      "eval_runtime": 24.3553,
      "eval_samples_per_second": 11.907,
      "eval_steps_per_second": 2.997,
      "step": 350
    },
    {
      "epoch": 0.5224963715529753,
      "grad_norm": 0.9822912812232971,
      "learning_rate": 4.5623534490777714e-05,
      "loss": 2.0033,
      "step": 360
    },
    {
      "epoch": 0.5370101596516691,
      "grad_norm": 0.9240527153015137,
      "learning_rate": 3.9779037303794365e-05,
      "loss": 1.933,
      "step": 370
    },
    {
      "epoch": 0.5515239477503628,
      "grad_norm": 1.1260921955108643,
      "learning_rate": 3.42449822418582e-05,
      "loss": 1.9529,
      "step": 380
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.302894949913025,
      "learning_rate": 2.9048330664949622e-05,
      "loss": 1.9263,
      "step": 390
    },
    {
      "epoch": 0.5805515239477503,
      "grad_norm": 2.6783480644226074,
      "learning_rate": 2.4214400137185785e-05,
      "loss": 1.8083,
      "step": 400
    },
    {
      "epoch": 0.5805515239477503,
      "eval_loss": 1.9605308771133423,
      "eval_runtime": 24.3765,
      "eval_samples_per_second": 11.897,
      "eval_steps_per_second": 2.995,
      "step": 400
    },
    {
      "epoch": 0.5950653120464441,
      "grad_norm": 0.927768886089325,
      "learning_rate": 1.976674108219295e-05,
      "loss": 1.9795,
      "step": 410
    },
    {
      "epoch": 0.6095791001451378,
      "grad_norm": 0.8885520696640015,
      "learning_rate": 1.572702204780991e-05,
      "loss": 1.9164,
      "step": 420
    },
    {
      "epoch": 0.6240928882438317,
      "grad_norm": 1.0483330488204956,
      "learning_rate": 1.2114924139101056e-05,
      "loss": 1.9517,
      "step": 430
    },
    {
      "epoch": 0.6386066763425254,
      "grad_norm": 1.1401947736740112,
      "learning_rate": 8.948045133990798e-06,
      "loss": 1.9481,
      "step": 440
    },
    {
      "epoch": 0.6531204644412192,
      "grad_norm": 3.351959705352783,
      "learning_rate": 6.241813748658489e-06,
      "loss": 1.8876,
      "step": 450
    },
    {
      "epoch": 0.6531204644412192,
      "eval_loss": 1.946034550666809,
      "eval_runtime": 24.5405,
      "eval_samples_per_second": 11.817,
      "eval_steps_per_second": 2.975,
      "step": 450
    },
    {
      "epoch": 0.6676342525399129,
      "grad_norm": 0.895086407661438,
      "learning_rate": 4.009414470383994e-06,
      "loss": 1.9791,
      "step": 460
    },
    {
      "epoch": 0.6821480406386067,
      "grad_norm": 0.8754801750183105,
      "learning_rate": 2.261723324051111e-06,
      "loss": 1.9452,
      "step": 470
    },
    {
      "epoch": 0.6966618287373004,
      "grad_norm": 1.139264702796936,
      "learning_rate": 1.0072548852474675e-06,
      "loss": 1.9159,
      "step": 480
    },
    {
      "epoch": 0.7111756168359942,
      "grad_norm": 1.3206005096435547,
      "learning_rate": 2.5212079810819554e-07,
      "loss": 1.9687,
      "step": 490
    },
    {
      "epoch": 0.7256894049346879,
      "grad_norm": 2.6603949069976807,
      "learning_rate": 0.0,
      "loss": 1.8801,
      "step": 500
    },
    {
      "epoch": 0.7256894049346879,
      "eval_loss": 1.9433879852294922,
      "eval_runtime": 24.5489,
      "eval_samples_per_second": 11.813,
      "eval_steps_per_second": 2.974,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2944932147612877e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}