{
  "best_metric": 0.5222252011299133,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.09402914903620123,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018805829807240243,
      "eval_loss": 1.0244735479354858,
      "eval_runtime": 109.8257,
      "eval_samples_per_second": 20.387,
      "eval_steps_per_second": 5.099,
      "step": 1
    },
    {
      "epoch": 0.0018805829807240243,
      "grad_norm": 1.325929880142212,
      "learning_rate": 4.36e-05,
      "loss": 1.1597,
      "step": 10
    },
    {
      "epoch": 0.0037611659614480487,
      "grad_norm": 1.204135775566101,
      "learning_rate": 8.72e-05,
      "loss": 0.7094,
      "step": 20
    },
    {
      "epoch": 0.005641748942172073,
      "grad_norm": 0.9052909016609192,
      "learning_rate": 0.0001308,
      "loss": 0.5569,
      "step": 30
    },
    {
      "epoch": 0.007522331922896097,
      "grad_norm": 0.8271329998970032,
      "learning_rate": 0.0001744,
      "loss": 0.5544,
      "step": 40
    },
    {
      "epoch": 0.009402914903620122,
      "grad_norm": 1.0857207775115967,
      "learning_rate": 0.000218,
      "loss": 0.6082,
      "step": 50
    },
    {
      "epoch": 0.009402914903620122,
      "eval_loss": 0.6114992499351501,
      "eval_runtime": 109.3954,
      "eval_samples_per_second": 20.467,
      "eval_steps_per_second": 5.119,
      "step": 50
    },
    {
      "epoch": 0.011283497884344146,
      "grad_norm": 0.8605771064758301,
      "learning_rate": 0.00021773448147832086,
      "loss": 0.8378,
      "step": 60
    },
    {
      "epoch": 0.013164080865068171,
      "grad_norm": 0.8328661322593689,
      "learning_rate": 0.0002169392194928312,
      "loss": 0.5875,
      "step": 70
    },
    {
      "epoch": 0.015044663845792195,
      "grad_norm": 0.7275546193122864,
      "learning_rate": 0.00021561808847998484,
      "loss": 0.5119,
      "step": 80
    },
    {
      "epoch": 0.01692524682651622,
      "grad_norm": 1.0191245079040527,
      "learning_rate": 0.00021377752485727676,
      "loss": 0.5626,
      "step": 90
    },
    {
      "epoch": 0.018805829807240243,
      "grad_norm": 0.8722258806228638,
      "learning_rate": 0.00021142649566566402,
      "loss": 0.4782,
      "step": 100
    },
    {
      "epoch": 0.018805829807240243,
      "eval_loss": 0.5893458724021912,
      "eval_runtime": 109.6174,
      "eval_samples_per_second": 20.426,
      "eval_steps_per_second": 5.109,
      "step": 100
    },
    {
      "epoch": 0.020686412787964268,
      "grad_norm": 0.8007014989852905,
      "learning_rate": 0.0002085764548830435,
      "loss": 0.7676,
      "step": 110
    },
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 0.765451192855835,
      "learning_rate": 0.00020524128762162305,
      "loss": 0.6089,
      "step": 120
    },
    {
      "epoch": 0.024447578749412318,
      "grad_norm": 0.775343656539917,
      "learning_rate": 0.00020143724248105043,
      "loss": 0.495,
      "step": 130
    },
    {
      "epoch": 0.026328161730136343,
      "grad_norm": 0.856227695941925,
      "learning_rate": 0.0001971828523868693,
      "loss": 0.5466,
      "step": 140
    },
    {
      "epoch": 0.028208744710860368,
      "grad_norm": 0.7619214653968811,
      "learning_rate": 0.0001924988442999686,
      "loss": 0.4931,
      "step": 150
    },
    {
      "epoch": 0.028208744710860368,
      "eval_loss": 0.582227885723114,
      "eval_runtime": 109.3257,
      "eval_samples_per_second": 20.48,
      "eval_steps_per_second": 5.122,
      "step": 150
    },
    {
      "epoch": 0.03008932769158439,
      "grad_norm": 0.756696343421936,
      "learning_rate": 0.00018740803823691298,
      "loss": 0.6907,
      "step": 160
    },
    {
      "epoch": 0.031969910672308414,
      "grad_norm": 0.7834084033966064,
      "learning_rate": 0.00018193523609311556,
      "loss": 0.5946,
      "step": 170
    },
    {
      "epoch": 0.03385049365303244,
      "grad_norm": 0.7365180253982544,
      "learning_rate": 0.00017610710081049675,
      "loss": 0.507,
      "step": 180
    },
    {
      "epoch": 0.035731076633756464,
      "grad_norm": 0.8306977152824402,
      "learning_rate": 0.00016995202647831142,
      "loss": 0.5288,
      "step": 190
    },
    {
      "epoch": 0.037611659614480486,
      "grad_norm": 0.9597771763801575,
      "learning_rate": 0.00016350000000000002,
      "loss": 0.4864,
      "step": 200
    },
    {
      "epoch": 0.037611659614480486,
      "eval_loss": 0.5659375786781311,
      "eval_runtime": 109.741,
      "eval_samples_per_second": 20.403,
      "eval_steps_per_second": 5.103,
      "step": 200
    },
    {
      "epoch": 0.039492242595204514,
      "grad_norm": 0.737483024597168,
      "learning_rate": 0.00015678245500000943,
      "loss": 0.709,
      "step": 210
    },
    {
      "epoch": 0.041372825575928536,
      "grad_norm": 0.7262437343597412,
      "learning_rate": 0.00014983211868233444,
      "loss": 0.5847,
      "step": 220
    },
    {
      "epoch": 0.043253408556652564,
      "grad_norm": 0.8214493989944458,
      "learning_rate": 0.00014268285238686927,
      "loss": 0.5337,
      "step": 230
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.7294580936431885,
      "learning_rate": 0.00013536948662036378,
      "loss": 0.4972,
      "step": 240
    },
    {
      "epoch": 0.047014574518100614,
      "grad_norm": 0.8281709551811218,
      "learning_rate": 0.00012792765136569544,
      "loss": 0.4884,
      "step": 250
    },
    {
      "epoch": 0.047014574518100614,
      "eval_loss": 0.5536655783653259,
      "eval_runtime": 109.8147,
      "eval_samples_per_second": 20.389,
      "eval_steps_per_second": 5.1,
      "step": 250
    },
    {
      "epoch": 0.048895157498824636,
      "grad_norm": 0.7920747995376587,
      "learning_rate": 0.00012039360249617425,
      "loss": 0.6937,
      "step": 260
    },
    {
      "epoch": 0.05077574047954866,
      "grad_norm": 0.7113749980926514,
      "learning_rate": 0.00011280404514057264,
      "loss": 0.5313,
      "step": 270
    },
    {
      "epoch": 0.052656323460272686,
      "grad_norm": 0.7820623517036438,
      "learning_rate": 0.00010519595485942743,
      "loss": 0.5391,
      "step": 280
    },
    {
      "epoch": 0.05453690644099671,
      "grad_norm": 0.762988805770874,
      "learning_rate": 9.76063975038258e-05,
      "loss": 0.5062,
      "step": 290
    },
    {
      "epoch": 0.056417489421720736,
      "grad_norm": 1.0487847328186035,
      "learning_rate": 9.00723486343046e-05,
      "loss": 0.4998,
      "step": 300
    },
    {
      "epoch": 0.056417489421720736,
      "eval_loss": 0.5473635196685791,
      "eval_runtime": 109.2505,
      "eval_samples_per_second": 20.494,
      "eval_steps_per_second": 5.126,
      "step": 300
    },
    {
      "epoch": 0.05829807240244476,
      "grad_norm": 0.7474403977394104,
      "learning_rate": 8.263051337963623e-05,
      "loss": 0.7482,
      "step": 310
    },
    {
      "epoch": 0.06017865538316878,
      "grad_norm": 0.824717104434967,
      "learning_rate": 7.531714761313074e-05,
      "loss": 0.5858,
      "step": 320
    },
    {
      "epoch": 0.06205923836389281,
      "grad_norm": 0.6236701011657715,
      "learning_rate": 6.816788131766559e-05,
      "loss": 0.5217,
      "step": 330
    },
    {
      "epoch": 0.06393982134461683,
      "grad_norm": 0.8206383585929871,
      "learning_rate": 6.121754499999055e-05,
      "loss": 0.4875,
      "step": 340
    },
    {
      "epoch": 0.06582040432534085,
      "grad_norm": 0.7857638001441956,
      "learning_rate": 5.450000000000003e-05,
      "loss": 0.4591,
      "step": 350
    },
    {
      "epoch": 0.06582040432534085,
      "eval_loss": 0.5349125862121582,
      "eval_runtime": 110.1428,
      "eval_samples_per_second": 20.328,
      "eval_steps_per_second": 5.084,
      "step": 350
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.721478283405304,
      "learning_rate": 4.804797352168861e-05,
      "loss": 0.6473,
      "step": 360
    },
    {
      "epoch": 0.06958157028678891,
      "grad_norm": 0.6118484735488892,
      "learning_rate": 4.189289918950325e-05,
      "loss": 0.5278,
      "step": 370
    },
    {
      "epoch": 0.07146215326751293,
      "grad_norm": 0.6939198970794678,
      "learning_rate": 3.606476390688449e-05,
      "loss": 0.516,
      "step": 380
    },
    {
      "epoch": 0.07334273624823695,
      "grad_norm": 0.6780189275741577,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 0.5085,
      "step": 390
    },
    {
      "epoch": 0.07522331922896097,
      "grad_norm": 0.786106288433075,
      "learning_rate": 2.550115570003141e-05,
      "loss": 0.4749,
      "step": 400
    },
    {
      "epoch": 0.07522331922896097,
      "eval_loss": 0.5289891362190247,
      "eval_runtime": 109.4848,
      "eval_samples_per_second": 20.45,
      "eval_steps_per_second": 5.115,
      "step": 400
    },
    {
      "epoch": 0.07710390220968501,
      "grad_norm": 0.6698129773139954,
      "learning_rate": 2.081714761313074e-05,
      "loss": 0.7042,
      "step": 410
    },
    {
      "epoch": 0.07898448519040903,
      "grad_norm": 0.6338317394256592,
      "learning_rate": 1.656275751894957e-05,
      "loss": 0.5512,
      "step": 420
    },
    {
      "epoch": 0.08086506817113305,
      "grad_norm": 0.6592607498168945,
      "learning_rate": 1.275871237837696e-05,
      "loss": 0.4842,
      "step": 430
    },
    {
      "epoch": 0.08274565115185707,
      "grad_norm": 0.6793785095214844,
      "learning_rate": 9.423545116956494e-06,
      "loss": 0.4469,
      "step": 440
    },
    {
      "epoch": 0.0846262341325811,
      "grad_norm": 0.8718426823616028,
      "learning_rate": 6.573504334335994e-06,
      "loss": 0.4685,
      "step": 450
    },
    {
      "epoch": 0.0846262341325811,
      "eval_loss": 0.5236806869506836,
      "eval_runtime": 109.5695,
      "eval_samples_per_second": 20.435,
      "eval_steps_per_second": 5.111,
      "step": 450
    },
    {
      "epoch": 0.08650681711330513,
      "grad_norm": 1.0036578178405762,
      "learning_rate": 4.22247514272324e-06,
      "loss": 0.6469,
      "step": 460
    },
    {
      "epoch": 0.08838740009402915,
      "grad_norm": 0.6492578983306885,
      "learning_rate": 2.38191152001518e-06,
      "loss": 0.535,
      "step": 470
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.6323084235191345,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 0.51,
      "step": 480
    },
    {
      "epoch": 0.0921485660554772,
      "grad_norm": 0.7388293743133545,
      "learning_rate": 2.655185216791625e-07,
      "loss": 0.4515,
      "step": 490
    },
    {
      "epoch": 0.09402914903620123,
      "grad_norm": 0.8955107927322388,
      "learning_rate": 0.0,
      "loss": 0.4406,
      "step": 500
    },
    {
      "epoch": 0.09402914903620123,
      "eval_loss": 0.5222252011299133,
      "eval_runtime": 109.295,
      "eval_samples_per_second": 20.486,
      "eval_steps_per_second": 5.124,
      "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": 5.442856891396915e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}