{
  "best_metric": 1.0734155178070068,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.3838771593090211,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007677543186180423,
      "eval_loss": 1.699501633644104,
      "eval_runtime": 34.5919,
      "eval_samples_per_second": 15.871,
      "eval_steps_per_second": 3.989,
      "step": 1
    },
    {
      "epoch": 0.007677543186180422,
      "grad_norm": 1.66623854637146,
      "learning_rate": 4.1400000000000003e-05,
      "loss": 1.4758,
      "step": 10
    },
    {
      "epoch": 0.015355086372360844,
      "grad_norm": 1.6191164255142212,
      "learning_rate": 8.280000000000001e-05,
      "loss": 1.1966,
      "step": 20
    },
    {
      "epoch": 0.023032629558541268,
      "grad_norm": 1.8581939935684204,
      "learning_rate": 0.00012419999999999998,
      "loss": 1.1972,
      "step": 30
    },
    {
      "epoch": 0.030710172744721688,
      "grad_norm": 2.0947399139404297,
      "learning_rate": 0.00016560000000000001,
      "loss": 1.1415,
      "step": 40
    },
    {
      "epoch": 0.03838771593090211,
      "grad_norm": 3.375594139099121,
      "learning_rate": 0.000207,
      "loss": 1.1509,
      "step": 50
    },
    {
      "epoch": 0.03838771593090211,
      "eval_loss": 1.1970173120498657,
      "eval_runtime": 34.6084,
      "eval_samples_per_second": 15.863,
      "eval_steps_per_second": 3.987,
      "step": 50
    },
    {
      "epoch": 0.046065259117082535,
      "grad_norm": 1.4098953008651733,
      "learning_rate": 0.00020674787920189178,
      "loss": 1.0217,
      "step": 60
    },
    {
      "epoch": 0.053742802303262956,
      "grad_norm": 1.2954459190368652,
      "learning_rate": 0.00020599274511475253,
      "loss": 1.196,
      "step": 70
    },
    {
      "epoch": 0.061420345489443376,
      "grad_norm": 1.554813265800476,
      "learning_rate": 0.00020473827667594888,
      "loss": 1.1842,
      "step": 80
    },
    {
      "epoch": 0.0690978886756238,
      "grad_norm": 1.6619945764541626,
      "learning_rate": 0.00020299058552961598,
      "loss": 1.1747,
      "step": 90
    },
    {
      "epoch": 0.07677543186180422,
      "grad_norm": 5.735137462615967,
      "learning_rate": 0.00020075818625134152,
      "loss": 1.1506,
      "step": 100
    },
    {
      "epoch": 0.07677543186180422,
      "eval_loss": 1.270753026008606,
      "eval_runtime": 34.5609,
      "eval_samples_per_second": 15.885,
      "eval_steps_per_second": 3.993,
      "step": 100
    },
    {
      "epoch": 0.08445297504798464,
      "grad_norm": 1.7361294031143188,
      "learning_rate": 0.00019805195486600916,
      "loss": 1.0687,
      "step": 110
    },
    {
      "epoch": 0.09213051823416507,
      "grad_norm": 1.5904954671859741,
      "learning_rate": 0.00019488507586089894,
      "loss": 1.139,
      "step": 120
    },
    {
      "epoch": 0.09980806142034548,
      "grad_norm": 1.775456428527832,
      "learning_rate": 0.00019127297795219008,
      "loss": 1.1186,
      "step": 130
    },
    {
      "epoch": 0.10748560460652591,
      "grad_norm": 2.0062367916107178,
      "learning_rate": 0.00018723325891780706,
      "loss": 1.2057,
      "step": 140
    },
    {
      "epoch": 0.11516314779270634,
      "grad_norm": 3.6948869228363037,
      "learning_rate": 0.0001827855998628142,
      "loss": 1.0385,
      "step": 150
    },
    {
      "epoch": 0.11516314779270634,
      "eval_loss": 1.1850098371505737,
      "eval_runtime": 34.5429,
      "eval_samples_per_second": 15.893,
      "eval_steps_per_second": 3.995,
      "step": 150
    },
    {
      "epoch": 0.12284069097888675,
      "grad_norm": 1.3466116189956665,
      "learning_rate": 0.0001779516693350504,
      "loss": 1.0089,
      "step": 160
    },
    {
      "epoch": 0.13051823416506717,
      "grad_norm": 1.5833830833435059,
      "learning_rate": 0.00017275501775814182,
      "loss": 1.183,
      "step": 170
    },
    {
      "epoch": 0.1381957773512476,
      "grad_norm": 1.7136775255203247,
      "learning_rate": 0.00016722096269620562,
      "loss": 1.1192,
      "step": 180
    },
    {
      "epoch": 0.14587332053742802,
      "grad_norm": 1.7458416223526,
      "learning_rate": 0.00016137646550922228,
      "loss": 1.1443,
      "step": 190
    },
    {
      "epoch": 0.15355086372360843,
      "grad_norm": 4.119271755218506,
      "learning_rate": 0.00015525,
      "loss": 1.1007,
      "step": 200
    },
    {
      "epoch": 0.15355086372360843,
      "eval_loss": 1.1791120767593384,
      "eval_runtime": 34.4288,
      "eval_samples_per_second": 15.946,
      "eval_steps_per_second": 4.008,
      "step": 200
    },
    {
      "epoch": 0.16122840690978887,
      "grad_norm": 1.5441445112228394,
      "learning_rate": 0.0001488714136926695,
      "loss": 0.987,
      "step": 210
    },
    {
      "epoch": 0.1689059500959693,
      "grad_norm": 1.489668846130371,
      "learning_rate": 0.0001422717824185469,
      "loss": 1.1229,
      "step": 220
    },
    {
      "epoch": 0.1765834932821497,
      "grad_norm": 1.63771653175354,
      "learning_rate": 0.00013548325891780705,
      "loss": 1.0888,
      "step": 230
    },
    {
      "epoch": 0.18426103646833014,
      "grad_norm": 1.9554612636566162,
      "learning_rate": 0.0001285389161945656,
      "loss": 1.1235,
      "step": 240
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 2.936532735824585,
      "learning_rate": 0.0001214725863885273,
      "loss": 1.1173,
      "step": 250
    },
    {
      "epoch": 0.19193857965451055,
      "eval_loss": 1.164772629737854,
      "eval_runtime": 34.6581,
      "eval_samples_per_second": 15.84,
      "eval_steps_per_second": 3.982,
      "step": 250
    },
    {
      "epoch": 0.19961612284069097,
      "grad_norm": 1.3022620677947998,
      "learning_rate": 0.00011431869594820213,
      "loss": 1.0618,
      "step": 260
    },
    {
      "epoch": 0.2072936660268714,
      "grad_norm": 1.5140739679336548,
      "learning_rate": 0.00010711209790870886,
      "loss": 1.0069,
      "step": 270
    },
    {
      "epoch": 0.21497120921305182,
      "grad_norm": 2.146951675415039,
      "learning_rate": 9.988790209129117e-05,
      "loss": 1.1379,
      "step": 280
    },
    {
      "epoch": 0.22264875239923224,
      "grad_norm": 1.9529863595962524,
      "learning_rate": 9.268130405179787e-05,
      "loss": 1.143,
      "step": 290
    },
    {
      "epoch": 0.23032629558541268,
      "grad_norm": 4.628264904022217,
      "learning_rate": 8.55274136114727e-05,
      "loss": 1.1066,
      "step": 300
    },
    {
      "epoch": 0.23032629558541268,
      "eval_loss": 1.1256804466247559,
      "eval_runtime": 34.7811,
      "eval_samples_per_second": 15.784,
      "eval_steps_per_second": 3.968,
      "step": 300
    },
    {
      "epoch": 0.2380038387715931,
      "grad_norm": 1.5281367301940918,
      "learning_rate": 7.84610838054344e-05,
      "loss": 1.0167,
      "step": 310
    },
    {
      "epoch": 0.2456813819577735,
      "grad_norm": 1.4944322109222412,
      "learning_rate": 7.151674108219295e-05,
      "loss": 1.0431,
      "step": 320
    },
    {
      "epoch": 0.2533589251439539,
      "grad_norm": 1.5290899276733398,
      "learning_rate": 6.472821758145309e-05,
      "loss": 1.0743,
      "step": 330
    },
    {
      "epoch": 0.26103646833013433,
      "grad_norm": 1.7399842739105225,
      "learning_rate": 5.8128586307330475e-05,
      "loss": 1.1366,
      "step": 340
    },
    {
      "epoch": 0.2687140115163148,
      "grad_norm": 3.488797903060913,
      "learning_rate": 5.175000000000002e-05,
      "loss": 1.106,
      "step": 350
    },
    {
      "epoch": 0.2687140115163148,
      "eval_loss": 1.0944420099258423,
      "eval_runtime": 34.5813,
      "eval_samples_per_second": 15.876,
      "eval_steps_per_second": 3.991,
      "step": 350
    },
    {
      "epoch": 0.2763915547024952,
      "grad_norm": 1.4888174533843994,
      "learning_rate": 4.5623534490777714e-05,
      "loss": 0.9956,
      "step": 360
    },
    {
      "epoch": 0.2840690978886756,
      "grad_norm": 1.6224281787872314,
      "learning_rate": 3.9779037303794365e-05,
      "loss": 1.1409,
      "step": 370
    },
    {
      "epoch": 0.29174664107485604,
      "grad_norm": 1.536541223526001,
      "learning_rate": 3.42449822418582e-05,
      "loss": 1.1059,
      "step": 380
    },
    {
      "epoch": 0.29942418426103645,
      "grad_norm": 1.5598728656768799,
      "learning_rate": 2.9048330664949622e-05,
      "loss": 1.0613,
      "step": 390
    },
    {
      "epoch": 0.30710172744721687,
      "grad_norm": 3.250027894973755,
      "learning_rate": 2.4214400137185785e-05,
      "loss": 1.0349,
      "step": 400
    },
    {
      "epoch": 0.30710172744721687,
      "eval_loss": 1.0797396898269653,
      "eval_runtime": 34.5561,
      "eval_samples_per_second": 15.887,
      "eval_steps_per_second": 3.994,
      "step": 400
    },
    {
      "epoch": 0.31477927063339733,
      "grad_norm": 1.4682611227035522,
      "learning_rate": 1.976674108219295e-05,
      "loss": 1.0682,
      "step": 410
    },
    {
      "epoch": 0.32245681381957775,
      "grad_norm": 1.593374490737915,
      "learning_rate": 1.572702204780991e-05,
      "loss": 0.9887,
      "step": 420
    },
    {
      "epoch": 0.33013435700575816,
      "grad_norm": 1.7837949991226196,
      "learning_rate": 1.2114924139101056e-05,
      "loss": 1.0989,
      "step": 430
    },
    {
      "epoch": 0.3378119001919386,
      "grad_norm": 1.7039244174957275,
      "learning_rate": 8.948045133990798e-06,
      "loss": 1.0906,
      "step": 440
    },
    {
      "epoch": 0.345489443378119,
      "grad_norm": 4.831996440887451,
      "learning_rate": 6.241813748658489e-06,
      "loss": 1.0559,
      "step": 450
    },
    {
      "epoch": 0.345489443378119,
      "eval_loss": 1.0759239196777344,
      "eval_runtime": 34.4862,
      "eval_samples_per_second": 15.919,
      "eval_steps_per_second": 4.002,
      "step": 450
    },
    {
      "epoch": 0.3531669865642994,
      "grad_norm": 1.207382082939148,
      "learning_rate": 4.009414470383994e-06,
      "loss": 0.9927,
      "step": 460
    },
    {
      "epoch": 0.36084452975047987,
      "grad_norm": 1.4170714616775513,
      "learning_rate": 2.261723324051111e-06,
      "loss": 1.037,
      "step": 470
    },
    {
      "epoch": 0.3685220729366603,
      "grad_norm": 1.47847580909729,
      "learning_rate": 1.0072548852474675e-06,
      "loss": 1.0271,
      "step": 480
    },
    {
      "epoch": 0.3761996161228407,
      "grad_norm": 1.718285083770752,
      "learning_rate": 2.5212079810819554e-07,
      "loss": 1.0511,
      "step": 490
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 3.448530435562134,
      "learning_rate": 0.0,
      "loss": 1.0046,
      "step": 500
    },
    {
      "epoch": 0.3838771593090211,
      "eval_loss": 1.0734155178070068,
      "eval_runtime": 34.6444,
      "eval_samples_per_second": 15.847,
      "eval_steps_per_second": 3.983,
      "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": 9.729912582910771e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}