{
  "best_metric": 1.1944663524627686,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.08488964346349745,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016977928692699492,
      "eval_loss": 1.4329637289047241,
      "eval_runtime": 234.9554,
      "eval_samples_per_second": 5.278,
      "eval_steps_per_second": 1.319,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": 1.341242790222168,
      "learning_rate": 4.12e-05,
      "loss": 1.4209,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": 0.7306675910949707,
      "learning_rate": 8.24e-05,
      "loss": 1.338,
      "step": 20
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": 0.7428624629974365,
      "learning_rate": 0.0001236,
      "loss": 1.2576,
      "step": 30
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": 0.7021359205245972,
      "learning_rate": 0.0001648,
      "loss": 1.2015,
      "step": 40
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": 0.8103872537612915,
      "learning_rate": 0.000206,
      "loss": 1.2281,
      "step": 50
    },
    {
      "epoch": 0.008488964346349746,
      "eval_loss": 1.2455830574035645,
      "eval_runtime": 237.2217,
      "eval_samples_per_second": 5.227,
      "eval_steps_per_second": 1.307,
      "step": 50
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": 0.7842703461647034,
      "learning_rate": 0.0002057490971767619,
      "loss": 1.2212,
      "step": 60
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": 0.8670001029968262,
      "learning_rate": 0.00020499761108038175,
      "loss": 1.2051,
      "step": 70
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": 0.8176340460777283,
      "learning_rate": 0.00020374920287558198,
      "loss": 1.209,
      "step": 80
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": 1.0117417573928833,
      "learning_rate": 0.00020200995468164684,
      "loss": 1.2546,
      "step": 90
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": 1.4239269495010376,
      "learning_rate": 0.00019978833994094855,
      "loss": 1.3016,
      "step": 100
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": 1.3394960165023804,
      "eval_runtime": 236.5162,
      "eval_samples_per_second": 5.243,
      "eval_steps_per_second": 1.311,
      "step": 100
    },
    {
      "epoch": 0.01867572156196944,
      "grad_norm": 0.6853418350219727,
      "learning_rate": 0.00019709518213718787,
      "loss": 1.3013,
      "step": 110
    },
    {
      "epoch": 0.02037351443123939,
      "grad_norm": 0.7583730816841125,
      "learning_rate": 0.00019394360206446948,
      "loss": 1.1855,
      "step": 120
    },
    {
      "epoch": 0.022071307300509338,
      "grad_norm": 0.8353321552276611,
      "learning_rate": 0.00019034895390411186,
      "loss": 1.2214,
      "step": 130
    },
    {
      "epoch": 0.023769100169779286,
      "grad_norm": 0.8519904613494873,
      "learning_rate": 0.0001863287504206196,
      "loss": 1.2907,
      "step": 140
    },
    {
      "epoch": 0.025466893039049237,
      "grad_norm": 0.7282483577728271,
      "learning_rate": 0.00018190257764125471,
      "loss": 1.1985,
      "step": 150
    },
    {
      "epoch": 0.025466893039049237,
      "eval_loss": 1.2455435991287231,
      "eval_runtime": 237.1965,
      "eval_samples_per_second": 5.228,
      "eval_steps_per_second": 1.307,
      "step": 150
    },
    {
      "epoch": 0.027164685908319185,
      "grad_norm": 0.8496482968330383,
      "learning_rate": 0.00017709199943488106,
      "loss": 1.1761,
      "step": 160
    },
    {
      "epoch": 0.028862478777589132,
      "grad_norm": 0.7892032861709595,
      "learning_rate": 0.00017192045245496238,
      "loss": 1.2281,
      "step": 170
    },
    {
      "epoch": 0.030560271646859084,
      "grad_norm": 0.8588133454322815,
      "learning_rate": 0.00016641313195854277,
      "loss": 1.205,
      "step": 180
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.9884034991264343,
      "learning_rate": 0.0001605968690574869,
      "loss": 1.2602,
      "step": 190
    },
    {
      "epoch": 0.03395585738539898,
      "grad_norm": 1.295212745666504,
      "learning_rate": 0.0001545,
      "loss": 1.2808,
      "step": 200
    },
    {
      "epoch": 0.03395585738539898,
      "eval_loss": 1.3785539865493774,
      "eval_runtime": 236.0337,
      "eval_samples_per_second": 5.253,
      "eval_steps_per_second": 1.313,
      "step": 200
    },
    {
      "epoch": 0.035653650254668934,
      "grad_norm": 0.7312771081924438,
      "learning_rate": 0.00014815222811927496,
      "loss": 1.249,
      "step": 210
    },
    {
      "epoch": 0.03735144312393888,
      "grad_norm": 0.748958170413971,
      "learning_rate": 0.00014158447912183896,
      "loss": 1.2374,
      "step": 220
    },
    {
      "epoch": 0.03904923599320883,
      "grad_norm": 0.7886843681335449,
      "learning_rate": 0.00013482875042061958,
      "loss": 1.2235,
      "step": 230
    },
    {
      "epoch": 0.04074702886247878,
      "grad_norm": 0.7367339134216309,
      "learning_rate": 0.00012791795524676576,
      "loss": 1.1971,
      "step": 240
    },
    {
      "epoch": 0.042444821731748725,
      "grad_norm": 0.8220826983451843,
      "learning_rate": 0.00012088576229969385,
      "loss": 1.2372,
      "step": 250
    },
    {
      "epoch": 0.042444821731748725,
      "eval_loss": 1.2279402017593384,
      "eval_runtime": 237.5615,
      "eval_samples_per_second": 5.22,
      "eval_steps_per_second": 1.305,
      "step": 250
    },
    {
      "epoch": 0.044142614601018676,
      "grad_norm": 0.7322437167167664,
      "learning_rate": 0.0001137664317165683,
      "loss": 1.2527,
      "step": 260
    },
    {
      "epoch": 0.04584040747028863,
      "grad_norm": 0.7987295985221863,
      "learning_rate": 0.00010659464816035761,
      "loss": 1.2151,
      "step": 270
    },
    {
      "epoch": 0.04753820033955857,
      "grad_norm": 0.8461410999298096,
      "learning_rate": 9.940535183964242e-05,
      "loss": 1.1581,
      "step": 280
    },
    {
      "epoch": 0.04923599320882852,
      "grad_norm": 0.893200159072876,
      "learning_rate": 9.22335682834317e-05,
      "loss": 1.1902,
      "step": 290
    },
    {
      "epoch": 0.050933786078098474,
      "grad_norm": 1.0908836126327515,
      "learning_rate": 8.511423770030617e-05,
      "loss": 1.285,
      "step": 300
    },
    {
      "epoch": 0.050933786078098474,
      "eval_loss": 1.2769778966903687,
      "eval_runtime": 235.1131,
      "eval_samples_per_second": 5.274,
      "eval_steps_per_second": 1.319,
      "step": 300
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.6881177425384521,
      "learning_rate": 7.808204475323423e-05,
      "loss": 1.2984,
      "step": 310
    },
    {
      "epoch": 0.05432937181663837,
      "grad_norm": 0.6913091540336609,
      "learning_rate": 7.117124957938042e-05,
      "loss": 1.1949,
      "step": 320
    },
    {
      "epoch": 0.05602716468590832,
      "grad_norm": 0.6359566450119019,
      "learning_rate": 6.441552087816105e-05,
      "loss": 1.2487,
      "step": 330
    },
    {
      "epoch": 0.057724957555178265,
      "grad_norm": 0.6509237289428711,
      "learning_rate": 5.784777188072502e-05,
      "loss": 1.1914,
      "step": 340
    },
    {
      "epoch": 0.059422750424448216,
      "grad_norm": 0.7074187994003296,
      "learning_rate": 5.150000000000002e-05,
      "loss": 1.1768,
      "step": 350
    },
    {
      "epoch": 0.059422750424448216,
      "eval_loss": 1.2067750692367554,
      "eval_runtime": 236.6964,
      "eval_samples_per_second": 5.239,
      "eval_steps_per_second": 1.31,
      "step": 350
    },
    {
      "epoch": 0.06112054329371817,
      "grad_norm": 0.7682424187660217,
      "learning_rate": 4.540313094251309e-05,
      "loss": 1.1792,
      "step": 360
    },
    {
      "epoch": 0.06281833616298811,
      "grad_norm": 0.7742196321487427,
      "learning_rate": 3.958686804145719e-05,
      "loss": 1.1434,
      "step": 370
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 0.8594280481338501,
      "learning_rate": 3.4079547545037634e-05,
      "loss": 1.1741,
      "step": 380
    },
    {
      "epoch": 0.06621392190152801,
      "grad_norm": 0.8601087331771851,
      "learning_rate": 2.8908000565118947e-05,
      "loss": 1.2038,
      "step": 390
    },
    {
      "epoch": 0.06791171477079797,
      "grad_norm": 1.167262077331543,
      "learning_rate": 2.4097422358745275e-05,
      "loss": 1.2147,
      "step": 400
    },
    {
      "epoch": 0.06791171477079797,
      "eval_loss": 1.2109880447387695,
      "eval_runtime": 235.5973,
      "eval_samples_per_second": 5.263,
      "eval_steps_per_second": 1.316,
      "step": 400
    },
    {
      "epoch": 0.06960950764006792,
      "grad_norm": 0.7046334743499756,
      "learning_rate": 1.9671249579380422e-05,
      "loss": 1.2294,
      "step": 410
    },
    {
      "epoch": 0.07130730050933787,
      "grad_norm": 0.6611829400062561,
      "learning_rate": 1.5651046095888127e-05,
      "loss": 1.1951,
      "step": 420
    },
    {
      "epoch": 0.0730050933786078,
      "grad_norm": 0.5956356525421143,
      "learning_rate": 1.205639793553052e-05,
      "loss": 1.1891,
      "step": 430
    },
    {
      "epoch": 0.07470288624787776,
      "grad_norm": 0.6220433115959167,
      "learning_rate": 8.904817862812098e-06,
      "loss": 1.1773,
      "step": 440
    },
    {
      "epoch": 0.07640067911714771,
      "grad_norm": 0.7181682586669922,
      "learning_rate": 6.211660059051443e-06,
      "loss": 1.2383,
      "step": 450
    },
    {
      "epoch": 0.07640067911714771,
      "eval_loss": 1.1962662935256958,
      "eval_runtime": 235.3359,
      "eval_samples_per_second": 5.269,
      "eval_steps_per_second": 1.317,
      "step": 450
    },
    {
      "epoch": 0.07809847198641766,
      "grad_norm": 0.7613552212715149,
      "learning_rate": 3.990045318353154e-06,
      "loss": 1.2263,
      "step": 460
    },
    {
      "epoch": 0.07979626485568761,
      "grad_norm": 0.7208029627799988,
      "learning_rate": 2.250797124418014e-06,
      "loss": 1.2039,
      "step": 470
    },
    {
      "epoch": 0.08149405772495756,
      "grad_norm": 0.8188151121139526,
      "learning_rate": 1.0023889196182526e-06,
      "loss": 1.2092,
      "step": 480
    },
    {
      "epoch": 0.0831918505942275,
      "grad_norm": 0.7839704751968384,
      "learning_rate": 2.5090282323810766e-07,
      "loss": 1.2678,
      "step": 490
    },
    {
      "epoch": 0.08488964346349745,
      "grad_norm": 1.197765588760376,
      "learning_rate": 0.0,
      "loss": 1.2776,
      "step": 500
    },
    {
      "epoch": 0.08488964346349745,
      "eval_loss": 1.1944663524627686,
      "eval_runtime": 235.1406,
      "eval_samples_per_second": 5.273,
      "eval_steps_per_second": 1.318,
      "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": 1.589424290959196e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}