{
  "best_metric": 1.5615293979644775,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.009793072380597964,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.958614476119593e-05,
      "eval_loss": 2.541055679321289,
      "eval_runtime": 808.5156,
      "eval_samples_per_second": 26.589,
      "eval_steps_per_second": 6.648,
      "step": 1
    },
    {
      "epoch": 0.0001958614476119593,
      "grad_norm": 0.42259156703948975,
      "learning_rate": 4.12e-05,
      "loss": 2.4447,
      "step": 10
    },
    {
      "epoch": 0.0003917228952239186,
      "grad_norm": 0.4474017918109894,
      "learning_rate": 8.24e-05,
      "loss": 2.3596,
      "step": 20
    },
    {
      "epoch": 0.0005875843428358779,
      "grad_norm": 0.5387372970581055,
      "learning_rate": 0.0001236,
      "loss": 2.2655,
      "step": 30
    },
    {
      "epoch": 0.0007834457904478372,
      "grad_norm": 0.6558287739753723,
      "learning_rate": 0.0001648,
      "loss": 2.1072,
      "step": 40
    },
    {
      "epoch": 0.0009793072380597965,
      "grad_norm": 0.790547788143158,
      "learning_rate": 0.000206,
      "loss": 2.031,
      "step": 50
    },
    {
      "epoch": 0.0009793072380597965,
      "eval_loss": 2.0144009590148926,
      "eval_runtime": 811.9056,
      "eval_samples_per_second": 26.478,
      "eval_steps_per_second": 6.62,
      "step": 50
    },
    {
      "epoch": 0.0011751686856717558,
      "grad_norm": 0.474514901638031,
      "learning_rate": 0.0002057490971767619,
      "loss": 1.9995,
      "step": 60
    },
    {
      "epoch": 0.001371030133283715,
      "grad_norm": 0.48066890239715576,
      "learning_rate": 0.00020499761108038175,
      "loss": 1.9568,
      "step": 70
    },
    {
      "epoch": 0.0015668915808956744,
      "grad_norm": 0.5162322521209717,
      "learning_rate": 0.00020374920287558198,
      "loss": 1.8879,
      "step": 80
    },
    {
      "epoch": 0.0017627530285076337,
      "grad_norm": 0.5203802585601807,
      "learning_rate": 0.00020200995468164684,
      "loss": 1.8786,
      "step": 90
    },
    {
      "epoch": 0.001958614476119593,
      "grad_norm": 0.6834505796432495,
      "learning_rate": 0.00019978833994094855,
      "loss": 1.8963,
      "step": 100
    },
    {
      "epoch": 0.001958614476119593,
      "eval_loss": 1.8420443534851074,
      "eval_runtime": 802.6412,
      "eval_samples_per_second": 26.784,
      "eval_steps_per_second": 6.697,
      "step": 100
    },
    {
      "epoch": 0.0021544759237315525,
      "grad_norm": 0.4236699044704437,
      "learning_rate": 0.00019709518213718787,
      "loss": 1.8609,
      "step": 110
    },
    {
      "epoch": 0.0023503373713435116,
      "grad_norm": 0.47379371523857117,
      "learning_rate": 0.00019394360206446948,
      "loss": 1.8112,
      "step": 120
    },
    {
      "epoch": 0.002546198818955471,
      "grad_norm": 0.48835086822509766,
      "learning_rate": 0.00019034895390411186,
      "loss": 1.7648,
      "step": 130
    },
    {
      "epoch": 0.00274206026656743,
      "grad_norm": 0.5578092336654663,
      "learning_rate": 0.0001863287504206196,
      "loss": 1.8491,
      "step": 140
    },
    {
      "epoch": 0.0029379217141793897,
      "grad_norm": 0.7225767374038696,
      "learning_rate": 0.00018190257764125471,
      "loss": 1.7379,
      "step": 150
    },
    {
      "epoch": 0.0029379217141793897,
      "eval_loss": 1.766533374786377,
      "eval_runtime": 808.4925,
      "eval_samples_per_second": 26.59,
      "eval_steps_per_second": 6.648,
      "step": 150
    },
    {
      "epoch": 0.0031337831617913488,
      "grad_norm": 0.4122462868690491,
      "learning_rate": 0.00017709199943488106,
      "loss": 1.8591,
      "step": 160
    },
    {
      "epoch": 0.0033296446094033083,
      "grad_norm": 0.45456036925315857,
      "learning_rate": 0.00017192045245496238,
      "loss": 1.7107,
      "step": 170
    },
    {
      "epoch": 0.0035255060570152674,
      "grad_norm": 0.4639202356338501,
      "learning_rate": 0.00016641313195854277,
      "loss": 1.6736,
      "step": 180
    },
    {
      "epoch": 0.003721367504627227,
      "grad_norm": 0.551369309425354,
      "learning_rate": 0.0001605968690574869,
      "loss": 1.7199,
      "step": 190
    },
    {
      "epoch": 0.003917228952239186,
      "grad_norm": 0.6994920969009399,
      "learning_rate": 0.0001545,
      "loss": 1.6386,
      "step": 200
    },
    {
      "epoch": 0.003917228952239186,
      "eval_loss": 1.7132164239883423,
      "eval_runtime": 815.4936,
      "eval_samples_per_second": 26.362,
      "eval_steps_per_second": 6.591,
      "step": 200
    },
    {
      "epoch": 0.004113090399851145,
      "grad_norm": 0.43010979890823364,
      "learning_rate": 0.00014815222811927496,
      "loss": 1.7888,
      "step": 210
    },
    {
      "epoch": 0.004308951847463105,
      "grad_norm": 0.4258266091346741,
      "learning_rate": 0.00014158447912183896,
      "loss": 1.6298,
      "step": 220
    },
    {
      "epoch": 0.004504813295075064,
      "grad_norm": 0.47796645760536194,
      "learning_rate": 0.00013482875042061958,
      "loss": 1.6301,
      "step": 230
    },
    {
      "epoch": 0.004700674742687023,
      "grad_norm": 0.5105708241462708,
      "learning_rate": 0.00012791795524676576,
      "loss": 1.6413,
      "step": 240
    },
    {
      "epoch": 0.004896536190298982,
      "grad_norm": 0.6835204362869263,
      "learning_rate": 0.00012088576229969385,
      "loss": 1.6857,
      "step": 250
    },
    {
      "epoch": 0.004896536190298982,
      "eval_loss": 1.6581625938415527,
      "eval_runtime": 808.8687,
      "eval_samples_per_second": 26.578,
      "eval_steps_per_second": 6.645,
      "step": 250
    },
    {
      "epoch": 0.005092397637910942,
      "grad_norm": 0.4199804961681366,
      "learning_rate": 0.0001137664317165683,
      "loss": 1.786,
      "step": 260
    },
    {
      "epoch": 0.005288259085522901,
      "grad_norm": 0.46537598967552185,
      "learning_rate": 0.00010659464816035761,
      "loss": 1.6461,
      "step": 270
    },
    {
      "epoch": 0.00548412053313486,
      "grad_norm": 0.5051584243774414,
      "learning_rate": 9.940535183964242e-05,
      "loss": 1.5999,
      "step": 280
    },
    {
      "epoch": 0.0056799819807468194,
      "grad_norm": 0.5738089680671692,
      "learning_rate": 9.22335682834317e-05,
      "loss": 1.6069,
      "step": 290
    },
    {
      "epoch": 0.005875843428358779,
      "grad_norm": 0.6677771210670471,
      "learning_rate": 8.511423770030617e-05,
      "loss": 1.6102,
      "step": 300
    },
    {
      "epoch": 0.005875843428358779,
      "eval_loss": 1.621539831161499,
      "eval_runtime": 849.3992,
      "eval_samples_per_second": 25.31,
      "eval_steps_per_second": 6.328,
      "step": 300
    },
    {
      "epoch": 0.0060717048759707385,
      "grad_norm": 0.42615145444869995,
      "learning_rate": 7.808204475323423e-05,
      "loss": 1.682,
      "step": 310
    },
    {
      "epoch": 0.0062675663235826976,
      "grad_norm": 0.4762561321258545,
      "learning_rate": 7.117124957938042e-05,
      "loss": 1.6215,
      "step": 320
    },
    {
      "epoch": 0.006463427771194657,
      "grad_norm": 0.5104791522026062,
      "learning_rate": 6.441552087816105e-05,
      "loss": 1.5619,
      "step": 330
    },
    {
      "epoch": 0.006659289218806617,
      "grad_norm": 0.575524091720581,
      "learning_rate": 5.784777188072502e-05,
      "loss": 1.6038,
      "step": 340
    },
    {
      "epoch": 0.006855150666418576,
      "grad_norm": 0.6795148849487305,
      "learning_rate": 5.150000000000002e-05,
      "loss": 1.6331,
      "step": 350
    },
    {
      "epoch": 0.006855150666418576,
      "eval_loss": 1.5960947275161743,
      "eval_runtime": 807.8208,
      "eval_samples_per_second": 26.612,
      "eval_steps_per_second": 6.654,
      "step": 350
    },
    {
      "epoch": 0.007051012114030535,
      "grad_norm": 0.4098166823387146,
      "learning_rate": 4.540313094251309e-05,
      "loss": 1.6492,
      "step": 360
    },
    {
      "epoch": 0.007246873561642494,
      "grad_norm": 0.47631141543388367,
      "learning_rate": 3.958686804145719e-05,
      "loss": 1.5605,
      "step": 370
    },
    {
      "epoch": 0.007442735009254454,
      "grad_norm": 0.5455722808837891,
      "learning_rate": 3.4079547545037634e-05,
      "loss": 1.5975,
      "step": 380
    },
    {
      "epoch": 0.007638596456866413,
      "grad_norm": 0.5428374409675598,
      "learning_rate": 2.8908000565118947e-05,
      "loss": 1.5256,
      "step": 390
    },
    {
      "epoch": 0.007834457904478372,
      "grad_norm": 0.7749019265174866,
      "learning_rate": 2.4097422358745275e-05,
      "loss": 1.5731,
      "step": 400
    },
    {
      "epoch": 0.007834457904478372,
      "eval_loss": 1.5720521211624146,
      "eval_runtime": 805.3716,
      "eval_samples_per_second": 26.693,
      "eval_steps_per_second": 6.674,
      "step": 400
    },
    {
      "epoch": 0.008030319352090332,
      "grad_norm": 0.4348071813583374,
      "learning_rate": 1.9671249579380422e-05,
      "loss": 1.6855,
      "step": 410
    },
    {
      "epoch": 0.00822618079970229,
      "grad_norm": 0.5242032408714294,
      "learning_rate": 1.5651046095888127e-05,
      "loss": 1.6195,
      "step": 420
    },
    {
      "epoch": 0.00842204224731425,
      "grad_norm": 0.5005368590354919,
      "learning_rate": 1.205639793553052e-05,
      "loss": 1.569,
      "step": 430
    },
    {
      "epoch": 0.00861790369492621,
      "grad_norm": 0.5892754793167114,
      "learning_rate": 8.904817862812098e-06,
      "loss": 1.5471,
      "step": 440
    },
    {
      "epoch": 0.008813765142538168,
      "grad_norm": 0.715459406375885,
      "learning_rate": 6.211660059051443e-06,
      "loss": 1.5927,
      "step": 450
    },
    {
      "epoch": 0.008813765142538168,
      "eval_loss": 1.5629593133926392,
      "eval_runtime": 809.2741,
      "eval_samples_per_second": 26.565,
      "eval_steps_per_second": 6.642,
      "step": 450
    },
    {
      "epoch": 0.009009626590150128,
      "grad_norm": 0.4325626492500305,
      "learning_rate": 3.990045318353154e-06,
      "loss": 1.6155,
      "step": 460
    },
    {
      "epoch": 0.009205488037762086,
      "grad_norm": 0.4722021222114563,
      "learning_rate": 2.250797124418014e-06,
      "loss": 1.5226,
      "step": 470
    },
    {
      "epoch": 0.009401349485374046,
      "grad_norm": 0.49364137649536133,
      "learning_rate": 1.0023889196182526e-06,
      "loss": 1.5093,
      "step": 480
    },
    {
      "epoch": 0.009597210932986006,
      "grad_norm": 0.5476292967796326,
      "learning_rate": 2.5090282323810766e-07,
      "loss": 1.5315,
      "step": 490
    },
    {
      "epoch": 0.009793072380597964,
      "grad_norm": 0.8033114075660706,
      "learning_rate": 0.0,
      "loss": 1.574,
      "step": 500
    },
    {
      "epoch": 0.009793072380597964,
      "eval_loss": 1.5615293979644775,
      "eval_runtime": 809.085,
      "eval_samples_per_second": 26.571,
      "eval_steps_per_second": 6.643,
      "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": 3.2862904541773824e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}