{
  "best_metric": 0.13189151883125305,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.5437737901033171,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001087547580206634,
      "eval_loss": 2.6140365600585938,
      "eval_runtime": 22.7312,
      "eval_samples_per_second": 17.069,
      "eval_steps_per_second": 4.267,
      "step": 1
    },
    {
      "epoch": 0.010875475802066341,
      "grad_norm": 1.1718631982803345,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 0.6852,
      "step": 10
    },
    {
      "epoch": 0.021750951604132682,
      "grad_norm": 1.6259856224060059,
      "learning_rate": 8.080000000000001e-05,
      "loss": 0.6464,
      "step": 20
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 2.4112484455108643,
      "learning_rate": 0.00012119999999999999,
      "loss": 0.4593,
      "step": 30
    },
    {
      "epoch": 0.043501903208265365,
      "grad_norm": 6.566432476043701,
      "learning_rate": 0.00016160000000000002,
      "loss": 0.546,
      "step": 40
    },
    {
      "epoch": 0.054377379010331704,
      "grad_norm": 4.432110786437988,
      "learning_rate": 0.000202,
      "loss": 0.465,
      "step": 50
    },
    {
      "epoch": 0.054377379010331704,
      "eval_loss": 0.5987022519111633,
      "eval_runtime": 22.7609,
      "eval_samples_per_second": 17.047,
      "eval_steps_per_second": 4.262,
      "step": 50
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 1.1767598390579224,
      "learning_rate": 0.00020175396907624226,
      "loss": 0.2883,
      "step": 60
    },
    {
      "epoch": 0.07612833061446438,
      "grad_norm": 0.9557681679725647,
      "learning_rate": 0.0002010170749428986,
      "loss": 0.2687,
      "step": 70
    },
    {
      "epoch": 0.08700380641653073,
      "grad_norm": 2.2727346420288086,
      "learning_rate": 0.00019979290767411438,
      "loss": 0.2226,
      "step": 80
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 3.207522392272949,
      "learning_rate": 0.0001980874312897702,
      "loss": 0.2887,
      "step": 90
    },
    {
      "epoch": 0.10875475802066341,
      "grad_norm": 5.689190864562988,
      "learning_rate": 0.00019590895469937675,
      "loss": 0.4137,
      "step": 100
    },
    {
      "epoch": 0.10875475802066341,
      "eval_loss": 0.5496706366539001,
      "eval_runtime": 22.733,
      "eval_samples_per_second": 17.068,
      "eval_steps_per_second": 4.267,
      "step": 100
    },
    {
      "epoch": 0.11963023382272975,
      "grad_norm": 0.8785877227783203,
      "learning_rate": 0.0001932680912219027,
      "loss": 0.2831,
      "step": 110
    },
    {
      "epoch": 0.13050570962479607,
      "grad_norm": 0.8429152965545654,
      "learning_rate": 0.00019017770687875164,
      "loss": 0.1949,
      "step": 120
    },
    {
      "epoch": 0.14138118542686243,
      "grad_norm": 1.1005014181137085,
      "learning_rate": 0.000186652857711799,
      "loss": 0.1827,
      "step": 130
    },
    {
      "epoch": 0.15225666122892875,
      "grad_norm": 4.498092174530029,
      "learning_rate": 0.00018271071643186968,
      "loss": 3.1838,
      "step": 140
    },
    {
      "epoch": 0.1631321370309951,
      "grad_norm": 12.54207706451416,
      "learning_rate": 0.00017837048875501678,
      "loss": 0.2994,
      "step": 150
    },
    {
      "epoch": 0.1631321370309951,
      "eval_loss": 0.4509264826774597,
      "eval_runtime": 22.7489,
      "eval_samples_per_second": 17.056,
      "eval_steps_per_second": 4.264,
      "step": 150
    },
    {
      "epoch": 0.17400761283306146,
      "grad_norm": 0.6588810682296753,
      "learning_rate": 0.00017365331983420376,
      "loss": 0.2452,
      "step": 160
    },
    {
      "epoch": 0.18488308863512778,
      "grad_norm": 0.8176196813583374,
      "learning_rate": 0.0001685821912422447,
      "loss": 0.1395,
      "step": 170
    },
    {
      "epoch": 0.19575856443719414,
      "grad_norm": 1.6196659803390503,
      "learning_rate": 0.00016318180900789148,
      "loss": 0.1752,
      "step": 180
    },
    {
      "epoch": 0.20663404023926046,
      "grad_norm": 1.6988027095794678,
      "learning_rate": 0.00015747848325054544,
      "loss": 0.272,
      "step": 190
    },
    {
      "epoch": 0.21750951604132682,
      "grad_norm": 2.5128302574157715,
      "learning_rate": 0.0001515,
      "loss": 0.3535,
      "step": 200
    },
    {
      "epoch": 0.21750951604132682,
      "eval_loss": 0.2948015630245209,
      "eval_runtime": 22.7652,
      "eval_samples_per_second": 17.044,
      "eval_steps_per_second": 4.261,
      "step": 200
    },
    {
      "epoch": 0.22838499184339314,
      "grad_norm": 0.5956371426582336,
      "learning_rate": 0.00014527548582569683,
      "loss": 0.211,
      "step": 210
    },
    {
      "epoch": 0.2392604676454595,
      "grad_norm": 0.7749199867248535,
      "learning_rate": 0.00013883526593500714,
      "loss": 0.1476,
      "step": 220
    },
    {
      "epoch": 0.2501359434475258,
      "grad_norm": 0.8212958574295044,
      "learning_rate": 0.0001322107164318697,
      "loss": 0.1348,
      "step": 230
    },
    {
      "epoch": 0.26101141924959215,
      "grad_norm": 2.9552807807922363,
      "learning_rate": 0.00012543411145556643,
      "loss": 0.2418,
      "step": 240
    },
    {
      "epoch": 0.27188689505165853,
      "grad_norm": 5.775247097015381,
      "learning_rate": 0.00011853846594435998,
      "loss": 0.203,
      "step": 250
    },
    {
      "epoch": 0.27188689505165853,
      "eval_loss": 0.27232831716537476,
      "eval_runtime": 22.8141,
      "eval_samples_per_second": 17.007,
      "eval_steps_per_second": 4.252,
      "step": 250
    },
    {
      "epoch": 0.28276237085372485,
      "grad_norm": 0.527335524559021,
      "learning_rate": 0.00011155737479003301,
      "loss": 0.2042,
      "step": 260
    },
    {
      "epoch": 0.2936378466557912,
      "grad_norm": 0.4495840072631836,
      "learning_rate": 0.00010452484916695262,
      "loss": 0.1778,
      "step": 270
    },
    {
      "epoch": 0.3045133224578575,
      "grad_norm": 0.55239337682724,
      "learning_rate": 9.747515083304742e-05,
      "loss": 0.0975,
      "step": 280
    },
    {
      "epoch": 0.3153887982599239,
      "grad_norm": 2.169278144836426,
      "learning_rate": 9.044262520996702e-05,
      "loss": 0.2378,
      "step": 290
    },
    {
      "epoch": 0.3262642740619902,
      "grad_norm": 6.8742995262146,
      "learning_rate": 8.346153405564004e-05,
      "loss": 0.4967,
      "step": 300
    },
    {
      "epoch": 0.3262642740619902,
      "eval_loss": 0.24104903638362885,
      "eval_runtime": 22.7429,
      "eval_samples_per_second": 17.06,
      "eval_steps_per_second": 4.265,
      "step": 300
    },
    {
      "epoch": 0.33713974986405654,
      "grad_norm": 0.5075086355209351,
      "learning_rate": 7.656588854443357e-05,
      "loss": 0.1705,
      "step": 310
    },
    {
      "epoch": 0.3480152256661229,
      "grad_norm": 0.6775454878807068,
      "learning_rate": 6.978928356813031e-05,
      "loss": 0.1091,
      "step": 320
    },
    {
      "epoch": 0.35889070146818924,
      "grad_norm": 4.688424587249756,
      "learning_rate": 6.316473406499288e-05,
      "loss": 0.1494,
      "step": 330
    },
    {
      "epoch": 0.36976617727025557,
      "grad_norm": 7.4858808517456055,
      "learning_rate": 5.672451417430317e-05,
      "loss": 0.1966,
      "step": 340
    },
    {
      "epoch": 0.3806416530723219,
      "grad_norm": 5.136172771453857,
      "learning_rate": 5.050000000000002e-05,
      "loss": 0.232,
      "step": 350
    },
    {
      "epoch": 0.3806416530723219,
      "eval_loss": 0.20996609330177307,
      "eval_runtime": 23.069,
      "eval_samples_per_second": 16.819,
      "eval_steps_per_second": 4.205,
      "step": 350
    },
    {
      "epoch": 0.3915171288743883,
      "grad_norm": 0.5805565714836121,
      "learning_rate": 4.452151674945458e-05,
      "loss": 0.1389,
      "step": 360
    },
    {
      "epoch": 0.4023926046764546,
      "grad_norm": 1.093970775604248,
      "learning_rate": 3.8818190992108515e-05,
      "loss": 0.1285,
      "step": 370
    },
    {
      "epoch": 0.4132680804785209,
      "grad_norm": 0.5711682438850403,
      "learning_rate": 3.3417808757755355e-05,
      "loss": 0.109,
      "step": 380
    },
    {
      "epoch": 0.42414355628058725,
      "grad_norm": 1.3308712244033813,
      "learning_rate": 2.8346680165796253e-05,
      "loss": 0.1234,
      "step": 390
    },
    {
      "epoch": 0.43501903208265363,
      "grad_norm": 3.603949546813965,
      "learning_rate": 2.362951124498323e-05,
      "loss": 0.1905,
      "step": 400
    },
    {
      "epoch": 0.43501903208265363,
      "eval_loss": 0.1441967934370041,
      "eval_runtime": 22.5486,
      "eval_samples_per_second": 17.207,
      "eval_steps_per_second": 4.302,
      "step": 400
    },
    {
      "epoch": 0.44589450788471996,
      "grad_norm": 0.4847097098827362,
      "learning_rate": 1.928928356813032e-05,
      "loss": 0.1315,
      "step": 410
    },
    {
      "epoch": 0.4567699836867863,
      "grad_norm": 0.6296175122261047,
      "learning_rate": 1.5347142288200977e-05,
      "loss": 0.1213,
      "step": 420
    },
    {
      "epoch": 0.4676454594888526,
      "grad_norm": 1.3326748609542847,
      "learning_rate": 1.1822293121248375e-05,
      "loss": 0.1011,
      "step": 430
    },
    {
      "epoch": 0.478520935290919,
      "grad_norm": 0.9956807494163513,
      "learning_rate": 8.731908778097302e-06,
      "loss": 0.1667,
      "step": 440
    },
    {
      "epoch": 0.4893964110929853,
      "grad_norm": 1.1891385316848755,
      "learning_rate": 6.09104530062326e-06,
      "loss": 0.2123,
      "step": 450
    },
    {
      "epoch": 0.4893964110929853,
      "eval_loss": 0.13189151883125305,
      "eval_runtime": 22.5505,
      "eval_samples_per_second": 17.206,
      "eval_steps_per_second": 4.301,
      "step": 450
    },
    {
      "epoch": 0.5002718868950516,
      "grad_norm": 0.4370393455028534,
      "learning_rate": 3.912568710229791e-06,
      "loss": 0.1239,
      "step": 460
    },
    {
      "epoch": 0.511147362697118,
      "grad_norm": 0.5538854002952576,
      "learning_rate": 2.2070923258856255e-06,
      "loss": 0.0938,
      "step": 470
    },
    {
      "epoch": 0.5220228384991843,
      "grad_norm": 1.1034691333770752,
      "learning_rate": 9.829250571013935e-07,
      "loss": 0.1054,
      "step": 480
    },
    {
      "epoch": 0.5328983143012507,
      "grad_norm": 1.444915533065796,
      "learning_rate": 2.4603092375775605e-07,
      "loss": 0.1426,
      "step": 490
    },
    {
      "epoch": 0.5437737901033171,
      "grad_norm": 3.916834831237793,
      "learning_rate": 0.0,
      "loss": 0.2352,
      "step": 500
    },
    {
      "epoch": 0.5437737901033171,
      "eval_loss": 0.13204382359981537,
      "eval_runtime": 22.7776,
      "eval_samples_per_second": 17.034,
      "eval_steps_per_second": 4.259,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.002332739076096e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}