{
  "best_metric": 0.9393484592437744,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.26881720430107525,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002688172043010753,
      "grad_norm": 2.552518367767334,
      "learning_rate": 1.008e-05,
      "loss": 4.2159,
      "step": 1
    },
    {
      "epoch": 0.002688172043010753,
      "eval_loss": 2.7429797649383545,
      "eval_runtime": 20.0523,
      "eval_samples_per_second": 7.83,
      "eval_steps_per_second": 1.995,
      "step": 1
    },
    {
      "epoch": 0.005376344086021506,
      "grad_norm": 4.294527053833008,
      "learning_rate": 2.016e-05,
      "loss": 5.2935,
      "step": 2
    },
    {
      "epoch": 0.008064516129032258,
      "grad_norm": 3.8511745929718018,
      "learning_rate": 3.024e-05,
      "loss": 4.435,
      "step": 3
    },
    {
      "epoch": 0.010752688172043012,
      "grad_norm": 4.876188278198242,
      "learning_rate": 4.032e-05,
      "loss": 5.0044,
      "step": 4
    },
    {
      "epoch": 0.013440860215053764,
      "grad_norm": 4.7782392501831055,
      "learning_rate": 5.04e-05,
      "loss": 4.3481,
      "step": 5
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 4.02572774887085,
      "learning_rate": 6.048e-05,
      "loss": 3.9645,
      "step": 6
    },
    {
      "epoch": 0.01881720430107527,
      "grad_norm": 4.530522346496582,
      "learning_rate": 7.055999999999999e-05,
      "loss": 3.7968,
      "step": 7
    },
    {
      "epoch": 0.021505376344086023,
      "grad_norm": 3.8177340030670166,
      "learning_rate": 8.064e-05,
      "loss": 3.9752,
      "step": 8
    },
    {
      "epoch": 0.024193548387096774,
      "grad_norm": 3.42366361618042,
      "learning_rate": 9.072e-05,
      "loss": 3.7669,
      "step": 9
    },
    {
      "epoch": 0.026881720430107527,
      "grad_norm": 3.45857572555542,
      "learning_rate": 0.0001008,
      "loss": 3.1495,
      "step": 10
    },
    {
      "epoch": 0.02956989247311828,
      "grad_norm": 5.064671516418457,
      "learning_rate": 0.00010026947368421052,
      "loss": 2.8932,
      "step": 11
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 7.331480979919434,
      "learning_rate": 9.973894736842104e-05,
      "loss": 2.1098,
      "step": 12
    },
    {
      "epoch": 0.03494623655913978,
      "grad_norm": 6.972163677215576,
      "learning_rate": 9.920842105263157e-05,
      "loss": 3.326,
      "step": 13
    },
    {
      "epoch": 0.03763440860215054,
      "grad_norm": 4.03656005859375,
      "learning_rate": 9.86778947368421e-05,
      "loss": 2.4259,
      "step": 14
    },
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 6.760096073150635,
      "learning_rate": 9.814736842105264e-05,
      "loss": 1.9487,
      "step": 15
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": 4.662262439727783,
      "learning_rate": 9.761684210526316e-05,
      "loss": 2.489,
      "step": 16
    },
    {
      "epoch": 0.0456989247311828,
      "grad_norm": 5.427197456359863,
      "learning_rate": 9.708631578947368e-05,
      "loss": 2.9028,
      "step": 17
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 6.550124168395996,
      "learning_rate": 9.655578947368421e-05,
      "loss": 2.5639,
      "step": 18
    },
    {
      "epoch": 0.051075268817204304,
      "grad_norm": 5.742612361907959,
      "learning_rate": 9.602526315789473e-05,
      "loss": 1.5072,
      "step": 19
    },
    {
      "epoch": 0.053763440860215055,
      "grad_norm": 4.321170330047607,
      "learning_rate": 9.549473684210525e-05,
      "loss": 1.1754,
      "step": 20
    },
    {
      "epoch": 0.056451612903225805,
      "grad_norm": 3.095183849334717,
      "learning_rate": 9.496421052631579e-05,
      "loss": 1.5671,
      "step": 21
    },
    {
      "epoch": 0.05913978494623656,
      "grad_norm": 2.853109121322632,
      "learning_rate": 9.443368421052631e-05,
      "loss": 1.2742,
      "step": 22
    },
    {
      "epoch": 0.06182795698924731,
      "grad_norm": 3.149440050125122,
      "learning_rate": 9.390315789473683e-05,
      "loss": 2.0117,
      "step": 23
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 3.0655312538146973,
      "learning_rate": 9.337263157894737e-05,
      "loss": 2.2624,
      "step": 24
    },
    {
      "epoch": 0.06720430107526881,
      "grad_norm": 3.4676096439361572,
      "learning_rate": 9.28421052631579e-05,
      "loss": 2.3864,
      "step": 25
    },
    {
      "epoch": 0.06989247311827956,
      "grad_norm": 3.4489779472351074,
      "learning_rate": 9.231157894736842e-05,
      "loss": 1.5537,
      "step": 26
    },
    {
      "epoch": 0.07258064516129033,
      "grad_norm": 3.5075297355651855,
      "learning_rate": 9.178105263157895e-05,
      "loss": 1.6461,
      "step": 27
    },
    {
      "epoch": 0.07526881720430108,
      "grad_norm": 2.4398374557495117,
      "learning_rate": 9.125052631578948e-05,
      "loss": 1.4466,
      "step": 28
    },
    {
      "epoch": 0.07795698924731183,
      "grad_norm": 3.644092321395874,
      "learning_rate": 9.072e-05,
      "loss": 2.507,
      "step": 29
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 3.263528823852539,
      "learning_rate": 9.018947368421052e-05,
      "loss": 1.2544,
      "step": 30
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 3.7490763664245605,
      "learning_rate": 8.965894736842104e-05,
      "loss": 1.2655,
      "step": 31
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 3.2782695293426514,
      "learning_rate": 8.912842105263157e-05,
      "loss": 1.7594,
      "step": 32
    },
    {
      "epoch": 0.08870967741935484,
      "grad_norm": 2.6544880867004395,
      "learning_rate": 8.85978947368421e-05,
      "loss": 1.6763,
      "step": 33
    },
    {
      "epoch": 0.0913978494623656,
      "grad_norm": 2.461487054824829,
      "learning_rate": 8.806736842105264e-05,
      "loss": 1.4153,
      "step": 34
    },
    {
      "epoch": 0.09408602150537634,
      "grad_norm": 2.037763833999634,
      "learning_rate": 8.753684210526316e-05,
      "loss": 1.4954,
      "step": 35
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 2.2501564025878906,
      "learning_rate": 8.700631578947369e-05,
      "loss": 1.8277,
      "step": 36
    },
    {
      "epoch": 0.09946236559139784,
      "grad_norm": 2.666536331176758,
      "learning_rate": 8.647578947368421e-05,
      "loss": 2.2322,
      "step": 37
    },
    {
      "epoch": 0.10215053763440861,
      "grad_norm": 3.9293577671051025,
      "learning_rate": 8.594526315789473e-05,
      "loss": 2.394,
      "step": 38
    },
    {
      "epoch": 0.10483870967741936,
      "grad_norm": 5.047905921936035,
      "learning_rate": 8.541473684210525e-05,
      "loss": 2.2877,
      "step": 39
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 3.5374960899353027,
      "learning_rate": 8.488421052631578e-05,
      "loss": 1.552,
      "step": 40
    },
    {
      "epoch": 0.11021505376344086,
      "grad_norm": 4.972512722015381,
      "learning_rate": 8.435368421052631e-05,
      "loss": 2.5782,
      "step": 41
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 4.151662349700928,
      "learning_rate": 8.382315789473684e-05,
      "loss": 1.3923,
      "step": 42
    },
    {
      "epoch": 0.11559139784946236,
      "grad_norm": 3.7074525356292725,
      "learning_rate": 8.329263157894737e-05,
      "loss": 1.3753,
      "step": 43
    },
    {
      "epoch": 0.11827956989247312,
      "grad_norm": 3.257704973220825,
      "learning_rate": 8.27621052631579e-05,
      "loss": 1.5227,
      "step": 44
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 2.8200066089630127,
      "learning_rate": 8.223157894736842e-05,
      "loss": 1.0166,
      "step": 45
    },
    {
      "epoch": 0.12365591397849462,
      "grad_norm": 9.245245933532715,
      "learning_rate": 8.170105263157894e-05,
      "loss": 3.0691,
      "step": 46
    },
    {
      "epoch": 0.12634408602150538,
      "grad_norm": 6.105884075164795,
      "learning_rate": 8.117052631578946e-05,
      "loss": 2.7272,
      "step": 47
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 9.19589900970459,
      "learning_rate": 8.064e-05,
      "loss": 2.4159,
      "step": 48
    },
    {
      "epoch": 0.13172043010752688,
      "grad_norm": 6.029378890991211,
      "learning_rate": 8.010947368421052e-05,
      "loss": 1.4225,
      "step": 49
    },
    {
      "epoch": 0.13440860215053763,
      "grad_norm": 4.892293930053711,
      "learning_rate": 7.957894736842105e-05,
      "loss": 0.7743,
      "step": 50
    },
    {
      "epoch": 0.13440860215053763,
      "eval_loss": 1.1576098203659058,
      "eval_runtime": 20.0295,
      "eval_samples_per_second": 7.838,
      "eval_steps_per_second": 1.997,
      "step": 50
    },
    {
      "epoch": 0.13709677419354838,
      "grad_norm": 3.6493349075317383,
      "learning_rate": 7.904842105263158e-05,
      "loss": 3.4341,
      "step": 51
    },
    {
      "epoch": 0.13978494623655913,
      "grad_norm": 3.946737051010132,
      "learning_rate": 7.85178947368421e-05,
      "loss": 4.1712,
      "step": 52
    },
    {
      "epoch": 0.1424731182795699,
      "grad_norm": 3.0488572120666504,
      "learning_rate": 7.798736842105263e-05,
      "loss": 2.7678,
      "step": 53
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 2.641152858734131,
      "learning_rate": 7.745684210526315e-05,
      "loss": 3.4299,
      "step": 54
    },
    {
      "epoch": 0.1478494623655914,
      "grad_norm": 2.6064324378967285,
      "learning_rate": 7.692631578947369e-05,
      "loss": 2.8889,
      "step": 55
    },
    {
      "epoch": 0.15053763440860216,
      "grad_norm": 2.853044271469116,
      "learning_rate": 7.639578947368421e-05,
      "loss": 3.9092,
      "step": 56
    },
    {
      "epoch": 0.1532258064516129,
      "grad_norm": 3.7264606952667236,
      "learning_rate": 7.586526315789473e-05,
      "loss": 3.1663,
      "step": 57
    },
    {
      "epoch": 0.15591397849462366,
      "grad_norm": 2.3590335845947266,
      "learning_rate": 7.533473684210526e-05,
      "loss": 2.5423,
      "step": 58
    },
    {
      "epoch": 0.1586021505376344,
      "grad_norm": 3.6274800300598145,
      "learning_rate": 7.480421052631578e-05,
      "loss": 2.7857,
      "step": 59
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 3.466926097869873,
      "learning_rate": 7.427368421052632e-05,
      "loss": 2.1407,
      "step": 60
    },
    {
      "epoch": 0.1639784946236559,
      "grad_norm": 2.135305166244507,
      "learning_rate": 7.374315789473685e-05,
      "loss": 2.0501,
      "step": 61
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.145434617996216,
      "learning_rate": 7.321263157894737e-05,
      "loss": 1.8671,
      "step": 62
    },
    {
      "epoch": 0.1693548387096774,
      "grad_norm": 2.250318765640259,
      "learning_rate": 7.26821052631579e-05,
      "loss": 2.8158,
      "step": 63
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 2.0222816467285156,
      "learning_rate": 7.215157894736842e-05,
      "loss": 1.9672,
      "step": 64
    },
    {
      "epoch": 0.17473118279569894,
      "grad_norm": 2.0015830993652344,
      "learning_rate": 7.162105263157894e-05,
      "loss": 1.7105,
      "step": 65
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 2.1358511447906494,
      "learning_rate": 7.109052631578947e-05,
      "loss": 2.0722,
      "step": 66
    },
    {
      "epoch": 0.18010752688172044,
      "grad_norm": 2.1164755821228027,
      "learning_rate": 7.055999999999999e-05,
      "loss": 1.3778,
      "step": 67
    },
    {
      "epoch": 0.1827956989247312,
      "grad_norm": 2.6545348167419434,
      "learning_rate": 7.002947368421052e-05,
      "loss": 1.5793,
      "step": 68
    },
    {
      "epoch": 0.18548387096774194,
      "grad_norm": 2.278327703475952,
      "learning_rate": 6.949894736842105e-05,
      "loss": 1.3986,
      "step": 69
    },
    {
      "epoch": 0.1881720430107527,
      "grad_norm": 2.1539969444274902,
      "learning_rate": 6.896842105263158e-05,
      "loss": 0.8514,
      "step": 70
    },
    {
      "epoch": 0.19086021505376344,
      "grad_norm": 2.815715789794922,
      "learning_rate": 6.843789473684211e-05,
      "loss": 1.9194,
      "step": 71
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 1.7789136171340942,
      "learning_rate": 6.790736842105263e-05,
      "loss": 1.1168,
      "step": 72
    },
    {
      "epoch": 0.19623655913978494,
      "grad_norm": 2.7908670902252197,
      "learning_rate": 6.737684210526315e-05,
      "loss": 1.6579,
      "step": 73
    },
    {
      "epoch": 0.1989247311827957,
      "grad_norm": 3.0436408519744873,
      "learning_rate": 6.684631578947368e-05,
      "loss": 2.1317,
      "step": 74
    },
    {
      "epoch": 0.20161290322580644,
      "grad_norm": 2.6586692333221436,
      "learning_rate": 6.631578947368421e-05,
      "loss": 1.5078,
      "step": 75
    },
    {
      "epoch": 0.20430107526881722,
      "grad_norm": 2.3957104682922363,
      "learning_rate": 6.578526315789473e-05,
      "loss": 1.4137,
      "step": 76
    },
    {
      "epoch": 0.20698924731182797,
      "grad_norm": 2.467710256576538,
      "learning_rate": 6.525473684210526e-05,
      "loss": 1.5379,
      "step": 77
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 2.3089401721954346,
      "learning_rate": 6.47242105263158e-05,
      "loss": 1.3105,
      "step": 78
    },
    {
      "epoch": 0.21236559139784947,
      "grad_norm": 3.3448803424835205,
      "learning_rate": 6.419368421052632e-05,
      "loss": 2.9907,
      "step": 79
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 1.918912649154663,
      "learning_rate": 6.366315789473684e-05,
      "loss": 1.0538,
      "step": 80
    },
    {
      "epoch": 0.21774193548387097,
      "grad_norm": 2.1565945148468018,
      "learning_rate": 6.313263157894736e-05,
      "loss": 0.8427,
      "step": 81
    },
    {
      "epoch": 0.22043010752688172,
      "grad_norm": 1.9118677377700806,
      "learning_rate": 6.26021052631579e-05,
      "loss": 0.8702,
      "step": 82
    },
    {
      "epoch": 0.22311827956989247,
      "grad_norm": 2.161041498184204,
      "learning_rate": 6.207157894736842e-05,
      "loss": 1.5612,
      "step": 83
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 1.8799899816513062,
      "learning_rate": 6.154105263157894e-05,
      "loss": 1.0472,
      "step": 84
    },
    {
      "epoch": 0.22849462365591397,
      "grad_norm": 3.115447521209717,
      "learning_rate": 6.1010526315789474e-05,
      "loss": 1.3093,
      "step": 85
    },
    {
      "epoch": 0.23118279569892472,
      "grad_norm": 2.5335817337036133,
      "learning_rate": 6.048e-05,
      "loss": 1.5528,
      "step": 86
    },
    {
      "epoch": 0.23387096774193547,
      "grad_norm": 2.8771631717681885,
      "learning_rate": 5.994947368421052e-05,
      "loss": 1.6662,
      "step": 87
    },
    {
      "epoch": 0.23655913978494625,
      "grad_norm": 3.9417519569396973,
      "learning_rate": 5.941894736842104e-05,
      "loss": 1.8012,
      "step": 88
    },
    {
      "epoch": 0.239247311827957,
      "grad_norm": 3.2698731422424316,
      "learning_rate": 5.888842105263158e-05,
      "loss": 2.3075,
      "step": 89
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 2.6435606479644775,
      "learning_rate": 5.835789473684211e-05,
      "loss": 1.3781,
      "step": 90
    },
    {
      "epoch": 0.2446236559139785,
      "grad_norm": 3.099759817123413,
      "learning_rate": 5.782736842105263e-05,
      "loss": 2.1561,
      "step": 91
    },
    {
      "epoch": 0.24731182795698925,
      "grad_norm": 3.145350217819214,
      "learning_rate": 5.7296842105263154e-05,
      "loss": 1.4506,
      "step": 92
    },
    {
      "epoch": 0.25,
      "grad_norm": 4.324268341064453,
      "learning_rate": 5.676631578947368e-05,
      "loss": 0.9423,
      "step": 93
    },
    {
      "epoch": 0.25268817204301075,
      "grad_norm": 2.9348642826080322,
      "learning_rate": 5.623578947368421e-05,
      "loss": 1.7886,
      "step": 94
    },
    {
      "epoch": 0.2553763440860215,
      "grad_norm": 1.738901138305664,
      "learning_rate": 5.570526315789474e-05,
      "loss": 0.676,
      "step": 95
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 2.8710925579071045,
      "learning_rate": 5.5174736842105266e-05,
      "loss": 0.9851,
      "step": 96
    },
    {
      "epoch": 0.260752688172043,
      "grad_norm": 3.99045729637146,
      "learning_rate": 5.464421052631579e-05,
      "loss": 1.8844,
      "step": 97
    },
    {
      "epoch": 0.26344086021505375,
      "grad_norm": 4.602737903594971,
      "learning_rate": 5.411368421052631e-05,
      "loss": 1.3643,
      "step": 98
    },
    {
      "epoch": 0.2661290322580645,
      "grad_norm": 3.7166576385498047,
      "learning_rate": 5.358315789473684e-05,
      "loss": 0.6935,
      "step": 99
    },
    {
      "epoch": 0.26881720430107525,
      "grad_norm": 3.1870436668395996,
      "learning_rate": 5.3052631578947364e-05,
      "loss": 1.2186,
      "step": 100
    },
    {
      "epoch": 0.26881720430107525,
      "eval_loss": 0.9393484592437744,
      "eval_runtime": 20.0614,
      "eval_samples_per_second": 7.826,
      "eval_steps_per_second": 1.994,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.32627164790784e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}