{
  "best_metric": 0.7244487404823303,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.8097165991902834,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008097165991902834,
      "grad_norm": 160.5043182373047,
      "learning_rate": 1e-06,
      "loss": 11.5445,
      "step": 1
    },
    {
      "epoch": 0.008097165991902834,
      "eval_loss": 11.895453453063965,
      "eval_runtime": 1.2561,
      "eval_samples_per_second": 41.398,
      "eval_steps_per_second": 10.349,
      "step": 1
    },
    {
      "epoch": 0.016194331983805668,
      "grad_norm": 113.18714904785156,
      "learning_rate": 2e-06,
      "loss": 12.2262,
      "step": 2
    },
    {
      "epoch": 0.024291497975708502,
      "grad_norm": 134.26119995117188,
      "learning_rate": 3e-06,
      "loss": 12.1703,
      "step": 3
    },
    {
      "epoch": 0.032388663967611336,
      "grad_norm": 151.49256896972656,
      "learning_rate": 4e-06,
      "loss": 11.2431,
      "step": 4
    },
    {
      "epoch": 0.04048582995951417,
      "grad_norm": 128.835205078125,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 12.309,
      "step": 5
    },
    {
      "epoch": 0.048582995951417005,
      "grad_norm": 126.78450012207031,
      "learning_rate": 6e-06,
      "loss": 12.4684,
      "step": 6
    },
    {
      "epoch": 0.05668016194331984,
      "grad_norm": 128.61981201171875,
      "learning_rate": 7e-06,
      "loss": 11.275,
      "step": 7
    },
    {
      "epoch": 0.06477732793522267,
      "grad_norm": 132.9573516845703,
      "learning_rate": 8e-06,
      "loss": 9.7015,
      "step": 8
    },
    {
      "epoch": 0.0728744939271255,
      "grad_norm": 114.10719299316406,
      "learning_rate": 9e-06,
      "loss": 8.4523,
      "step": 9
    },
    {
      "epoch": 0.08097165991902834,
      "grad_norm": 102.33385467529297,
      "learning_rate": 9.999999999999999e-06,
      "loss": 7.9721,
      "step": 10
    },
    {
      "epoch": 0.08906882591093117,
      "grad_norm": 85.0543212890625,
      "learning_rate": 1.1e-05,
      "loss": 6.5994,
      "step": 11
    },
    {
      "epoch": 0.09716599190283401,
      "grad_norm": 114.57733917236328,
      "learning_rate": 1.2e-05,
      "loss": 5.7194,
      "step": 12
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 84.9945297241211,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 4.7599,
      "step": 13
    },
    {
      "epoch": 0.11336032388663968,
      "grad_norm": 82.66494750976562,
      "learning_rate": 1.4e-05,
      "loss": 6.2553,
      "step": 14
    },
    {
      "epoch": 0.1214574898785425,
      "grad_norm": 66.0272445678711,
      "learning_rate": 1.5e-05,
      "loss": 3.5185,
      "step": 15
    },
    {
      "epoch": 0.12955465587044535,
      "grad_norm": 59.03416061401367,
      "learning_rate": 1.6e-05,
      "loss": 2.4052,
      "step": 16
    },
    {
      "epoch": 0.13765182186234817,
      "grad_norm": 60.23641586303711,
      "learning_rate": 1.7e-05,
      "loss": 2.7286,
      "step": 17
    },
    {
      "epoch": 0.145748987854251,
      "grad_norm": 37.41645431518555,
      "learning_rate": 1.8e-05,
      "loss": 2.7418,
      "step": 18
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 31.624427795410156,
      "learning_rate": 1.9e-05,
      "loss": 1.5455,
      "step": 19
    },
    {
      "epoch": 0.16194331983805668,
      "grad_norm": 33.63788986206055,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 2.2783,
      "step": 20
    },
    {
      "epoch": 0.1700404858299595,
      "grad_norm": 35.38190841674805,
      "learning_rate": 2.1e-05,
      "loss": 1.6235,
      "step": 21
    },
    {
      "epoch": 0.17813765182186234,
      "grad_norm": 46.83808135986328,
      "learning_rate": 2.2e-05,
      "loss": 1.8509,
      "step": 22
    },
    {
      "epoch": 0.1862348178137652,
      "grad_norm": 21.023977279663086,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.9755,
      "step": 23
    },
    {
      "epoch": 0.19433198380566802,
      "grad_norm": 34.79740905761719,
      "learning_rate": 2.4e-05,
      "loss": 0.9948,
      "step": 24
    },
    {
      "epoch": 0.20242914979757085,
      "grad_norm": 26.90549659729004,
      "learning_rate": 2.5e-05,
      "loss": 0.7971,
      "step": 25
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 30.40579605102539,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.1038,
      "step": 26
    },
    {
      "epoch": 0.21862348178137653,
      "grad_norm": 36.04926681518555,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.7739,
      "step": 27
    },
    {
      "epoch": 0.22672064777327935,
      "grad_norm": 35.41645050048828,
      "learning_rate": 2.8e-05,
      "loss": 1.3239,
      "step": 28
    },
    {
      "epoch": 0.23481781376518218,
      "grad_norm": 26.374845504760742,
      "learning_rate": 2.9e-05,
      "loss": 1.2692,
      "step": 29
    },
    {
      "epoch": 0.242914979757085,
      "grad_norm": 24.77640151977539,
      "learning_rate": 3e-05,
      "loss": 0.8267,
      "step": 30
    },
    {
      "epoch": 0.25101214574898784,
      "grad_norm": 27.26534652709961,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 0.8929,
      "step": 31
    },
    {
      "epoch": 0.2591093117408907,
      "grad_norm": 16.130844116210938,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.8517,
      "step": 32
    },
    {
      "epoch": 0.26720647773279355,
      "grad_norm": 18.54865074157715,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.7742,
      "step": 33
    },
    {
      "epoch": 0.27530364372469635,
      "grad_norm": 12.706560134887695,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.6831,
      "step": 34
    },
    {
      "epoch": 0.2834008097165992,
      "grad_norm": 12.227797508239746,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.749,
      "step": 35
    },
    {
      "epoch": 0.291497975708502,
      "grad_norm": 17.94428062438965,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.7489,
      "step": 36
    },
    {
      "epoch": 0.29959514170040485,
      "grad_norm": 12.291033744812012,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.6317,
      "step": 37
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 23.2242431640625,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.9003,
      "step": 38
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 15.302254676818848,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.6306,
      "step": 39
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 17.329072952270508,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 0.8858,
      "step": 40
    },
    {
      "epoch": 0.3319838056680162,
      "grad_norm": 11.782532691955566,
      "learning_rate": 2.820893297785107e-05,
      "loss": 0.7977,
      "step": 41
    },
    {
      "epoch": 0.340080971659919,
      "grad_norm": 10.306597709655762,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 0.6432,
      "step": 42
    },
    {
      "epoch": 0.3481781376518219,
      "grad_norm": 15.597854614257812,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.6245,
      "step": 43
    },
    {
      "epoch": 0.3562753036437247,
      "grad_norm": 13.594710350036621,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.7767,
      "step": 44
    },
    {
      "epoch": 0.3643724696356275,
      "grad_norm": 9.834576606750488,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.768,
      "step": 45
    },
    {
      "epoch": 0.3724696356275304,
      "grad_norm": 4.552821159362793,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.6271,
      "step": 46
    },
    {
      "epoch": 0.3805668016194332,
      "grad_norm": 9.330282211303711,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.7619,
      "step": 47
    },
    {
      "epoch": 0.38866396761133604,
      "grad_norm": 10.170756340026855,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 0.7114,
      "step": 48
    },
    {
      "epoch": 0.3967611336032389,
      "grad_norm": 7.350127696990967,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 0.7545,
      "step": 49
    },
    {
      "epoch": 0.4048582995951417,
      "grad_norm": 11.022176742553711,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 0.7612,
      "step": 50
    },
    {
      "epoch": 0.4048582995951417,
      "eval_loss": 0.7244487404823303,
      "eval_runtime": 1.2651,
      "eval_samples_per_second": 41.102,
      "eval_steps_per_second": 10.275,
      "step": 50
    },
    {
      "epoch": 0.41295546558704455,
      "grad_norm": 6.105991363525391,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 0.7112,
      "step": 51
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 5.9137163162231445,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 0.6772,
      "step": 52
    },
    {
      "epoch": 0.4291497975708502,
      "grad_norm": 6.709981918334961,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 0.7273,
      "step": 53
    },
    {
      "epoch": 0.43724696356275305,
      "grad_norm": 4.602910041809082,
      "learning_rate": 2.210802993709498e-05,
      "loss": 0.7377,
      "step": 54
    },
    {
      "epoch": 0.44534412955465585,
      "grad_norm": 8.946381568908691,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 0.6814,
      "step": 55
    },
    {
      "epoch": 0.4534412955465587,
      "grad_norm": 5.092156887054443,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 0.6879,
      "step": 56
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 4.789443016052246,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 0.6239,
      "step": 57
    },
    {
      "epoch": 0.46963562753036436,
      "grad_norm": 4.035036087036133,
      "learning_rate": 1.963525491562421e-05,
      "loss": 0.6038,
      "step": 58
    },
    {
      "epoch": 0.4777327935222672,
      "grad_norm": 4.545828819274902,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 0.7022,
      "step": 59
    },
    {
      "epoch": 0.48582995951417,
      "grad_norm": 6.806140899658203,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 0.7606,
      "step": 60
    },
    {
      "epoch": 0.4939271255060729,
      "grad_norm": 4.344721794128418,
      "learning_rate": 1.767835342197955e-05,
      "loss": 0.6619,
      "step": 61
    },
    {
      "epoch": 0.5020242914979757,
      "grad_norm": 5.1954345703125,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 0.6223,
      "step": 62
    },
    {
      "epoch": 0.5101214574898786,
      "grad_norm": 8.843324661254883,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 0.833,
      "step": 63
    },
    {
      "epoch": 0.5182186234817814,
      "grad_norm": 8.470301628112793,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 0.872,
      "step": 64
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 8.447321891784668,
      "learning_rate": 1.5e-05,
      "loss": 0.8794,
      "step": 65
    },
    {
      "epoch": 0.5344129554655871,
      "grad_norm": 7.982692241668701,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 0.8019,
      "step": 66
    },
    {
      "epoch": 0.5425101214574899,
      "grad_norm": 9.073297500610352,
      "learning_rate": 1.36554103664485e-05,
      "loss": 0.6302,
      "step": 67
    },
    {
      "epoch": 0.5506072874493927,
      "grad_norm": 4.642770767211914,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 0.6202,
      "step": 68
    },
    {
      "epoch": 0.5587044534412956,
      "grad_norm": 5.061112403869629,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 0.6198,
      "step": 69
    },
    {
      "epoch": 0.5668016194331984,
      "grad_norm": 7.011550426483154,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 0.8346,
      "step": 70
    },
    {
      "epoch": 0.5748987854251012,
      "grad_norm": 4.438355445861816,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 0.6787,
      "step": 71
    },
    {
      "epoch": 0.582995951417004,
      "grad_norm": 6.0901055335998535,
      "learning_rate": 1.036474508437579e-05,
      "loss": 0.8458,
      "step": 72
    },
    {
      "epoch": 0.5910931174089069,
      "grad_norm": 76.47030639648438,
      "learning_rate": 9.729377638779859e-06,
      "loss": 0.8839,
      "step": 73
    },
    {
      "epoch": 0.5991902834008097,
      "grad_norm": 6.974242687225342,
      "learning_rate": 9.104624525191147e-06,
      "loss": 0.733,
      "step": 74
    },
    {
      "epoch": 0.6072874493927125,
      "grad_norm": 7.109065055847168,
      "learning_rate": 8.491743913236629e-06,
      "loss": 0.8075,
      "step": 75
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 8.350259780883789,
      "learning_rate": 7.89197006290502e-06,
      "loss": 0.7467,
      "step": 76
    },
    {
      "epoch": 0.6234817813765182,
      "grad_norm": 5.253984451293945,
      "learning_rate": 7.30651083891141e-06,
      "loss": 0.7108,
      "step": 77
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 7.530630111694336,
      "learning_rate": 6.736545278218464e-06,
      "loss": 0.7081,
      "step": 78
    },
    {
      "epoch": 0.6396761133603239,
      "grad_norm": 18.218433380126953,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 0.6932,
      "step": 79
    },
    {
      "epoch": 0.6477732793522267,
      "grad_norm": 5.084344387054443,
      "learning_rate": 5.647652972118998e-06,
      "loss": 0.7684,
      "step": 80
    },
    {
      "epoch": 0.6558704453441295,
      "grad_norm": 4.171597480773926,
      "learning_rate": 5.130919110904311e-06,
      "loss": 0.7214,
      "step": 81
    },
    {
      "epoch": 0.6639676113360324,
      "grad_norm": 5.165872573852539,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 0.7379,
      "step": 82
    },
    {
      "epoch": 0.6720647773279352,
      "grad_norm": 8.189788818359375,
      "learning_rate": 4.158077042589129e-06,
      "loss": 0.8242,
      "step": 83
    },
    {
      "epoch": 0.680161943319838,
      "grad_norm": 5.687074661254883,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 0.6482,
      "step": 84
    },
    {
      "epoch": 0.6882591093117408,
      "grad_norm": 4.640507221221924,
      "learning_rate": 3.272527762979553e-06,
      "loss": 0.7058,
      "step": 85
    },
    {
      "epoch": 0.6963562753036437,
      "grad_norm": 4.909543514251709,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.6626,
      "step": 86
    },
    {
      "epoch": 0.7044534412955465,
      "grad_norm": 5.721399784088135,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 0.7401,
      "step": 87
    },
    {
      "epoch": 0.7125506072874493,
      "grad_norm": 4.203503131866455,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 0.7072,
      "step": 88
    },
    {
      "epoch": 0.7206477732793523,
      "grad_norm": 7.876823425292969,
      "learning_rate": 1.79106702214893e-06,
      "loss": 0.559,
      "step": 89
    },
    {
      "epoch": 0.728744939271255,
      "grad_norm": 9.562280654907227,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 0.7441,
      "step": 90
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 4.9196319580078125,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 0.6806,
      "step": 91
    },
    {
      "epoch": 0.7449392712550608,
      "grad_norm": 4.913059711456299,
      "learning_rate": 9.56476940403942e-07,
      "loss": 0.6895,
      "step": 92
    },
    {
      "epoch": 0.7530364372469636,
      "grad_norm": 6.508387088775635,
      "learning_rate": 7.341522555726971e-07,
      "loss": 0.7577,
      "step": 93
    },
    {
      "epoch": 0.7611336032388664,
      "grad_norm": 3.305694103240967,
      "learning_rate": 5.405570895622014e-07,
      "loss": 0.7149,
      "step": 94
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 6.714405536651611,
      "learning_rate": 3.760813172726457e-07,
      "loss": 0.7731,
      "step": 95
    },
    {
      "epoch": 0.7773279352226721,
      "grad_norm": 4.101876735687256,
      "learning_rate": 2.41056171020555e-07,
      "loss": 0.7061,
      "step": 96
    },
    {
      "epoch": 0.7854251012145749,
      "grad_norm": 3.9142746925354004,
      "learning_rate": 1.357535734809795e-07,
      "loss": 0.7258,
      "step": 97
    },
    {
      "epoch": 0.7935222672064778,
      "grad_norm": 3.286195993423462,
      "learning_rate": 6.038559007141397e-08,
      "loss": 0.7034,
      "step": 98
    },
    {
      "epoch": 0.8016194331983806,
      "grad_norm": 4.398167133331299,
      "learning_rate": 1.510400188028116e-08,
      "loss": 0.6205,
      "step": 99
    },
    {
      "epoch": 0.8097165991902834,
      "grad_norm": 4.571166515350342,
      "learning_rate": 0.0,
      "loss": 0.733,
      "step": 100
    },
    {
      "epoch": 0.8097165991902834,
      "eval_loss": 0.728439450263977,
      "eval_runtime": 1.266,
      "eval_samples_per_second": 41.075,
      "eval_steps_per_second": 10.269,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1932120607948800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}