{
  "best_metric": 0.4173365831375122,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0784313725490196,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000784313725490196,
      "grad_norm": 13.154260635375977,
      "learning_rate": 7e-06,
      "loss": 4.2676,
      "step": 1
    },
    {
      "epoch": 0.000784313725490196,
      "eval_loss": 1.2241708040237427,
      "eval_runtime": 167.7852,
      "eval_samples_per_second": 12.802,
      "eval_steps_per_second": 3.201,
      "step": 1
    },
    {
      "epoch": 0.001568627450980392,
      "grad_norm": 15.154508590698242,
      "learning_rate": 1.4e-05,
      "loss": 2.7549,
      "step": 2
    },
    {
      "epoch": 0.002352941176470588,
      "grad_norm": 14.48685073852539,
      "learning_rate": 2.1e-05,
      "loss": 2.7878,
      "step": 3
    },
    {
      "epoch": 0.003137254901960784,
      "grad_norm": 13.144845008850098,
      "learning_rate": 2.8e-05,
      "loss": 2.3061,
      "step": 4
    },
    {
      "epoch": 0.00392156862745098,
      "grad_norm": 9.391257286071777,
      "learning_rate": 3.5e-05,
      "loss": 1.9517,
      "step": 5
    },
    {
      "epoch": 0.004705882352941176,
      "grad_norm": 8.726778984069824,
      "learning_rate": 4.2e-05,
      "loss": 2.1089,
      "step": 6
    },
    {
      "epoch": 0.005490196078431373,
      "grad_norm": 7.819472789764404,
      "learning_rate": 4.899999999999999e-05,
      "loss": 1.7353,
      "step": 7
    },
    {
      "epoch": 0.006274509803921568,
      "grad_norm": 7.163968086242676,
      "learning_rate": 5.6e-05,
      "loss": 1.7352,
      "step": 8
    },
    {
      "epoch": 0.007058823529411765,
      "grad_norm": 7.747889995574951,
      "learning_rate": 6.3e-05,
      "loss": 2.1403,
      "step": 9
    },
    {
      "epoch": 0.00784313725490196,
      "grad_norm": 7.355112075805664,
      "learning_rate": 7e-05,
      "loss": 1.7824,
      "step": 10
    },
    {
      "epoch": 0.008627450980392156,
      "grad_norm": 6.8065619468688965,
      "learning_rate": 6.999886445007847e-05,
      "loss": 1.7958,
      "step": 11
    },
    {
      "epoch": 0.009411764705882352,
      "grad_norm": 7.497786045074463,
      "learning_rate": 6.999545787399811e-05,
      "loss": 1.8139,
      "step": 12
    },
    {
      "epoch": 0.01019607843137255,
      "grad_norm": 8.02735710144043,
      "learning_rate": 6.998978049280675e-05,
      "loss": 1.7139,
      "step": 13
    },
    {
      "epoch": 0.010980392156862745,
      "grad_norm": 7.836209297180176,
      "learning_rate": 6.998183267490152e-05,
      "loss": 1.7008,
      "step": 14
    },
    {
      "epoch": 0.011764705882352941,
      "grad_norm": 6.723918914794922,
      "learning_rate": 6.997161493600493e-05,
      "loss": 1.5095,
      "step": 15
    },
    {
      "epoch": 0.012549019607843137,
      "grad_norm": 7.266279220581055,
      "learning_rate": 6.995912793913143e-05,
      "loss": 1.7114,
      "step": 16
    },
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 8.910981178283691,
      "learning_rate": 6.994437249454433e-05,
      "loss": 1.8847,
      "step": 17
    },
    {
      "epoch": 0.01411764705882353,
      "grad_norm": 7.561214923858643,
      "learning_rate": 6.992734955970331e-05,
      "loss": 1.4478,
      "step": 18
    },
    {
      "epoch": 0.014901960784313726,
      "grad_norm": 11.097957611083984,
      "learning_rate": 6.990806023920219e-05,
      "loss": 1.8268,
      "step": 19
    },
    {
      "epoch": 0.01568627450980392,
      "grad_norm": 8.547746658325195,
      "learning_rate": 6.988650578469734e-05,
      "loss": 1.9715,
      "step": 20
    },
    {
      "epoch": 0.01647058823529412,
      "grad_norm": 7.6952643394470215,
      "learning_rate": 6.986268759482644e-05,
      "loss": 1.3908,
      "step": 21
    },
    {
      "epoch": 0.017254901960784313,
      "grad_norm": 9.783441543579102,
      "learning_rate": 6.983660721511769e-05,
      "loss": 1.6528,
      "step": 22
    },
    {
      "epoch": 0.01803921568627451,
      "grad_norm": 8.756048202514648,
      "learning_rate": 6.980826633788956e-05,
      "loss": 1.3471,
      "step": 23
    },
    {
      "epoch": 0.018823529411764704,
      "grad_norm": 10.131261825561523,
      "learning_rate": 6.977766680214095e-05,
      "loss": 1.6056,
      "step": 24
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 9.784903526306152,
      "learning_rate": 6.974481059343188e-05,
      "loss": 1.349,
      "step": 25
    },
    {
      "epoch": 0.0203921568627451,
      "grad_norm": 10.655691146850586,
      "learning_rate": 6.970969984375466e-05,
      "loss": 1.0902,
      "step": 26
    },
    {
      "epoch": 0.021176470588235293,
      "grad_norm": 10.72864055633545,
      "learning_rate": 6.967233683139552e-05,
      "loss": 1.4288,
      "step": 27
    },
    {
      "epoch": 0.02196078431372549,
      "grad_norm": 7.463002681732178,
      "learning_rate": 6.963272398078678e-05,
      "loss": 1.0672,
      "step": 28
    },
    {
      "epoch": 0.022745098039215685,
      "grad_norm": 11.380589485168457,
      "learning_rate": 6.959086386234956e-05,
      "loss": 1.3336,
      "step": 29
    },
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 9.633968353271484,
      "learning_rate": 6.954675919232694e-05,
      "loss": 0.9633,
      "step": 30
    },
    {
      "epoch": 0.02431372549019608,
      "grad_norm": 8.88882827758789,
      "learning_rate": 6.950041283260778e-05,
      "loss": 1.0786,
      "step": 31
    },
    {
      "epoch": 0.025098039215686273,
      "grad_norm": 14.510672569274902,
      "learning_rate": 6.945182779054092e-05,
      "loss": 1.4122,
      "step": 32
    },
    {
      "epoch": 0.02588235294117647,
      "grad_norm": 15.632862091064453,
      "learning_rate": 6.940100721874013e-05,
      "loss": 2.0142,
      "step": 33
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 12.684489250183105,
      "learning_rate": 6.934795441487947e-05,
      "loss": 1.6836,
      "step": 34
    },
    {
      "epoch": 0.027450980392156862,
      "grad_norm": 13.649406433105469,
      "learning_rate": 6.929267282147936e-05,
      "loss": 1.7083,
      "step": 35
    },
    {
      "epoch": 0.02823529411764706,
      "grad_norm": 10.714078903198242,
      "learning_rate": 6.923516602568319e-05,
      "loss": 1.6407,
      "step": 36
    },
    {
      "epoch": 0.029019607843137254,
      "grad_norm": 10.981186866760254,
      "learning_rate": 6.917543775902452e-05,
      "loss": 1.483,
      "step": 37
    },
    {
      "epoch": 0.02980392156862745,
      "grad_norm": 12.960887908935547,
      "learning_rate": 6.911349189718497e-05,
      "loss": 1.7072,
      "step": 38
    },
    {
      "epoch": 0.03058823529411765,
      "grad_norm": 11.793508529663086,
      "learning_rate": 6.904933245974274e-05,
      "loss": 2.088,
      "step": 39
    },
    {
      "epoch": 0.03137254901960784,
      "grad_norm": 14.335042953491211,
      "learning_rate": 6.898296360991182e-05,
      "loss": 1.5573,
      "step": 40
    },
    {
      "epoch": 0.03215686274509804,
      "grad_norm": 19.681434631347656,
      "learning_rate": 6.891438965427172e-05,
      "loss": 1.7118,
      "step": 41
    },
    {
      "epoch": 0.03294117647058824,
      "grad_norm": 14.27527904510498,
      "learning_rate": 6.884361504248818e-05,
      "loss": 2.44,
      "step": 42
    },
    {
      "epoch": 0.03372549019607843,
      "grad_norm": 16.58424186706543,
      "learning_rate": 6.87706443670243e-05,
      "loss": 1.6355,
      "step": 43
    },
    {
      "epoch": 0.034509803921568626,
      "grad_norm": 20.70366096496582,
      "learning_rate": 6.869548236284267e-05,
      "loss": 2.2336,
      "step": 44
    },
    {
      "epoch": 0.03529411764705882,
      "grad_norm": 13.909195899963379,
      "learning_rate": 6.861813390709803e-05,
      "loss": 1.6299,
      "step": 45
    },
    {
      "epoch": 0.03607843137254902,
      "grad_norm": 18.837871551513672,
      "learning_rate": 6.853860401882081e-05,
      "loss": 2.6585,
      "step": 46
    },
    {
      "epoch": 0.03686274509803922,
      "grad_norm": 32.49602127075195,
      "learning_rate": 6.845689785859151e-05,
      "loss": 2.2312,
      "step": 47
    },
    {
      "epoch": 0.03764705882352941,
      "grad_norm": 22.12024688720703,
      "learning_rate": 6.837302072820576e-05,
      "loss": 2.5807,
      "step": 48
    },
    {
      "epoch": 0.038431372549019606,
      "grad_norm": 32.349609375,
      "learning_rate": 6.828697807033038e-05,
      "loss": 2.6884,
      "step": 49
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 38.483177185058594,
      "learning_rate": 6.819877546815009e-05,
      "loss": 3.4595,
      "step": 50
    },
    {
      "epoch": 0.04,
      "grad_norm": 11.971654891967773,
      "learning_rate": 6.810841864500537e-05,
      "loss": 3.9855,
      "step": 51
    },
    {
      "epoch": 0.0407843137254902,
      "grad_norm": 5.677441120147705,
      "learning_rate": 6.8015913464021e-05,
      "loss": 2.2597,
      "step": 52
    },
    {
      "epoch": 0.04156862745098039,
      "grad_norm": 3.608100652694702,
      "learning_rate": 6.79212659277256e-05,
      "loss": 1.8872,
      "step": 53
    },
    {
      "epoch": 0.042352941176470586,
      "grad_norm": 3.213096857070923,
      "learning_rate": 6.782448217766216e-05,
      "loss": 1.4016,
      "step": 54
    },
    {
      "epoch": 0.043137254901960784,
      "grad_norm": 4.3245744705200195,
      "learning_rate": 6.772556849398952e-05,
      "loss": 1.5969,
      "step": 55
    },
    {
      "epoch": 0.04392156862745098,
      "grad_norm": 4.572765350341797,
      "learning_rate": 6.762453129507487e-05,
      "loss": 1.5966,
      "step": 56
    },
    {
      "epoch": 0.04470588235294118,
      "grad_norm": 2.8827388286590576,
      "learning_rate": 6.752137713707726e-05,
      "loss": 1.0312,
      "step": 57
    },
    {
      "epoch": 0.04549019607843137,
      "grad_norm": 3.4303178787231445,
      "learning_rate": 6.741611271352217e-05,
      "loss": 1.3693,
      "step": 58
    },
    {
      "epoch": 0.04627450980392157,
      "grad_norm": 3.742342948913574,
      "learning_rate": 6.730874485486721e-05,
      "loss": 1.2792,
      "step": 59
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 3.946136713027954,
      "learning_rate": 6.719928052805884e-05,
      "loss": 1.4547,
      "step": 60
    },
    {
      "epoch": 0.04784313725490196,
      "grad_norm": 3.579709768295288,
      "learning_rate": 6.708772683608038e-05,
      "loss": 1.265,
      "step": 61
    },
    {
      "epoch": 0.04862745098039216,
      "grad_norm": 3.937344551086426,
      "learning_rate": 6.697409101749102e-05,
      "loss": 1.475,
      "step": 62
    },
    {
      "epoch": 0.04941176470588235,
      "grad_norm": 4.387577056884766,
      "learning_rate": 6.685838044595621e-05,
      "loss": 1.5258,
      "step": 63
    },
    {
      "epoch": 0.05019607843137255,
      "grad_norm": 5.537537574768066,
      "learning_rate": 6.674060262976909e-05,
      "loss": 1.426,
      "step": 64
    },
    {
      "epoch": 0.050980392156862744,
      "grad_norm": 4.949011325836182,
      "learning_rate": 6.662076521136337e-05,
      "loss": 1.6677,
      "step": 65
    },
    {
      "epoch": 0.05176470588235294,
      "grad_norm": 5.1415114402771,
      "learning_rate": 6.649887596681742e-05,
      "loss": 1.5576,
      "step": 66
    },
    {
      "epoch": 0.05254901960784314,
      "grad_norm": 4.477947235107422,
      "learning_rate": 6.637494280534962e-05,
      "loss": 1.4792,
      "step": 67
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 5.3575758934021,
      "learning_rate": 6.624897376880523e-05,
      "loss": 1.6056,
      "step": 68
    },
    {
      "epoch": 0.05411764705882353,
      "grad_norm": 5.173808574676514,
      "learning_rate": 6.612097703113452e-05,
      "loss": 1.1905,
      "step": 69
    },
    {
      "epoch": 0.054901960784313725,
      "grad_norm": 5.39131498336792,
      "learning_rate": 6.599096089786233e-05,
      "loss": 1.5183,
      "step": 70
    },
    {
      "epoch": 0.05568627450980392,
      "grad_norm": 6.076783180236816,
      "learning_rate": 6.585893380554929e-05,
      "loss": 1.0184,
      "step": 71
    },
    {
      "epoch": 0.05647058823529412,
      "grad_norm": 7.40262508392334,
      "learning_rate": 6.572490432124416e-05,
      "loss": 1.6043,
      "step": 72
    },
    {
      "epoch": 0.05725490196078432,
      "grad_norm": 6.334597587585449,
      "learning_rate": 6.558888114192812e-05,
      "loss": 1.3284,
      "step": 73
    },
    {
      "epoch": 0.05803921568627451,
      "grad_norm": 6.603546619415283,
      "learning_rate": 6.545087309395037e-05,
      "loss": 1.4609,
      "step": 74
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 10.423970222473145,
      "learning_rate": 6.531088913245535e-05,
      "loss": 1.5566,
      "step": 75
    },
    {
      "epoch": 0.0596078431372549,
      "grad_norm": 7.711127758026123,
      "learning_rate": 6.516893834080172e-05,
      "loss": 1.525,
      "step": 76
    },
    {
      "epoch": 0.0603921568627451,
      "grad_norm": 6.958899974822998,
      "learning_rate": 6.502502992997292e-05,
      "loss": 1.6027,
      "step": 77
    },
    {
      "epoch": 0.0611764705882353,
      "grad_norm": 8.05106258392334,
      "learning_rate": 6.487917323797953e-05,
      "loss": 1.5831,
      "step": 78
    },
    {
      "epoch": 0.06196078431372549,
      "grad_norm": 5.530167579650879,
      "learning_rate": 6.473137772925323e-05,
      "loss": 1.0131,
      "step": 79
    },
    {
      "epoch": 0.06274509803921569,
      "grad_norm": 6.529147624969482,
      "learning_rate": 6.458165299403281e-05,
      "loss": 1.026,
      "step": 80
    },
    {
      "epoch": 0.06352941176470588,
      "grad_norm": 4.573212623596191,
      "learning_rate": 6.443000874774177e-05,
      "loss": 0.6019,
      "step": 81
    },
    {
      "epoch": 0.06431372549019608,
      "grad_norm": 6.415572166442871,
      "learning_rate": 6.427645483035793e-05,
      "loss": 1.2427,
      "step": 82
    },
    {
      "epoch": 0.06509803921568627,
      "grad_norm": 12.587393760681152,
      "learning_rate": 6.412100120577495e-05,
      "loss": 0.8412,
      "step": 83
    },
    {
      "epoch": 0.06588235294117648,
      "grad_norm": 8.243964195251465,
      "learning_rate": 6.396365796115574e-05,
      "loss": 1.4314,
      "step": 84
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 10.298484802246094,
      "learning_rate": 6.380443530627796e-05,
      "loss": 1.471,
      "step": 85
    },
    {
      "epoch": 0.06745098039215686,
      "grad_norm": 7.470930099487305,
      "learning_rate": 6.364334357287154e-05,
      "loss": 1.6067,
      "step": 86
    },
    {
      "epoch": 0.06823529411764706,
      "grad_norm": 7.880890846252441,
      "learning_rate": 6.348039321394819e-05,
      "loss": 1.7093,
      "step": 87
    },
    {
      "epoch": 0.06901960784313725,
      "grad_norm": 8.50384521484375,
      "learning_rate": 6.331559480312315e-05,
      "loss": 1.5957,
      "step": 88
    },
    {
      "epoch": 0.06980392156862746,
      "grad_norm": 11.584599494934082,
      "learning_rate": 6.314895903392917e-05,
      "loss": 2.2822,
      "step": 89
    },
    {
      "epoch": 0.07058823529411765,
      "grad_norm": 8.506998062133789,
      "learning_rate": 6.298049671912254e-05,
      "loss": 1.3157,
      "step": 90
    },
    {
      "epoch": 0.07137254901960784,
      "grad_norm": 8.96076488494873,
      "learning_rate": 6.281021878998139e-05,
      "loss": 1.399,
      "step": 91
    },
    {
      "epoch": 0.07215686274509804,
      "grad_norm": 7.781743049621582,
      "learning_rate": 6.263813629559657e-05,
      "loss": 1.3365,
      "step": 92
    },
    {
      "epoch": 0.07294117647058823,
      "grad_norm": 11.301823616027832,
      "learning_rate": 6.246426040215451e-05,
      "loss": 1.931,
      "step": 93
    },
    {
      "epoch": 0.07372549019607844,
      "grad_norm": 14.643918991088867,
      "learning_rate": 6.228860239221277e-05,
      "loss": 1.949,
      "step": 94
    },
    {
      "epoch": 0.07450980392156863,
      "grad_norm": 12.800115585327148,
      "learning_rate": 6.21111736639679e-05,
      "loss": 1.9397,
      "step": 95
    },
    {
      "epoch": 0.07529411764705882,
      "grad_norm": 15.508123397827148,
      "learning_rate": 6.193198573051581e-05,
      "loss": 2.5479,
      "step": 96
    },
    {
      "epoch": 0.07607843137254902,
      "grad_norm": 22.137767791748047,
      "learning_rate": 6.175105021910468e-05,
      "loss": 2.0942,
      "step": 97
    },
    {
      "epoch": 0.07686274509803921,
      "grad_norm": 17.05497169494629,
      "learning_rate": 6.156837887038059e-05,
      "loss": 2.3568,
      "step": 98
    },
    {
      "epoch": 0.07764705882352942,
      "grad_norm": 18.51692771911621,
      "learning_rate": 6.138398353762557e-05,
      "loss": 2.4071,
      "step": 99
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 18.45566177368164,
      "learning_rate": 6.119787618598853e-05,
      "loss": 1.7988,
      "step": 100
    },
    {
      "epoch": 0.0784313725490196,
      "eval_loss": 0.4173365831375122,
      "eval_runtime": 169.3484,
      "eval_samples_per_second": 12.684,
      "eval_steps_per_second": 3.171,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": 1.513282097727406e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}