{
  "best_metric": 1.4315483570098877,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.14836795252225518,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000741839762611276,
      "grad_norm": 0.34722599387168884,
      "learning_rate": 1.0017e-05,
      "loss": 1.6873,
      "step": 1
    },
    {
      "epoch": 0.000741839762611276,
      "eval_loss": 1.8154631853103638,
      "eval_runtime": 24.6231,
      "eval_samples_per_second": 23.068,
      "eval_steps_per_second": 5.767,
      "step": 1
    },
    {
      "epoch": 0.001483679525222552,
      "grad_norm": 0.3773996829986572,
      "learning_rate": 2.0034e-05,
      "loss": 1.6132,
      "step": 2
    },
    {
      "epoch": 0.002225519287833828,
      "grad_norm": 0.3886512517929077,
      "learning_rate": 3.0050999999999997e-05,
      "loss": 1.7477,
      "step": 3
    },
    {
      "epoch": 0.002967359050445104,
      "grad_norm": 0.3726235628128052,
      "learning_rate": 4.0068e-05,
      "loss": 1.6803,
      "step": 4
    },
    {
      "epoch": 0.00370919881305638,
      "grad_norm": 0.41099005937576294,
      "learning_rate": 5.0085e-05,
      "loss": 1.7182,
      "step": 5
    },
    {
      "epoch": 0.004451038575667656,
      "grad_norm": 0.41989028453826904,
      "learning_rate": 6.0101999999999995e-05,
      "loss": 1.7672,
      "step": 6
    },
    {
      "epoch": 0.0051928783382789315,
      "grad_norm": 0.4218914806842804,
      "learning_rate": 7.0119e-05,
      "loss": 1.6714,
      "step": 7
    },
    {
      "epoch": 0.005934718100890208,
      "grad_norm": 0.40673041343688965,
      "learning_rate": 8.0136e-05,
      "loss": 1.7538,
      "step": 8
    },
    {
      "epoch": 0.0066765578635014835,
      "grad_norm": 0.40596580505371094,
      "learning_rate": 9.0153e-05,
      "loss": 1.6588,
      "step": 9
    },
    {
      "epoch": 0.00741839762611276,
      "grad_norm": 0.3768528997898102,
      "learning_rate": 0.00010017,
      "loss": 1.6586,
      "step": 10
    },
    {
      "epoch": 0.008160237388724036,
      "grad_norm": 0.37419360876083374,
      "learning_rate": 9.964278947368421e-05,
      "loss": 1.594,
      "step": 11
    },
    {
      "epoch": 0.008902077151335312,
      "grad_norm": 0.3967873156070709,
      "learning_rate": 9.911557894736841e-05,
      "loss": 1.6244,
      "step": 12
    },
    {
      "epoch": 0.009643916913946587,
      "grad_norm": 0.42619067430496216,
      "learning_rate": 9.858836842105263e-05,
      "loss": 1.5205,
      "step": 13
    },
    {
      "epoch": 0.010385756676557863,
      "grad_norm": 0.42936253547668457,
      "learning_rate": 9.806115789473684e-05,
      "loss": 1.5066,
      "step": 14
    },
    {
      "epoch": 0.01112759643916914,
      "grad_norm": 0.42404335737228394,
      "learning_rate": 9.753394736842106e-05,
      "loss": 1.6706,
      "step": 15
    },
    {
      "epoch": 0.011869436201780416,
      "grad_norm": 0.4178953468799591,
      "learning_rate": 9.700673684210526e-05,
      "loss": 1.6554,
      "step": 16
    },
    {
      "epoch": 0.012611275964391691,
      "grad_norm": 0.42441174387931824,
      "learning_rate": 9.647952631578948e-05,
      "loss": 1.6094,
      "step": 17
    },
    {
      "epoch": 0.013353115727002967,
      "grad_norm": 0.4085826277732849,
      "learning_rate": 9.595231578947368e-05,
      "loss": 1.8246,
      "step": 18
    },
    {
      "epoch": 0.014094955489614243,
      "grad_norm": 0.4366580843925476,
      "learning_rate": 9.542510526315789e-05,
      "loss": 1.7384,
      "step": 19
    },
    {
      "epoch": 0.01483679525222552,
      "grad_norm": 0.4653952419757843,
      "learning_rate": 9.48978947368421e-05,
      "loss": 1.8026,
      "step": 20
    },
    {
      "epoch": 0.015578635014836795,
      "grad_norm": 0.41364946961402893,
      "learning_rate": 9.437068421052632e-05,
      "loss": 1.4229,
      "step": 21
    },
    {
      "epoch": 0.016320474777448073,
      "grad_norm": 0.4450036883354187,
      "learning_rate": 9.384347368421052e-05,
      "loss": 1.5319,
      "step": 22
    },
    {
      "epoch": 0.017062314540059347,
      "grad_norm": 0.4304330348968506,
      "learning_rate": 9.331626315789474e-05,
      "loss": 1.5087,
      "step": 23
    },
    {
      "epoch": 0.017804154302670624,
      "grad_norm": 0.4402780830860138,
      "learning_rate": 9.278905263157894e-05,
      "loss": 1.527,
      "step": 24
    },
    {
      "epoch": 0.018545994065281898,
      "grad_norm": 0.5134778618812561,
      "learning_rate": 9.226184210526316e-05,
      "loss": 1.7225,
      "step": 25
    },
    {
      "epoch": 0.019287833827893175,
      "grad_norm": 0.44076353311538696,
      "learning_rate": 9.173463157894736e-05,
      "loss": 1.448,
      "step": 26
    },
    {
      "epoch": 0.020029673590504452,
      "grad_norm": 0.48980656266212463,
      "learning_rate": 9.120742105263159e-05,
      "loss": 1.6529,
      "step": 27
    },
    {
      "epoch": 0.020771513353115726,
      "grad_norm": 0.46377643942832947,
      "learning_rate": 9.068021052631579e-05,
      "loss": 1.4986,
      "step": 28
    },
    {
      "epoch": 0.021513353115727003,
      "grad_norm": 0.472007155418396,
      "learning_rate": 9.0153e-05,
      "loss": 1.7628,
      "step": 29
    },
    {
      "epoch": 0.02225519287833828,
      "grad_norm": 0.45802855491638184,
      "learning_rate": 8.96257894736842e-05,
      "loss": 1.6237,
      "step": 30
    },
    {
      "epoch": 0.022997032640949554,
      "grad_norm": 0.46878162026405334,
      "learning_rate": 8.909857894736842e-05,
      "loss": 1.6249,
      "step": 31
    },
    {
      "epoch": 0.02373887240356083,
      "grad_norm": 0.47090795636177063,
      "learning_rate": 8.857136842105263e-05,
      "loss": 1.5893,
      "step": 32
    },
    {
      "epoch": 0.024480712166172106,
      "grad_norm": 0.5051029920578003,
      "learning_rate": 8.804415789473684e-05,
      "loss": 1.5688,
      "step": 33
    },
    {
      "epoch": 0.025222551928783383,
      "grad_norm": 0.4550938606262207,
      "learning_rate": 8.751694736842105e-05,
      "loss": 1.4056,
      "step": 34
    },
    {
      "epoch": 0.02596439169139466,
      "grad_norm": 0.540347158908844,
      "learning_rate": 8.698973684210527e-05,
      "loss": 1.658,
      "step": 35
    },
    {
      "epoch": 0.026706231454005934,
      "grad_norm": 0.4885530173778534,
      "learning_rate": 8.646252631578948e-05,
      "loss": 1.4331,
      "step": 36
    },
    {
      "epoch": 0.02744807121661721,
      "grad_norm": 0.49800577759742737,
      "learning_rate": 8.593531578947368e-05,
      "loss": 1.3833,
      "step": 37
    },
    {
      "epoch": 0.028189910979228485,
      "grad_norm": 0.5188278555870056,
      "learning_rate": 8.54081052631579e-05,
      "loss": 1.5612,
      "step": 38
    },
    {
      "epoch": 0.028931750741839762,
      "grad_norm": 0.5572861433029175,
      "learning_rate": 8.48808947368421e-05,
      "loss": 1.6761,
      "step": 39
    },
    {
      "epoch": 0.02967359050445104,
      "grad_norm": 0.5264113545417786,
      "learning_rate": 8.435368421052631e-05,
      "loss": 1.3864,
      "step": 40
    },
    {
      "epoch": 0.030415430267062313,
      "grad_norm": 0.5517453551292419,
      "learning_rate": 8.382647368421053e-05,
      "loss": 1.5269,
      "step": 41
    },
    {
      "epoch": 0.03115727002967359,
      "grad_norm": 0.5187894105911255,
      "learning_rate": 8.329926315789474e-05,
      "loss": 1.4188,
      "step": 42
    },
    {
      "epoch": 0.031899109792284865,
      "grad_norm": 0.5830979943275452,
      "learning_rate": 8.277205263157894e-05,
      "loss": 1.7822,
      "step": 43
    },
    {
      "epoch": 0.032640949554896145,
      "grad_norm": 0.5921754837036133,
      "learning_rate": 8.224484210526316e-05,
      "loss": 1.5062,
      "step": 44
    },
    {
      "epoch": 0.03338278931750742,
      "grad_norm": 0.5693333148956299,
      "learning_rate": 8.171763157894736e-05,
      "loss": 1.5407,
      "step": 45
    },
    {
      "epoch": 0.03412462908011869,
      "grad_norm": 0.6015297770500183,
      "learning_rate": 8.119042105263158e-05,
      "loss": 1.5718,
      "step": 46
    },
    {
      "epoch": 0.034866468842729974,
      "grad_norm": 0.6420146226882935,
      "learning_rate": 8.066321052631578e-05,
      "loss": 1.6665,
      "step": 47
    },
    {
      "epoch": 0.03560830860534125,
      "grad_norm": 0.6055085062980652,
      "learning_rate": 8.0136e-05,
      "loss": 1.5059,
      "step": 48
    },
    {
      "epoch": 0.03635014836795252,
      "grad_norm": 0.7061499953269958,
      "learning_rate": 7.960878947368421e-05,
      "loss": 1.8428,
      "step": 49
    },
    {
      "epoch": 0.037091988130563795,
      "grad_norm": 0.7242527604103088,
      "learning_rate": 7.908157894736842e-05,
      "loss": 1.5827,
      "step": 50
    },
    {
      "epoch": 0.037091988130563795,
      "eval_loss": 1.5464621782302856,
      "eval_runtime": 24.5932,
      "eval_samples_per_second": 23.096,
      "eval_steps_per_second": 5.774,
      "step": 50
    },
    {
      "epoch": 0.037833827893175076,
      "grad_norm": 0.4841320216655731,
      "learning_rate": 7.855436842105262e-05,
      "loss": 1.4443,
      "step": 51
    },
    {
      "epoch": 0.03857566765578635,
      "grad_norm": 0.46595099568367004,
      "learning_rate": 7.802715789473684e-05,
      "loss": 1.4447,
      "step": 52
    },
    {
      "epoch": 0.039317507418397624,
      "grad_norm": 0.4743313491344452,
      "learning_rate": 7.749994736842104e-05,
      "loss": 1.4073,
      "step": 53
    },
    {
      "epoch": 0.040059347181008904,
      "grad_norm": 0.46219533681869507,
      "learning_rate": 7.697273684210526e-05,
      "loss": 1.4843,
      "step": 54
    },
    {
      "epoch": 0.04080118694362018,
      "grad_norm": 0.4498580992221832,
      "learning_rate": 7.644552631578947e-05,
      "loss": 1.3828,
      "step": 55
    },
    {
      "epoch": 0.04154302670623145,
      "grad_norm": 0.4310692250728607,
      "learning_rate": 7.591831578947369e-05,
      "loss": 1.5251,
      "step": 56
    },
    {
      "epoch": 0.04228486646884273,
      "grad_norm": 0.44536563754081726,
      "learning_rate": 7.539110526315789e-05,
      "loss": 1.5329,
      "step": 57
    },
    {
      "epoch": 0.04302670623145401,
      "grad_norm": 0.4388580620288849,
      "learning_rate": 7.48638947368421e-05,
      "loss": 1.4534,
      "step": 58
    },
    {
      "epoch": 0.04376854599406528,
      "grad_norm": 0.44389694929122925,
      "learning_rate": 7.433668421052632e-05,
      "loss": 1.6085,
      "step": 59
    },
    {
      "epoch": 0.04451038575667656,
      "grad_norm": 0.42019519209861755,
      "learning_rate": 7.380947368421052e-05,
      "loss": 1.3532,
      "step": 60
    },
    {
      "epoch": 0.045252225519287835,
      "grad_norm": 0.4290321469306946,
      "learning_rate": 7.328226315789473e-05,
      "loss": 1.4509,
      "step": 61
    },
    {
      "epoch": 0.04599406528189911,
      "grad_norm": 0.44131532311439514,
      "learning_rate": 7.275505263157895e-05,
      "loss": 1.4341,
      "step": 62
    },
    {
      "epoch": 0.04673590504451038,
      "grad_norm": 0.4584609866142273,
      "learning_rate": 7.222784210526316e-05,
      "loss": 1.4711,
      "step": 63
    },
    {
      "epoch": 0.04747774480712166,
      "grad_norm": 0.45380136370658875,
      "learning_rate": 7.170063157894737e-05,
      "loss": 1.5905,
      "step": 64
    },
    {
      "epoch": 0.04821958456973294,
      "grad_norm": 0.44095584750175476,
      "learning_rate": 7.117342105263158e-05,
      "loss": 1.3695,
      "step": 65
    },
    {
      "epoch": 0.04896142433234421,
      "grad_norm": 0.43939009308815,
      "learning_rate": 7.064621052631578e-05,
      "loss": 1.4743,
      "step": 66
    },
    {
      "epoch": 0.04970326409495549,
      "grad_norm": 0.44385743141174316,
      "learning_rate": 7.0119e-05,
      "loss": 1.3362,
      "step": 67
    },
    {
      "epoch": 0.050445103857566766,
      "grad_norm": 0.46653878688812256,
      "learning_rate": 6.959178947368421e-05,
      "loss": 1.353,
      "step": 68
    },
    {
      "epoch": 0.05118694362017804,
      "grad_norm": 0.49922919273376465,
      "learning_rate": 6.906457894736843e-05,
      "loss": 1.5815,
      "step": 69
    },
    {
      "epoch": 0.05192878338278932,
      "grad_norm": 0.48967719078063965,
      "learning_rate": 6.853736842105263e-05,
      "loss": 1.6117,
      "step": 70
    },
    {
      "epoch": 0.052670623145400594,
      "grad_norm": 0.5269822478294373,
      "learning_rate": 6.801015789473684e-05,
      "loss": 1.7096,
      "step": 71
    },
    {
      "epoch": 0.05341246290801187,
      "grad_norm": 0.5190030932426453,
      "learning_rate": 6.748294736842105e-05,
      "loss": 1.5746,
      "step": 72
    },
    {
      "epoch": 0.05415430267062315,
      "grad_norm": 0.5140092372894287,
      "learning_rate": 6.695573684210526e-05,
      "loss": 1.5915,
      "step": 73
    },
    {
      "epoch": 0.05489614243323442,
      "grad_norm": 0.5112202167510986,
      "learning_rate": 6.642852631578946e-05,
      "loss": 1.5368,
      "step": 74
    },
    {
      "epoch": 0.055637982195845696,
      "grad_norm": 0.45904073119163513,
      "learning_rate": 6.590131578947369e-05,
      "loss": 1.3563,
      "step": 75
    },
    {
      "epoch": 0.05637982195845697,
      "grad_norm": 0.4861205816268921,
      "learning_rate": 6.537410526315789e-05,
      "loss": 1.4552,
      "step": 76
    },
    {
      "epoch": 0.05712166172106825,
      "grad_norm": 0.5068615674972534,
      "learning_rate": 6.484689473684211e-05,
      "loss": 1.4687,
      "step": 77
    },
    {
      "epoch": 0.057863501483679525,
      "grad_norm": 0.49406206607818604,
      "learning_rate": 6.431968421052631e-05,
      "loss": 1.4759,
      "step": 78
    },
    {
      "epoch": 0.0586053412462908,
      "grad_norm": 0.4920863211154938,
      "learning_rate": 6.379247368421052e-05,
      "loss": 1.4521,
      "step": 79
    },
    {
      "epoch": 0.05934718100890208,
      "grad_norm": 0.5270341038703918,
      "learning_rate": 6.326526315789474e-05,
      "loss": 1.6008,
      "step": 80
    },
    {
      "epoch": 0.06008902077151335,
      "grad_norm": 0.5248571038246155,
      "learning_rate": 6.273805263157894e-05,
      "loss": 1.6934,
      "step": 81
    },
    {
      "epoch": 0.06083086053412463,
      "grad_norm": 0.519171416759491,
      "learning_rate": 6.221084210526315e-05,
      "loss": 1.5087,
      "step": 82
    },
    {
      "epoch": 0.06157270029673591,
      "grad_norm": 0.4932954013347626,
      "learning_rate": 6.168363157894737e-05,
      "loss": 1.3543,
      "step": 83
    },
    {
      "epoch": 0.06231454005934718,
      "grad_norm": 0.5216118097305298,
      "learning_rate": 6.115642105263159e-05,
      "loss": 1.4453,
      "step": 84
    },
    {
      "epoch": 0.06305637982195846,
      "grad_norm": 0.5293753147125244,
      "learning_rate": 6.0629210526315787e-05,
      "loss": 1.4051,
      "step": 85
    },
    {
      "epoch": 0.06379821958456973,
      "grad_norm": 0.5512006878852844,
      "learning_rate": 6.0101999999999995e-05,
      "loss": 1.4588,
      "step": 86
    },
    {
      "epoch": 0.064540059347181,
      "grad_norm": 0.5609034895896912,
      "learning_rate": 5.95747894736842e-05,
      "loss": 1.5523,
      "step": 87
    },
    {
      "epoch": 0.06528189910979229,
      "grad_norm": 0.6228796243667603,
      "learning_rate": 5.904757894736841e-05,
      "loss": 1.563,
      "step": 88
    },
    {
      "epoch": 0.06602373887240356,
      "grad_norm": 0.6174453496932983,
      "learning_rate": 5.852036842105263e-05,
      "loss": 1.6785,
      "step": 89
    },
    {
      "epoch": 0.06676557863501484,
      "grad_norm": 0.560930609703064,
      "learning_rate": 5.799315789473684e-05,
      "loss": 1.5602,
      "step": 90
    },
    {
      "epoch": 0.06750741839762611,
      "grad_norm": 0.5620979070663452,
      "learning_rate": 5.746594736842105e-05,
      "loss": 1.4652,
      "step": 91
    },
    {
      "epoch": 0.06824925816023739,
      "grad_norm": 0.5614945888519287,
      "learning_rate": 5.693873684210526e-05,
      "loss": 1.4533,
      "step": 92
    },
    {
      "epoch": 0.06899109792284866,
      "grad_norm": 0.6170912384986877,
      "learning_rate": 5.641152631578947e-05,
      "loss": 1.5405,
      "step": 93
    },
    {
      "epoch": 0.06973293768545995,
      "grad_norm": 0.6051465272903442,
      "learning_rate": 5.588431578947368e-05,
      "loss": 1.3788,
      "step": 94
    },
    {
      "epoch": 0.07047477744807122,
      "grad_norm": 0.612392008304596,
      "learning_rate": 5.5357105263157896e-05,
      "loss": 1.513,
      "step": 95
    },
    {
      "epoch": 0.0712166172106825,
      "grad_norm": 0.5922538638114929,
      "learning_rate": 5.482989473684211e-05,
      "loss": 1.6693,
      "step": 96
    },
    {
      "epoch": 0.07195845697329377,
      "grad_norm": 0.6305238604545593,
      "learning_rate": 5.430268421052632e-05,
      "loss": 1.5546,
      "step": 97
    },
    {
      "epoch": 0.07270029673590504,
      "grad_norm": 0.6214465498924255,
      "learning_rate": 5.377547368421053e-05,
      "loss": 1.4541,
      "step": 98
    },
    {
      "epoch": 0.07344213649851632,
      "grad_norm": 0.6209021806716919,
      "learning_rate": 5.3248263157894736e-05,
      "loss": 1.4974,
      "step": 99
    },
    {
      "epoch": 0.07418397626112759,
      "grad_norm": 0.7504584193229675,
      "learning_rate": 5.2721052631578944e-05,
      "loss": 1.7205,
      "step": 100
    },
    {
      "epoch": 0.07418397626112759,
      "eval_loss": 1.4849724769592285,
      "eval_runtime": 24.627,
      "eval_samples_per_second": 23.064,
      "eval_steps_per_second": 5.766,
      "step": 100
    },
    {
      "epoch": 0.07492581602373888,
      "grad_norm": 0.4530433416366577,
      "learning_rate": 5.219384210526315e-05,
      "loss": 1.514,
      "step": 101
    },
    {
      "epoch": 0.07566765578635015,
      "grad_norm": 0.4724753201007843,
      "learning_rate": 5.1666631578947374e-05,
      "loss": 1.4021,
      "step": 102
    },
    {
      "epoch": 0.07640949554896143,
      "grad_norm": 0.47871169447898865,
      "learning_rate": 5.113942105263158e-05,
      "loss": 1.5589,
      "step": 103
    },
    {
      "epoch": 0.0771513353115727,
      "grad_norm": 0.45524775981903076,
      "learning_rate": 5.061221052631579e-05,
      "loss": 1.3405,
      "step": 104
    },
    {
      "epoch": 0.07789317507418397,
      "grad_norm": 0.4814228415489197,
      "learning_rate": 5.0085e-05,
      "loss": 1.4676,
      "step": 105
    },
    {
      "epoch": 0.07863501483679525,
      "grad_norm": 0.4835189878940582,
      "learning_rate": 4.955778947368421e-05,
      "loss": 1.4522,
      "step": 106
    },
    {
      "epoch": 0.07937685459940653,
      "grad_norm": 0.4658392071723938,
      "learning_rate": 4.903057894736842e-05,
      "loss": 1.3801,
      "step": 107
    },
    {
      "epoch": 0.08011869436201781,
      "grad_norm": 0.47330623865127563,
      "learning_rate": 4.850336842105263e-05,
      "loss": 1.4066,
      "step": 108
    },
    {
      "epoch": 0.08086053412462908,
      "grad_norm": 0.46363088488578796,
      "learning_rate": 4.797615789473684e-05,
      "loss": 1.3805,
      "step": 109
    },
    {
      "epoch": 0.08160237388724036,
      "grad_norm": 0.4817906618118286,
      "learning_rate": 4.744894736842105e-05,
      "loss": 1.4796,
      "step": 110
    },
    {
      "epoch": 0.08234421364985163,
      "grad_norm": 0.4742972254753113,
      "learning_rate": 4.692173684210526e-05,
      "loss": 1.4028,
      "step": 111
    },
    {
      "epoch": 0.0830860534124629,
      "grad_norm": 0.4543997049331665,
      "learning_rate": 4.639452631578947e-05,
      "loss": 1.3328,
      "step": 112
    },
    {
      "epoch": 0.08382789317507418,
      "grad_norm": 0.4936276376247406,
      "learning_rate": 4.586731578947368e-05,
      "loss": 1.5478,
      "step": 113
    },
    {
      "epoch": 0.08456973293768547,
      "grad_norm": 0.48722100257873535,
      "learning_rate": 4.5340105263157894e-05,
      "loss": 1.3693,
      "step": 114
    },
    {
      "epoch": 0.08531157270029674,
      "grad_norm": 0.4936085641384125,
      "learning_rate": 4.48128947368421e-05,
      "loss": 1.4177,
      "step": 115
    },
    {
      "epoch": 0.08605341246290801,
      "grad_norm": 0.5257976055145264,
      "learning_rate": 4.428568421052632e-05,
      "loss": 1.4234,
      "step": 116
    },
    {
      "epoch": 0.08679525222551929,
      "grad_norm": 0.5145537853240967,
      "learning_rate": 4.3758473684210525e-05,
      "loss": 1.4445,
      "step": 117
    },
    {
      "epoch": 0.08753709198813056,
      "grad_norm": 0.5173904895782471,
      "learning_rate": 4.323126315789474e-05,
      "loss": 1.3109,
      "step": 118
    },
    {
      "epoch": 0.08827893175074183,
      "grad_norm": 0.5231949090957642,
      "learning_rate": 4.270405263157895e-05,
      "loss": 1.4202,
      "step": 119
    },
    {
      "epoch": 0.08902077151335312,
      "grad_norm": 0.5481486320495605,
      "learning_rate": 4.217684210526316e-05,
      "loss": 1.6027,
      "step": 120
    },
    {
      "epoch": 0.0897626112759644,
      "grad_norm": 0.5185007452964783,
      "learning_rate": 4.164963157894737e-05,
      "loss": 1.4227,
      "step": 121
    },
    {
      "epoch": 0.09050445103857567,
      "grad_norm": 0.5656704306602478,
      "learning_rate": 4.112242105263158e-05,
      "loss": 1.7125,
      "step": 122
    },
    {
      "epoch": 0.09124629080118694,
      "grad_norm": 0.5431631207466125,
      "learning_rate": 4.059521052631579e-05,
      "loss": 1.5132,
      "step": 123
    },
    {
      "epoch": 0.09198813056379822,
      "grad_norm": 0.5578521490097046,
      "learning_rate": 4.0068e-05,
      "loss": 1.4467,
      "step": 124
    },
    {
      "epoch": 0.09272997032640949,
      "grad_norm": 0.535007119178772,
      "learning_rate": 3.954078947368421e-05,
      "loss": 1.2726,
      "step": 125
    },
    {
      "epoch": 0.09347181008902077,
      "grad_norm": 0.5330731272697449,
      "learning_rate": 3.901357894736842e-05,
      "loss": 1.4208,
      "step": 126
    },
    {
      "epoch": 0.09421364985163205,
      "grad_norm": 0.567901611328125,
      "learning_rate": 3.848636842105263e-05,
      "loss": 1.3921,
      "step": 127
    },
    {
      "epoch": 0.09495548961424333,
      "grad_norm": 0.5680362582206726,
      "learning_rate": 3.795915789473684e-05,
      "loss": 1.3536,
      "step": 128
    },
    {
      "epoch": 0.0956973293768546,
      "grad_norm": 0.5580912828445435,
      "learning_rate": 3.743194736842105e-05,
      "loss": 1.3825,
      "step": 129
    },
    {
      "epoch": 0.09643916913946587,
      "grad_norm": 0.5955318808555603,
      "learning_rate": 3.690473684210526e-05,
      "loss": 1.5347,
      "step": 130
    },
    {
      "epoch": 0.09718100890207715,
      "grad_norm": 0.5580132007598877,
      "learning_rate": 3.6377526315789475e-05,
      "loss": 1.4045,
      "step": 131
    },
    {
      "epoch": 0.09792284866468842,
      "grad_norm": 0.6038758158683777,
      "learning_rate": 3.585031578947368e-05,
      "loss": 1.4749,
      "step": 132
    },
    {
      "epoch": 0.09866468842729971,
      "grad_norm": 0.5841488242149353,
      "learning_rate": 3.532310526315789e-05,
      "loss": 1.4079,
      "step": 133
    },
    {
      "epoch": 0.09940652818991098,
      "grad_norm": 0.5694416165351868,
      "learning_rate": 3.4795894736842106e-05,
      "loss": 1.483,
      "step": 134
    },
    {
      "epoch": 0.10014836795252226,
      "grad_norm": 0.6277908682823181,
      "learning_rate": 3.4268684210526314e-05,
      "loss": 1.42,
      "step": 135
    },
    {
      "epoch": 0.10089020771513353,
      "grad_norm": 0.6425288319587708,
      "learning_rate": 3.374147368421052e-05,
      "loss": 1.5528,
      "step": 136
    },
    {
      "epoch": 0.1016320474777448,
      "grad_norm": 0.5806187391281128,
      "learning_rate": 3.321426315789473e-05,
      "loss": 1.5093,
      "step": 137
    },
    {
      "epoch": 0.10237388724035608,
      "grad_norm": 0.6284953355789185,
      "learning_rate": 3.2687052631578946e-05,
      "loss": 1.3592,
      "step": 138
    },
    {
      "epoch": 0.10311572700296735,
      "grad_norm": 0.6375062465667725,
      "learning_rate": 3.2159842105263154e-05,
      "loss": 1.281,
      "step": 139
    },
    {
      "epoch": 0.10385756676557864,
      "grad_norm": 0.5946156978607178,
      "learning_rate": 3.163263157894737e-05,
      "loss": 1.2957,
      "step": 140
    },
    {
      "epoch": 0.10459940652818991,
      "grad_norm": 0.6250626444816589,
      "learning_rate": 3.110542105263158e-05,
      "loss": 1.455,
      "step": 141
    },
    {
      "epoch": 0.10534124629080119,
      "grad_norm": 0.6201031804084778,
      "learning_rate": 3.057821052631579e-05,
      "loss": 1.5049,
      "step": 142
    },
    {
      "epoch": 0.10608308605341246,
      "grad_norm": 0.6878780126571655,
      "learning_rate": 3.0050999999999997e-05,
      "loss": 1.4236,
      "step": 143
    },
    {
      "epoch": 0.10682492581602374,
      "grad_norm": 0.6680196523666382,
      "learning_rate": 2.9523789473684206e-05,
      "loss": 1.4347,
      "step": 144
    },
    {
      "epoch": 0.10756676557863501,
      "grad_norm": 0.7300444841384888,
      "learning_rate": 2.899657894736842e-05,
      "loss": 1.7655,
      "step": 145
    },
    {
      "epoch": 0.1083086053412463,
      "grad_norm": 0.7111066579818726,
      "learning_rate": 2.846936842105263e-05,
      "loss": 1.6347,
      "step": 146
    },
    {
      "epoch": 0.10905044510385757,
      "grad_norm": 0.663420557975769,
      "learning_rate": 2.794215789473684e-05,
      "loss": 1.345,
      "step": 147
    },
    {
      "epoch": 0.10979228486646884,
      "grad_norm": 0.7585017681121826,
      "learning_rate": 2.7414947368421056e-05,
      "loss": 1.4643,
      "step": 148
    },
    {
      "epoch": 0.11053412462908012,
      "grad_norm": 0.7578019499778748,
      "learning_rate": 2.6887736842105264e-05,
      "loss": 1.6194,
      "step": 149
    },
    {
      "epoch": 0.11127596439169139,
      "grad_norm": 0.8730563521385193,
      "learning_rate": 2.6360526315789472e-05,
      "loss": 1.6065,
      "step": 150
    },
    {
      "epoch": 0.11127596439169139,
      "eval_loss": 1.4480029344558716,
      "eval_runtime": 24.6337,
      "eval_samples_per_second": 23.058,
      "eval_steps_per_second": 5.764,
      "step": 150
    },
    {
      "epoch": 0.11201780415430267,
      "grad_norm": 0.4206100106239319,
      "learning_rate": 2.5833315789473687e-05,
      "loss": 1.1387,
      "step": 151
    },
    {
      "epoch": 0.11275964391691394,
      "grad_norm": 0.4989394247531891,
      "learning_rate": 2.5306105263157895e-05,
      "loss": 1.4917,
      "step": 152
    },
    {
      "epoch": 0.11350148367952523,
      "grad_norm": 0.5074396729469299,
      "learning_rate": 2.4778894736842104e-05,
      "loss": 1.686,
      "step": 153
    },
    {
      "epoch": 0.1142433234421365,
      "grad_norm": 0.5123466849327087,
      "learning_rate": 2.4251684210526315e-05,
      "loss": 1.3703,
      "step": 154
    },
    {
      "epoch": 0.11498516320474778,
      "grad_norm": 0.5191718935966492,
      "learning_rate": 2.3724473684210524e-05,
      "loss": 1.4312,
      "step": 155
    },
    {
      "epoch": 0.11572700296735905,
      "grad_norm": 0.47905129194259644,
      "learning_rate": 2.3197263157894735e-05,
      "loss": 1.4236,
      "step": 156
    },
    {
      "epoch": 0.11646884272997032,
      "grad_norm": 0.4941026270389557,
      "learning_rate": 2.2670052631578947e-05,
      "loss": 1.2631,
      "step": 157
    },
    {
      "epoch": 0.1172106824925816,
      "grad_norm": 0.5065926909446716,
      "learning_rate": 2.214284210526316e-05,
      "loss": 1.4134,
      "step": 158
    },
    {
      "epoch": 0.11795252225519288,
      "grad_norm": 0.5101008415222168,
      "learning_rate": 2.161563157894737e-05,
      "loss": 1.3647,
      "step": 159
    },
    {
      "epoch": 0.11869436201780416,
      "grad_norm": 0.5099448561668396,
      "learning_rate": 2.108842105263158e-05,
      "loss": 1.3093,
      "step": 160
    },
    {
      "epoch": 0.11943620178041543,
      "grad_norm": 0.5270506143569946,
      "learning_rate": 2.056121052631579e-05,
      "loss": 1.4776,
      "step": 161
    },
    {
      "epoch": 0.1201780415430267,
      "grad_norm": 0.519027829170227,
      "learning_rate": 2.0034e-05,
      "loss": 1.4011,
      "step": 162
    },
    {
      "epoch": 0.12091988130563798,
      "grad_norm": 0.520959734916687,
      "learning_rate": 1.950678947368421e-05,
      "loss": 1.3618,
      "step": 163
    },
    {
      "epoch": 0.12166172106824925,
      "grad_norm": 0.5643500685691833,
      "learning_rate": 1.897957894736842e-05,
      "loss": 1.5463,
      "step": 164
    },
    {
      "epoch": 0.12240356083086053,
      "grad_norm": 0.5543540716171265,
      "learning_rate": 1.845236842105263e-05,
      "loss": 1.3988,
      "step": 165
    },
    {
      "epoch": 0.12314540059347182,
      "grad_norm": 0.5814954042434692,
      "learning_rate": 1.792515789473684e-05,
      "loss": 1.5149,
      "step": 166
    },
    {
      "epoch": 0.12388724035608309,
      "grad_norm": 0.5395814180374146,
      "learning_rate": 1.7397947368421053e-05,
      "loss": 1.4446,
      "step": 167
    },
    {
      "epoch": 0.12462908011869436,
      "grad_norm": 0.5087323784828186,
      "learning_rate": 1.687073684210526e-05,
      "loss": 1.3358,
      "step": 168
    },
    {
      "epoch": 0.12537091988130564,
      "grad_norm": 0.5564747452735901,
      "learning_rate": 1.6343526315789473e-05,
      "loss": 1.416,
      "step": 169
    },
    {
      "epoch": 0.1261127596439169,
      "grad_norm": 0.5298991799354553,
      "learning_rate": 1.5816315789473685e-05,
      "loss": 1.3435,
      "step": 170
    },
    {
      "epoch": 0.12685459940652818,
      "grad_norm": 0.554205060005188,
      "learning_rate": 1.5289105263157896e-05,
      "loss": 1.4239,
      "step": 171
    },
    {
      "epoch": 0.12759643916913946,
      "grad_norm": 0.5437472462654114,
      "learning_rate": 1.4761894736842103e-05,
      "loss": 1.5082,
      "step": 172
    },
    {
      "epoch": 0.12833827893175073,
      "grad_norm": 0.5654957294464111,
      "learning_rate": 1.4234684210526314e-05,
      "loss": 1.4074,
      "step": 173
    },
    {
      "epoch": 0.129080118694362,
      "grad_norm": 0.5292185544967651,
      "learning_rate": 1.3707473684210528e-05,
      "loss": 1.4173,
      "step": 174
    },
    {
      "epoch": 0.1298219584569733,
      "grad_norm": 0.5802279114723206,
      "learning_rate": 1.3180263157894736e-05,
      "loss": 1.4608,
      "step": 175
    },
    {
      "epoch": 0.13056379821958458,
      "grad_norm": 0.5980931520462036,
      "learning_rate": 1.2653052631578948e-05,
      "loss": 1.6759,
      "step": 176
    },
    {
      "epoch": 0.13130563798219586,
      "grad_norm": 0.5813962817192078,
      "learning_rate": 1.2125842105263158e-05,
      "loss": 1.4882,
      "step": 177
    },
    {
      "epoch": 0.13204747774480713,
      "grad_norm": 0.6063507199287415,
      "learning_rate": 1.1598631578947368e-05,
      "loss": 1.518,
      "step": 178
    },
    {
      "epoch": 0.1327893175074184,
      "grad_norm": 0.5826941132545471,
      "learning_rate": 1.107142105263158e-05,
      "loss": 1.4704,
      "step": 179
    },
    {
      "epoch": 0.13353115727002968,
      "grad_norm": 0.6097956895828247,
      "learning_rate": 1.054421052631579e-05,
      "loss": 1.4025,
      "step": 180
    },
    {
      "epoch": 0.13427299703264095,
      "grad_norm": 0.6548146605491638,
      "learning_rate": 1.0017e-05,
      "loss": 1.548,
      "step": 181
    },
    {
      "epoch": 0.13501483679525222,
      "grad_norm": 0.663008987903595,
      "learning_rate": 9.48978947368421e-06,
      "loss": 1.764,
      "step": 182
    },
    {
      "epoch": 0.1357566765578635,
      "grad_norm": 0.5668148994445801,
      "learning_rate": 8.96257894736842e-06,
      "loss": 1.351,
      "step": 183
    },
    {
      "epoch": 0.13649851632047477,
      "grad_norm": 0.6421298384666443,
      "learning_rate": 8.43536842105263e-06,
      "loss": 1.4227,
      "step": 184
    },
    {
      "epoch": 0.13724035608308605,
      "grad_norm": 0.6036615967750549,
      "learning_rate": 7.908157894736842e-06,
      "loss": 1.3897,
      "step": 185
    },
    {
      "epoch": 0.13798219584569732,
      "grad_norm": 0.6182149052619934,
      "learning_rate": 7.380947368421051e-06,
      "loss": 1.7172,
      "step": 186
    },
    {
      "epoch": 0.1387240356083086,
      "grad_norm": 0.6109817624092102,
      "learning_rate": 6.853736842105264e-06,
      "loss": 1.4867,
      "step": 187
    },
    {
      "epoch": 0.1394658753709199,
      "grad_norm": 0.696526288986206,
      "learning_rate": 6.326526315789474e-06,
      "loss": 1.5992,
      "step": 188
    },
    {
      "epoch": 0.14020771513353117,
      "grad_norm": 0.6494670510292053,
      "learning_rate": 5.799315789473684e-06,
      "loss": 1.3784,
      "step": 189
    },
    {
      "epoch": 0.14094955489614244,
      "grad_norm": 0.6380143761634827,
      "learning_rate": 5.272105263157895e-06,
      "loss": 1.4366,
      "step": 190
    },
    {
      "epoch": 0.14169139465875372,
      "grad_norm": 0.6222284436225891,
      "learning_rate": 4.744894736842105e-06,
      "loss": 1.379,
      "step": 191
    },
    {
      "epoch": 0.142433234421365,
      "grad_norm": 0.6166477203369141,
      "learning_rate": 4.217684210526315e-06,
      "loss": 1.3242,
      "step": 192
    },
    {
      "epoch": 0.14317507418397626,
      "grad_norm": 0.7048677206039429,
      "learning_rate": 3.6904736842105257e-06,
      "loss": 1.5888,
      "step": 193
    },
    {
      "epoch": 0.14391691394658754,
      "grad_norm": 0.708202600479126,
      "learning_rate": 3.163263157894737e-06,
      "loss": 1.5138,
      "step": 194
    },
    {
      "epoch": 0.1446587537091988,
      "grad_norm": 0.6921345591545105,
      "learning_rate": 2.6360526315789473e-06,
      "loss": 1.2819,
      "step": 195
    },
    {
      "epoch": 0.14540059347181009,
      "grad_norm": 0.7002333998680115,
      "learning_rate": 2.1088421052631577e-06,
      "loss": 1.3984,
      "step": 196
    },
    {
      "epoch": 0.14614243323442136,
      "grad_norm": 0.7143130898475647,
      "learning_rate": 1.5816315789473685e-06,
      "loss": 1.5338,
      "step": 197
    },
    {
      "epoch": 0.14688427299703263,
      "grad_norm": 0.7665969133377075,
      "learning_rate": 1.0544210526315788e-06,
      "loss": 1.5382,
      "step": 198
    },
    {
      "epoch": 0.1476261127596439,
      "grad_norm": 0.8401339650154114,
      "learning_rate": 5.272105263157894e-07,
      "loss": 1.8398,
      "step": 199
    },
    {
      "epoch": 0.14836795252225518,
      "grad_norm": 0.8993075489997864,
      "learning_rate": 0.0,
      "loss": 1.6225,
      "step": 200
    },
    {
      "epoch": 0.14836795252225518,
      "eval_loss": 1.4315483570098877,
      "eval_runtime": 25.1319,
      "eval_samples_per_second": 22.601,
      "eval_steps_per_second": 5.65,
      "step": 200
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.65452005244928e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}