{
  "best_metric": 0.5461220145225525,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0203190084323885,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001015950421619425,
      "grad_norm": 2.2005860805511475,
      "learning_rate": 1.001e-05,
      "loss": 0.646,
      "step": 1
    },
    {
      "epoch": 0.0001015950421619425,
      "eval_loss": 0.6843345165252686,
      "eval_runtime": 515.2648,
      "eval_samples_per_second": 8.044,
      "eval_steps_per_second": 2.013,
      "step": 1
    },
    {
      "epoch": 0.000203190084323885,
      "grad_norm": 2.192756175994873,
      "learning_rate": 2.002e-05,
      "loss": 0.7142,
      "step": 2
    },
    {
      "epoch": 0.00030478512648582747,
      "grad_norm": 2.6510324478149414,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 0.8049,
      "step": 3
    },
    {
      "epoch": 0.00040638016864777,
      "grad_norm": 2.7101404666900635,
      "learning_rate": 4.004e-05,
      "loss": 0.7722,
      "step": 4
    },
    {
      "epoch": 0.0005079752108097125,
      "grad_norm": 3.240100145339966,
      "learning_rate": 5.005e-05,
      "loss": 0.79,
      "step": 5
    },
    {
      "epoch": 0.0006095702529716549,
      "grad_norm": 3.555654525756836,
      "learning_rate": 6.005999999999999e-05,
      "loss": 1.065,
      "step": 6
    },
    {
      "epoch": 0.0007111652951335975,
      "grad_norm": 4.47487735748291,
      "learning_rate": 7.006999999999998e-05,
      "loss": 0.863,
      "step": 7
    },
    {
      "epoch": 0.00081276033729554,
      "grad_norm": 2.9086074829101562,
      "learning_rate": 8.008e-05,
      "loss": 0.9118,
      "step": 8
    },
    {
      "epoch": 0.0009143553794574825,
      "grad_norm": 3.0420775413513184,
      "learning_rate": 9.009e-05,
      "loss": 0.7969,
      "step": 9
    },
    {
      "epoch": 0.001015950421619425,
      "grad_norm": 3.648852825164795,
      "learning_rate": 0.0001001,
      "loss": 1.228,
      "step": 10
    },
    {
      "epoch": 0.0011175454637813674,
      "grad_norm": 3.1643669605255127,
      "learning_rate": 9.957315789473684e-05,
      "loss": 0.9534,
      "step": 11
    },
    {
      "epoch": 0.0012191405059433099,
      "grad_norm": 3.5377748012542725,
      "learning_rate": 9.904631578947367e-05,
      "loss": 0.9373,
      "step": 12
    },
    {
      "epoch": 0.0013207355481052526,
      "grad_norm": 3.505016565322876,
      "learning_rate": 9.851947368421052e-05,
      "loss": 1.179,
      "step": 13
    },
    {
      "epoch": 0.001422330590267195,
      "grad_norm": 3.4394781589508057,
      "learning_rate": 9.799263157894736e-05,
      "loss": 1.1948,
      "step": 14
    },
    {
      "epoch": 0.0015239256324291375,
      "grad_norm": 3.656883955001831,
      "learning_rate": 9.746578947368421e-05,
      "loss": 1.1357,
      "step": 15
    },
    {
      "epoch": 0.00162552067459108,
      "grad_norm": 4.39939546585083,
      "learning_rate": 9.693894736842104e-05,
      "loss": 1.2653,
      "step": 16
    },
    {
      "epoch": 0.0017271157167530224,
      "grad_norm": 3.9846978187561035,
      "learning_rate": 9.641210526315789e-05,
      "loss": 1.1856,
      "step": 17
    },
    {
      "epoch": 0.001828710758914965,
      "grad_norm": 3.4548585414886475,
      "learning_rate": 9.588526315789473e-05,
      "loss": 1.1261,
      "step": 18
    },
    {
      "epoch": 0.0019303058010769075,
      "grad_norm": 3.6354310512542725,
      "learning_rate": 9.535842105263157e-05,
      "loss": 1.0152,
      "step": 19
    },
    {
      "epoch": 0.00203190084323885,
      "grad_norm": 3.5814967155456543,
      "learning_rate": 9.483157894736841e-05,
      "loss": 1.1737,
      "step": 20
    },
    {
      "epoch": 0.0021334958854007926,
      "grad_norm": 3.7806692123413086,
      "learning_rate": 9.430473684210526e-05,
      "loss": 1.1642,
      "step": 21
    },
    {
      "epoch": 0.002235090927562735,
      "grad_norm": 3.724287509918213,
      "learning_rate": 9.37778947368421e-05,
      "loss": 1.2753,
      "step": 22
    },
    {
      "epoch": 0.0023366859697246775,
      "grad_norm": 3.3061375617980957,
      "learning_rate": 9.325105263157894e-05,
      "loss": 0.9576,
      "step": 23
    },
    {
      "epoch": 0.0024382810118866198,
      "grad_norm": 4.0224714279174805,
      "learning_rate": 9.272421052631578e-05,
      "loss": 1.28,
      "step": 24
    },
    {
      "epoch": 0.0025398760540485624,
      "grad_norm": 3.936861991882324,
      "learning_rate": 9.219736842105263e-05,
      "loss": 0.9267,
      "step": 25
    },
    {
      "epoch": 0.002641471096210505,
      "grad_norm": 4.16921854019165,
      "learning_rate": 9.167052631578946e-05,
      "loss": 1.2012,
      "step": 26
    },
    {
      "epoch": 0.0027430661383724473,
      "grad_norm": 3.989863157272339,
      "learning_rate": 9.114368421052632e-05,
      "loss": 1.2667,
      "step": 27
    },
    {
      "epoch": 0.00284466118053439,
      "grad_norm": 4.120609760284424,
      "learning_rate": 9.061684210526315e-05,
      "loss": 1.1629,
      "step": 28
    },
    {
      "epoch": 0.0029462562226963323,
      "grad_norm": 3.723917245864868,
      "learning_rate": 9.009e-05,
      "loss": 1.1301,
      "step": 29
    },
    {
      "epoch": 0.003047851264858275,
      "grad_norm": 4.069361686706543,
      "learning_rate": 8.956315789473683e-05,
      "loss": 1.1755,
      "step": 30
    },
    {
      "epoch": 0.0031494463070202176,
      "grad_norm": 3.857142925262451,
      "learning_rate": 8.903631578947368e-05,
      "loss": 1.1941,
      "step": 31
    },
    {
      "epoch": 0.00325104134918216,
      "grad_norm": 4.503450870513916,
      "learning_rate": 8.850947368421052e-05,
      "loss": 1.3796,
      "step": 32
    },
    {
      "epoch": 0.0033526363913441025,
      "grad_norm": 5.638123989105225,
      "learning_rate": 8.798263157894736e-05,
      "loss": 1.2541,
      "step": 33
    },
    {
      "epoch": 0.0034542314335060447,
      "grad_norm": 4.330247402191162,
      "learning_rate": 8.745578947368422e-05,
      "loss": 1.133,
      "step": 34
    },
    {
      "epoch": 0.0035558264756679874,
      "grad_norm": 5.019191741943359,
      "learning_rate": 8.692894736842105e-05,
      "loss": 1.5509,
      "step": 35
    },
    {
      "epoch": 0.00365742151782993,
      "grad_norm": 5.650910377502441,
      "learning_rate": 8.64021052631579e-05,
      "loss": 1.3531,
      "step": 36
    },
    {
      "epoch": 0.0037590165599918723,
      "grad_norm": 6.807903289794922,
      "learning_rate": 8.587526315789473e-05,
      "loss": 1.4887,
      "step": 37
    },
    {
      "epoch": 0.003860611602153815,
      "grad_norm": 5.474514484405518,
      "learning_rate": 8.534842105263157e-05,
      "loss": 1.1593,
      "step": 38
    },
    {
      "epoch": 0.003962206644315757,
      "grad_norm": 7.569794178009033,
      "learning_rate": 8.482157894736842e-05,
      "loss": 1.5063,
      "step": 39
    },
    {
      "epoch": 0.0040638016864777,
      "grad_norm": 6.703556060791016,
      "learning_rate": 8.429473684210525e-05,
      "loss": 1.2757,
      "step": 40
    },
    {
      "epoch": 0.004165396728639643,
      "grad_norm": 7.127315044403076,
      "learning_rate": 8.376789473684211e-05,
      "loss": 1.5994,
      "step": 41
    },
    {
      "epoch": 0.004266991770801585,
      "grad_norm": 7.127439975738525,
      "learning_rate": 8.324105263157894e-05,
      "loss": 1.5217,
      "step": 42
    },
    {
      "epoch": 0.004368586812963527,
      "grad_norm": 7.988884449005127,
      "learning_rate": 8.271421052631579e-05,
      "loss": 1.5936,
      "step": 43
    },
    {
      "epoch": 0.00447018185512547,
      "grad_norm": 6.814123153686523,
      "learning_rate": 8.218736842105262e-05,
      "loss": 1.3053,
      "step": 44
    },
    {
      "epoch": 0.004571776897287412,
      "grad_norm": 7.040807723999023,
      "learning_rate": 8.166052631578947e-05,
      "loss": 1.2787,
      "step": 45
    },
    {
      "epoch": 0.004673371939449355,
      "grad_norm": 7.2124834060668945,
      "learning_rate": 8.113368421052631e-05,
      "loss": 0.9922,
      "step": 46
    },
    {
      "epoch": 0.004774966981611298,
      "grad_norm": 11.030911445617676,
      "learning_rate": 8.060684210526315e-05,
      "loss": 1.3986,
      "step": 47
    },
    {
      "epoch": 0.0048765620237732395,
      "grad_norm": 10.35793685913086,
      "learning_rate": 8.008e-05,
      "loss": 1.0637,
      "step": 48
    },
    {
      "epoch": 0.004978157065935182,
      "grad_norm": 11.990375518798828,
      "learning_rate": 7.955315789473684e-05,
      "loss": 1.4477,
      "step": 49
    },
    {
      "epoch": 0.005079752108097125,
      "grad_norm": 15.286636352539062,
      "learning_rate": 7.902631578947368e-05,
      "loss": 2.0203,
      "step": 50
    },
    {
      "epoch": 0.005079752108097125,
      "eval_loss": 0.6280013918876648,
      "eval_runtime": 518.3017,
      "eval_samples_per_second": 7.997,
      "eval_steps_per_second": 2.001,
      "step": 50
    },
    {
      "epoch": 0.0051813471502590676,
      "grad_norm": 2.2037503719329834,
      "learning_rate": 7.849947368421052e-05,
      "loss": 0.6711,
      "step": 51
    },
    {
      "epoch": 0.00528294219242101,
      "grad_norm": 1.9842642545700073,
      "learning_rate": 7.797263157894736e-05,
      "loss": 0.6906,
      "step": 52
    },
    {
      "epoch": 0.005384537234582952,
      "grad_norm": 2.058812379837036,
      "learning_rate": 7.744578947368421e-05,
      "loss": 0.5586,
      "step": 53
    },
    {
      "epoch": 0.005486132276744895,
      "grad_norm": 2.2531464099884033,
      "learning_rate": 7.691894736842104e-05,
      "loss": 0.9127,
      "step": 54
    },
    {
      "epoch": 0.005587727318906837,
      "grad_norm": 2.2486493587493896,
      "learning_rate": 7.63921052631579e-05,
      "loss": 0.8567,
      "step": 55
    },
    {
      "epoch": 0.00568932236106878,
      "grad_norm": 2.560076951980591,
      "learning_rate": 7.586526315789473e-05,
      "loss": 0.8653,
      "step": 56
    },
    {
      "epoch": 0.005790917403230723,
      "grad_norm": 2.5297718048095703,
      "learning_rate": 7.533842105263158e-05,
      "loss": 0.8544,
      "step": 57
    },
    {
      "epoch": 0.0058925124453926645,
      "grad_norm": 2.6768887042999268,
      "learning_rate": 7.481157894736841e-05,
      "loss": 1.1578,
      "step": 58
    },
    {
      "epoch": 0.005994107487554607,
      "grad_norm": 2.5234925746917725,
      "learning_rate": 7.428473684210526e-05,
      "loss": 1.0016,
      "step": 59
    },
    {
      "epoch": 0.00609570252971655,
      "grad_norm": 2.62858247756958,
      "learning_rate": 7.375789473684209e-05,
      "loss": 1.0307,
      "step": 60
    },
    {
      "epoch": 0.0061972975718784925,
      "grad_norm": 2.6815719604492188,
      "learning_rate": 7.323105263157895e-05,
      "loss": 1.0425,
      "step": 61
    },
    {
      "epoch": 0.006298892614040435,
      "grad_norm": 2.671543836593628,
      "learning_rate": 7.270421052631578e-05,
      "loss": 0.9924,
      "step": 62
    },
    {
      "epoch": 0.006400487656202377,
      "grad_norm": 2.5434019565582275,
      "learning_rate": 7.217736842105263e-05,
      "loss": 0.962,
      "step": 63
    },
    {
      "epoch": 0.00650208269836432,
      "grad_norm": 3.021360397338867,
      "learning_rate": 7.165052631578947e-05,
      "loss": 1.1692,
      "step": 64
    },
    {
      "epoch": 0.006603677740526262,
      "grad_norm": 2.617884397506714,
      "learning_rate": 7.11236842105263e-05,
      "loss": 0.9373,
      "step": 65
    },
    {
      "epoch": 0.006705272782688205,
      "grad_norm": 2.834733247756958,
      "learning_rate": 7.059684210526315e-05,
      "loss": 1.0911,
      "step": 66
    },
    {
      "epoch": 0.006806867824850148,
      "grad_norm": 3.138725996017456,
      "learning_rate": 7.006999999999998e-05,
      "loss": 1.0814,
      "step": 67
    },
    {
      "epoch": 0.0069084628670120895,
      "grad_norm": 3.1022236347198486,
      "learning_rate": 6.954315789473684e-05,
      "loss": 1.2817,
      "step": 68
    },
    {
      "epoch": 0.007010057909174032,
      "grad_norm": 2.899486541748047,
      "learning_rate": 6.901631578947368e-05,
      "loss": 0.9868,
      "step": 69
    },
    {
      "epoch": 0.007111652951335975,
      "grad_norm": 3.156597137451172,
      "learning_rate": 6.848947368421052e-05,
      "loss": 1.0047,
      "step": 70
    },
    {
      "epoch": 0.0072132479934979175,
      "grad_norm": 3.3846867084503174,
      "learning_rate": 6.796263157894737e-05,
      "loss": 1.143,
      "step": 71
    },
    {
      "epoch": 0.00731484303565986,
      "grad_norm": 3.0827393531799316,
      "learning_rate": 6.74357894736842e-05,
      "loss": 1.1043,
      "step": 72
    },
    {
      "epoch": 0.007416438077821802,
      "grad_norm": 2.9473469257354736,
      "learning_rate": 6.690894736842105e-05,
      "loss": 1.074,
      "step": 73
    },
    {
      "epoch": 0.007518033119983745,
      "grad_norm": 3.0625174045562744,
      "learning_rate": 6.638210526315788e-05,
      "loss": 1.0141,
      "step": 74
    },
    {
      "epoch": 0.007619628162145687,
      "grad_norm": 3.610325813293457,
      "learning_rate": 6.585526315789474e-05,
      "loss": 1.2885,
      "step": 75
    },
    {
      "epoch": 0.00772122320430763,
      "grad_norm": 3.014136791229248,
      "learning_rate": 6.532842105263157e-05,
      "loss": 0.9769,
      "step": 76
    },
    {
      "epoch": 0.007822818246469573,
      "grad_norm": 3.436788558959961,
      "learning_rate": 6.480157894736842e-05,
      "loss": 1.1911,
      "step": 77
    },
    {
      "epoch": 0.007924413288631514,
      "grad_norm": 3.2950663566589355,
      "learning_rate": 6.427473684210526e-05,
      "loss": 1.2536,
      "step": 78
    },
    {
      "epoch": 0.008026008330793458,
      "grad_norm": 3.095257043838501,
      "learning_rate": 6.37478947368421e-05,
      "loss": 1.0352,
      "step": 79
    },
    {
      "epoch": 0.0081276033729554,
      "grad_norm": 3.387840509414673,
      "learning_rate": 6.322105263157894e-05,
      "loss": 1.1025,
      "step": 80
    },
    {
      "epoch": 0.008229198415117342,
      "grad_norm": 3.795701503753662,
      "learning_rate": 6.269421052631577e-05,
      "loss": 1.1707,
      "step": 81
    },
    {
      "epoch": 0.008330793457279285,
      "grad_norm": 3.4337081909179688,
      "learning_rate": 6.216736842105263e-05,
      "loss": 0.9816,
      "step": 82
    },
    {
      "epoch": 0.008432388499441227,
      "grad_norm": 3.789355754852295,
      "learning_rate": 6.164052631578947e-05,
      "loss": 1.3528,
      "step": 83
    },
    {
      "epoch": 0.00853398354160317,
      "grad_norm": 4.3252434730529785,
      "learning_rate": 6.111368421052631e-05,
      "loss": 1.3132,
      "step": 84
    },
    {
      "epoch": 0.008635578583765112,
      "grad_norm": 3.853529214859009,
      "learning_rate": 6.058684210526315e-05,
      "loss": 1.0348,
      "step": 85
    },
    {
      "epoch": 0.008737173625927054,
      "grad_norm": 4.666858673095703,
      "learning_rate": 6.005999999999999e-05,
      "loss": 1.0574,
      "step": 86
    },
    {
      "epoch": 0.008838768668088998,
      "grad_norm": 3.7602200508117676,
      "learning_rate": 5.953315789473684e-05,
      "loss": 1.2996,
      "step": 87
    },
    {
      "epoch": 0.00894036371025094,
      "grad_norm": 4.555033206939697,
      "learning_rate": 5.9006315789473676e-05,
      "loss": 1.4222,
      "step": 88
    },
    {
      "epoch": 0.009041958752412883,
      "grad_norm": 4.328731060028076,
      "learning_rate": 5.847947368421053e-05,
      "loss": 1.1422,
      "step": 89
    },
    {
      "epoch": 0.009143553794574825,
      "grad_norm": 4.52231502532959,
      "learning_rate": 5.795263157894737e-05,
      "loss": 1.3654,
      "step": 90
    },
    {
      "epoch": 0.009245148836736767,
      "grad_norm": 5.197935104370117,
      "learning_rate": 5.742578947368421e-05,
      "loss": 1.2897,
      "step": 91
    },
    {
      "epoch": 0.00934674387889871,
      "grad_norm": 5.237155914306641,
      "learning_rate": 5.6898947368421046e-05,
      "loss": 1.4891,
      "step": 92
    },
    {
      "epoch": 0.009448338921060652,
      "grad_norm": 5.300315856933594,
      "learning_rate": 5.6372105263157886e-05,
      "loss": 1.2487,
      "step": 93
    },
    {
      "epoch": 0.009549933963222595,
      "grad_norm": 5.781769752502441,
      "learning_rate": 5.584526315789473e-05,
      "loss": 1.1509,
      "step": 94
    },
    {
      "epoch": 0.009651529005384537,
      "grad_norm": 6.380777359008789,
      "learning_rate": 5.531842105263158e-05,
      "loss": 1.4483,
      "step": 95
    },
    {
      "epoch": 0.009753124047546479,
      "grad_norm": 7.0414204597473145,
      "learning_rate": 5.4791578947368424e-05,
      "loss": 1.4183,
      "step": 96
    },
    {
      "epoch": 0.009854719089708423,
      "grad_norm": 6.7459635734558105,
      "learning_rate": 5.426473684210526e-05,
      "loss": 1.2053,
      "step": 97
    },
    {
      "epoch": 0.009956314131870364,
      "grad_norm": 8.890039443969727,
      "learning_rate": 5.37378947368421e-05,
      "loss": 1.4122,
      "step": 98
    },
    {
      "epoch": 0.010057909174032308,
      "grad_norm": 7.953348636627197,
      "learning_rate": 5.321105263157894e-05,
      "loss": 0.6997,
      "step": 99
    },
    {
      "epoch": 0.01015950421619425,
      "grad_norm": 8.372994422912598,
      "learning_rate": 5.268421052631578e-05,
      "loss": 0.9565,
      "step": 100
    },
    {
      "epoch": 0.01015950421619425,
      "eval_loss": 0.5977502465248108,
      "eval_runtime": 519.035,
      "eval_samples_per_second": 7.986,
      "eval_steps_per_second": 1.998,
      "step": 100
    },
    {
      "epoch": 0.010261099258356192,
      "grad_norm": 1.7353254556655884,
      "learning_rate": 5.2157368421052626e-05,
      "loss": 0.6462,
      "step": 101
    },
    {
      "epoch": 0.010362694300518135,
      "grad_norm": 1.8115421533584595,
      "learning_rate": 5.163052631578947e-05,
      "loss": 0.7568,
      "step": 102
    },
    {
      "epoch": 0.010464289342680077,
      "grad_norm": 2.0411505699157715,
      "learning_rate": 5.110368421052632e-05,
      "loss": 0.8423,
      "step": 103
    },
    {
      "epoch": 0.01056588438484202,
      "grad_norm": 1.840236783027649,
      "learning_rate": 5.057684210526316e-05,
      "loss": 0.6614,
      "step": 104
    },
    {
      "epoch": 0.010667479427003962,
      "grad_norm": 2.0278501510620117,
      "learning_rate": 5.005e-05,
      "loss": 0.9404,
      "step": 105
    },
    {
      "epoch": 0.010769074469165904,
      "grad_norm": 2.038224935531616,
      "learning_rate": 4.9523157894736836e-05,
      "loss": 0.7997,
      "step": 106
    },
    {
      "epoch": 0.010870669511327848,
      "grad_norm": 1.961540937423706,
      "learning_rate": 4.899631578947368e-05,
      "loss": 0.88,
      "step": 107
    },
    {
      "epoch": 0.01097226455348979,
      "grad_norm": 1.8542038202285767,
      "learning_rate": 4.846947368421052e-05,
      "loss": 0.7586,
      "step": 108
    },
    {
      "epoch": 0.011073859595651733,
      "grad_norm": 2.5004920959472656,
      "learning_rate": 4.794263157894737e-05,
      "loss": 1.1421,
      "step": 109
    },
    {
      "epoch": 0.011175454637813675,
      "grad_norm": 2.2767207622528076,
      "learning_rate": 4.7415789473684206e-05,
      "loss": 0.8825,
      "step": 110
    },
    {
      "epoch": 0.011277049679975617,
      "grad_norm": 2.6416478157043457,
      "learning_rate": 4.688894736842105e-05,
      "loss": 1.0648,
      "step": 111
    },
    {
      "epoch": 0.01137864472213756,
      "grad_norm": 2.6188547611236572,
      "learning_rate": 4.636210526315789e-05,
      "loss": 1.0757,
      "step": 112
    },
    {
      "epoch": 0.011480239764299502,
      "grad_norm": 2.7085273265838623,
      "learning_rate": 4.583526315789473e-05,
      "loss": 1.0747,
      "step": 113
    },
    {
      "epoch": 0.011581834806461445,
      "grad_norm": 2.96585750579834,
      "learning_rate": 4.530842105263158e-05,
      "loss": 1.1136,
      "step": 114
    },
    {
      "epoch": 0.011683429848623387,
      "grad_norm": 3.3075642585754395,
      "learning_rate": 4.4781578947368416e-05,
      "loss": 1.1926,
      "step": 115
    },
    {
      "epoch": 0.011785024890785329,
      "grad_norm": 2.8126935958862305,
      "learning_rate": 4.425473684210526e-05,
      "loss": 1.2221,
      "step": 116
    },
    {
      "epoch": 0.011886619932947273,
      "grad_norm": 2.7019283771514893,
      "learning_rate": 4.372789473684211e-05,
      "loss": 1.0727,
      "step": 117
    },
    {
      "epoch": 0.011988214975109214,
      "grad_norm": 3.095580577850342,
      "learning_rate": 4.320105263157895e-05,
      "loss": 1.0674,
      "step": 118
    },
    {
      "epoch": 0.012089810017271158,
      "grad_norm": 3.138235330581665,
      "learning_rate": 4.2674210526315786e-05,
      "loss": 1.3973,
      "step": 119
    },
    {
      "epoch": 0.0121914050594331,
      "grad_norm": 2.981416702270508,
      "learning_rate": 4.2147368421052626e-05,
      "loss": 1.2259,
      "step": 120
    },
    {
      "epoch": 0.012293000101595042,
      "grad_norm": 2.793827772140503,
      "learning_rate": 4.162052631578947e-05,
      "loss": 1.1706,
      "step": 121
    },
    {
      "epoch": 0.012394595143756985,
      "grad_norm": 3.055459976196289,
      "learning_rate": 4.109368421052631e-05,
      "loss": 1.1658,
      "step": 122
    },
    {
      "epoch": 0.012496190185918927,
      "grad_norm": 2.991947889328003,
      "learning_rate": 4.056684210526316e-05,
      "loss": 1.1881,
      "step": 123
    },
    {
      "epoch": 0.01259778522808087,
      "grad_norm": 2.9653897285461426,
      "learning_rate": 4.004e-05,
      "loss": 1.1678,
      "step": 124
    },
    {
      "epoch": 0.012699380270242812,
      "grad_norm": 2.954136371612549,
      "learning_rate": 3.951315789473684e-05,
      "loss": 1.0478,
      "step": 125
    },
    {
      "epoch": 0.012800975312404754,
      "grad_norm": 3.4325461387634277,
      "learning_rate": 3.898631578947368e-05,
      "loss": 1.2497,
      "step": 126
    },
    {
      "epoch": 0.012902570354566698,
      "grad_norm": 4.589744567871094,
      "learning_rate": 3.845947368421052e-05,
      "loss": 1.2284,
      "step": 127
    },
    {
      "epoch": 0.01300416539672864,
      "grad_norm": 3.4360063076019287,
      "learning_rate": 3.7932631578947367e-05,
      "loss": 1.1895,
      "step": 128
    },
    {
      "epoch": 0.013105760438890583,
      "grad_norm": 3.6225502490997314,
      "learning_rate": 3.7405789473684206e-05,
      "loss": 1.182,
      "step": 129
    },
    {
      "epoch": 0.013207355481052525,
      "grad_norm": 3.9139211177825928,
      "learning_rate": 3.6878947368421045e-05,
      "loss": 1.4435,
      "step": 130
    },
    {
      "epoch": 0.013308950523214466,
      "grad_norm": 3.7881407737731934,
      "learning_rate": 3.635210526315789e-05,
      "loss": 1.1918,
      "step": 131
    },
    {
      "epoch": 0.01341054556537641,
      "grad_norm": 3.863058567047119,
      "learning_rate": 3.582526315789474e-05,
      "loss": 1.1332,
      "step": 132
    },
    {
      "epoch": 0.013512140607538352,
      "grad_norm": 3.9372336864471436,
      "learning_rate": 3.5298421052631576e-05,
      "loss": 1.0857,
      "step": 133
    },
    {
      "epoch": 0.013613735649700295,
      "grad_norm": 4.330385684967041,
      "learning_rate": 3.477157894736842e-05,
      "loss": 1.1804,
      "step": 134
    },
    {
      "epoch": 0.013715330691862237,
      "grad_norm": 4.239872455596924,
      "learning_rate": 3.424473684210526e-05,
      "loss": 1.2745,
      "step": 135
    },
    {
      "epoch": 0.013816925734024179,
      "grad_norm": 4.237067699432373,
      "learning_rate": 3.37178947368421e-05,
      "loss": 1.0984,
      "step": 136
    },
    {
      "epoch": 0.013918520776186123,
      "grad_norm": 4.873085975646973,
      "learning_rate": 3.319105263157894e-05,
      "loss": 1.4904,
      "step": 137
    },
    {
      "epoch": 0.014020115818348064,
      "grad_norm": 5.1811842918396,
      "learning_rate": 3.2664210526315786e-05,
      "loss": 1.3309,
      "step": 138
    },
    {
      "epoch": 0.014121710860510008,
      "grad_norm": 5.059803009033203,
      "learning_rate": 3.213736842105263e-05,
      "loss": 1.1333,
      "step": 139
    },
    {
      "epoch": 0.01422330590267195,
      "grad_norm": 5.975893974304199,
      "learning_rate": 3.161052631578947e-05,
      "loss": 1.387,
      "step": 140
    },
    {
      "epoch": 0.014324900944833891,
      "grad_norm": 6.209765911102295,
      "learning_rate": 3.108368421052632e-05,
      "loss": 1.681,
      "step": 141
    },
    {
      "epoch": 0.014426495986995835,
      "grad_norm": 5.893293857574463,
      "learning_rate": 3.0556842105263156e-05,
      "loss": 1.4305,
      "step": 142
    },
    {
      "epoch": 0.014528091029157777,
      "grad_norm": 8.19773006439209,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 1.5269,
      "step": 143
    },
    {
      "epoch": 0.01462968607131972,
      "grad_norm": 7.0231547355651855,
      "learning_rate": 2.9503157894736838e-05,
      "loss": 1.4278,
      "step": 144
    },
    {
      "epoch": 0.014731281113481662,
      "grad_norm": 6.790130615234375,
      "learning_rate": 2.8976315789473684e-05,
      "loss": 1.2506,
      "step": 145
    },
    {
      "epoch": 0.014832876155643604,
      "grad_norm": 6.087902069091797,
      "learning_rate": 2.8449473684210523e-05,
      "loss": 0.8843,
      "step": 146
    },
    {
      "epoch": 0.014934471197805547,
      "grad_norm": 7.544525623321533,
      "learning_rate": 2.7922631578947366e-05,
      "loss": 0.9716,
      "step": 147
    },
    {
      "epoch": 0.01503606623996749,
      "grad_norm": 7.611911296844482,
      "learning_rate": 2.7395789473684212e-05,
      "loss": 1.0314,
      "step": 148
    },
    {
      "epoch": 0.015137661282129433,
      "grad_norm": 8.211386680603027,
      "learning_rate": 2.686894736842105e-05,
      "loss": 0.9311,
      "step": 149
    },
    {
      "epoch": 0.015239256324291375,
      "grad_norm": 12.661590576171875,
      "learning_rate": 2.634210526315789e-05,
      "loss": 0.8717,
      "step": 150
    },
    {
      "epoch": 0.015239256324291375,
      "eval_loss": 0.5625200271606445,
      "eval_runtime": 517.8623,
      "eval_samples_per_second": 8.004,
      "eval_steps_per_second": 2.002,
      "step": 150
    },
    {
      "epoch": 0.015340851366453316,
      "grad_norm": 1.5939819812774658,
      "learning_rate": 2.5815263157894736e-05,
      "loss": 0.7066,
      "step": 151
    },
    {
      "epoch": 0.01544244640861526,
      "grad_norm": 1.6483330726623535,
      "learning_rate": 2.528842105263158e-05,
      "loss": 0.6955,
      "step": 152
    },
    {
      "epoch": 0.015544041450777202,
      "grad_norm": 1.583403468132019,
      "learning_rate": 2.4761578947368418e-05,
      "loss": 0.6968,
      "step": 153
    },
    {
      "epoch": 0.015645636492939145,
      "grad_norm": 1.8011175394058228,
      "learning_rate": 2.423473684210526e-05,
      "loss": 0.7792,
      "step": 154
    },
    {
      "epoch": 0.015747231535101085,
      "grad_norm": 1.8397107124328613,
      "learning_rate": 2.3707894736842103e-05,
      "loss": 0.7355,
      "step": 155
    },
    {
      "epoch": 0.01584882657726303,
      "grad_norm": 1.9635233879089355,
      "learning_rate": 2.3181052631578946e-05,
      "loss": 0.843,
      "step": 156
    },
    {
      "epoch": 0.015950421619424972,
      "grad_norm": 2.132654905319214,
      "learning_rate": 2.265421052631579e-05,
      "loss": 0.9858,
      "step": 157
    },
    {
      "epoch": 0.016052016661586916,
      "grad_norm": 2.553905487060547,
      "learning_rate": 2.212736842105263e-05,
      "loss": 1.091,
      "step": 158
    },
    {
      "epoch": 0.016153611703748856,
      "grad_norm": 1.965105414390564,
      "learning_rate": 2.1600526315789474e-05,
      "loss": 0.8878,
      "step": 159
    },
    {
      "epoch": 0.0162552067459108,
      "grad_norm": 2.0289783477783203,
      "learning_rate": 2.1073684210526313e-05,
      "loss": 0.8764,
      "step": 160
    },
    {
      "epoch": 0.016356801788072743,
      "grad_norm": 2.401559352874756,
      "learning_rate": 2.0546842105263155e-05,
      "loss": 1.0646,
      "step": 161
    },
    {
      "epoch": 0.016458396830234683,
      "grad_norm": 2.2588117122650146,
      "learning_rate": 2.002e-05,
      "loss": 0.9658,
      "step": 162
    },
    {
      "epoch": 0.016559991872396627,
      "grad_norm": 2.1253316402435303,
      "learning_rate": 1.949315789473684e-05,
      "loss": 0.8729,
      "step": 163
    },
    {
      "epoch": 0.01666158691455857,
      "grad_norm": 2.832216739654541,
      "learning_rate": 1.8966315789473683e-05,
      "loss": 1.2091,
      "step": 164
    },
    {
      "epoch": 0.01676318195672051,
      "grad_norm": 2.343205690383911,
      "learning_rate": 1.8439473684210522e-05,
      "loss": 1.0685,
      "step": 165
    },
    {
      "epoch": 0.016864776998882454,
      "grad_norm": 2.5135369300842285,
      "learning_rate": 1.791263157894737e-05,
      "loss": 0.9415,
      "step": 166
    },
    {
      "epoch": 0.016966372041044397,
      "grad_norm": 2.691727876663208,
      "learning_rate": 1.738578947368421e-05,
      "loss": 1.0256,
      "step": 167
    },
    {
      "epoch": 0.01706796708320634,
      "grad_norm": 2.4180541038513184,
      "learning_rate": 1.685894736842105e-05,
      "loss": 0.9336,
      "step": 168
    },
    {
      "epoch": 0.01716956212536828,
      "grad_norm": 2.8233697414398193,
      "learning_rate": 1.6332105263157893e-05,
      "loss": 1.0405,
      "step": 169
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 2.802211284637451,
      "learning_rate": 1.5805263157894735e-05,
      "loss": 1.0237,
      "step": 170
    },
    {
      "epoch": 0.017372752209692168,
      "grad_norm": 2.543400764465332,
      "learning_rate": 1.5278421052631578e-05,
      "loss": 1.0185,
      "step": 171
    },
    {
      "epoch": 0.017474347251854108,
      "grad_norm": 2.7977938652038574,
      "learning_rate": 1.4751578947368419e-05,
      "loss": 1.0385,
      "step": 172
    },
    {
      "epoch": 0.017575942294016052,
      "grad_norm": 3.0091969966888428,
      "learning_rate": 1.4224736842105262e-05,
      "loss": 1.184,
      "step": 173
    },
    {
      "epoch": 0.017677537336177995,
      "grad_norm": 2.7623536586761475,
      "learning_rate": 1.3697894736842106e-05,
      "loss": 1.0893,
      "step": 174
    },
    {
      "epoch": 0.017779132378339935,
      "grad_norm": 3.233461618423462,
      "learning_rate": 1.3171052631578945e-05,
      "loss": 1.2953,
      "step": 175
    },
    {
      "epoch": 0.01788072742050188,
      "grad_norm": 2.841423511505127,
      "learning_rate": 1.264421052631579e-05,
      "loss": 1.1212,
      "step": 176
    },
    {
      "epoch": 0.017982322462663822,
      "grad_norm": 3.207925796508789,
      "learning_rate": 1.211736842105263e-05,
      "loss": 1.2039,
      "step": 177
    },
    {
      "epoch": 0.018083917504825766,
      "grad_norm": 2.9837098121643066,
      "learning_rate": 1.1590526315789473e-05,
      "loss": 1.0074,
      "step": 178
    },
    {
      "epoch": 0.018185512546987706,
      "grad_norm": 3.340939521789551,
      "learning_rate": 1.1063684210526316e-05,
      "loss": 1.2716,
      "step": 179
    },
    {
      "epoch": 0.01828710758914965,
      "grad_norm": 3.5256423950195312,
      "learning_rate": 1.0536842105263156e-05,
      "loss": 1.0574,
      "step": 180
    },
    {
      "epoch": 0.018388702631311593,
      "grad_norm": 3.2755520343780518,
      "learning_rate": 1.001e-05,
      "loss": 1.1183,
      "step": 181
    },
    {
      "epoch": 0.018490297673473533,
      "grad_norm": 3.5652754306793213,
      "learning_rate": 9.483157894736842e-06,
      "loss": 1.1908,
      "step": 182
    },
    {
      "epoch": 0.018591892715635477,
      "grad_norm": 3.5001885890960693,
      "learning_rate": 8.956315789473684e-06,
      "loss": 1.3586,
      "step": 183
    },
    {
      "epoch": 0.01869348775779742,
      "grad_norm": 3.986107110977173,
      "learning_rate": 8.429473684210525e-06,
      "loss": 1.4174,
      "step": 184
    },
    {
      "epoch": 0.01879508279995936,
      "grad_norm": 3.2602295875549316,
      "learning_rate": 7.902631578947368e-06,
      "loss": 1.0629,
      "step": 185
    },
    {
      "epoch": 0.018896677842121304,
      "grad_norm": 3.6767148971557617,
      "learning_rate": 7.3757894736842095e-06,
      "loss": 1.2673,
      "step": 186
    },
    {
      "epoch": 0.018998272884283247,
      "grad_norm": 4.002993106842041,
      "learning_rate": 6.848947368421053e-06,
      "loss": 1.2915,
      "step": 187
    },
    {
      "epoch": 0.01909986792644519,
      "grad_norm": 4.814608097076416,
      "learning_rate": 6.322105263157895e-06,
      "loss": 1.4219,
      "step": 188
    },
    {
      "epoch": 0.01920146296860713,
      "grad_norm": 4.147160530090332,
      "learning_rate": 5.7952631578947365e-06,
      "loss": 1.1889,
      "step": 189
    },
    {
      "epoch": 0.019303058010769075,
      "grad_norm": 5.3963470458984375,
      "learning_rate": 5.268421052631578e-06,
      "loss": 1.4151,
      "step": 190
    },
    {
      "epoch": 0.019404653052931018,
      "grad_norm": 5.4656982421875,
      "learning_rate": 4.741578947368421e-06,
      "loss": 1.2987,
      "step": 191
    },
    {
      "epoch": 0.019506248095092958,
      "grad_norm": 5.874293327331543,
      "learning_rate": 4.2147368421052626e-06,
      "loss": 1.3427,
      "step": 192
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 5.825425148010254,
      "learning_rate": 3.6878947368421047e-06,
      "loss": 1.0556,
      "step": 193
    },
    {
      "epoch": 0.019709438179416845,
      "grad_norm": 5.29592227935791,
      "learning_rate": 3.1610526315789474e-06,
      "loss": 0.9699,
      "step": 194
    },
    {
      "epoch": 0.019811033221578785,
      "grad_norm": 6.861169815063477,
      "learning_rate": 2.634210526315789e-06,
      "loss": 1.2375,
      "step": 195
    },
    {
      "epoch": 0.01991262826374073,
      "grad_norm": 7.811491966247559,
      "learning_rate": 2.1073684210526313e-06,
      "loss": 0.8911,
      "step": 196
    },
    {
      "epoch": 0.020014223305902672,
      "grad_norm": 8.977100372314453,
      "learning_rate": 1.5805263157894737e-06,
      "loss": 1.1859,
      "step": 197
    },
    {
      "epoch": 0.020115818348064616,
      "grad_norm": 9.319770812988281,
      "learning_rate": 1.0536842105263156e-06,
      "loss": 1.5089,
      "step": 198
    },
    {
      "epoch": 0.020217413390226556,
      "grad_norm": 6.771570205688477,
      "learning_rate": 5.268421052631578e-07,
      "loss": 0.5158,
      "step": 199
    },
    {
      "epoch": 0.0203190084323885,
      "grad_norm": 9.172361373901367,
      "learning_rate": 0.0,
      "loss": 0.8363,
      "step": 200
    },
    {
      "epoch": 0.0203190084323885,
      "eval_loss": 0.5461220145225525,
      "eval_runtime": 519.175,
      "eval_samples_per_second": 7.984,
      "eval_steps_per_second": 1.997,
      "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": 7.71283380904919e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}