{
  "best_metric": 0.22681911289691925,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.29027576197387517,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001451378809869376,
      "grad_norm": 0.11486738920211792,
      "learning_rate": 1.0110000000000001e-05,
      "loss": 0.2249,
      "step": 1
    },
    {
      "epoch": 0.001451378809869376,
      "eval_loss": 0.27678582072257996,
      "eval_runtime": 142.974,
      "eval_samples_per_second": 2.035,
      "eval_steps_per_second": 0.511,
      "step": 1
    },
    {
      "epoch": 0.002902757619738752,
      "grad_norm": 0.11387992650270462,
      "learning_rate": 2.0220000000000003e-05,
      "loss": 0.4195,
      "step": 2
    },
    {
      "epoch": 0.0043541364296081275,
      "grad_norm": 0.1770201325416565,
      "learning_rate": 3.033e-05,
      "loss": 0.3746,
      "step": 3
    },
    {
      "epoch": 0.005805515239477504,
      "grad_norm": 0.15089277923107147,
      "learning_rate": 4.0440000000000006e-05,
      "loss": 0.3461,
      "step": 4
    },
    {
      "epoch": 0.00725689404934688,
      "grad_norm": 0.11748471856117249,
      "learning_rate": 5.055e-05,
      "loss": 0.1969,
      "step": 5
    },
    {
      "epoch": 0.008708272859216255,
      "grad_norm": 0.1325271725654602,
      "learning_rate": 6.066e-05,
      "loss": 0.2835,
      "step": 6
    },
    {
      "epoch": 0.010159651669085631,
      "grad_norm": 0.14989273250102997,
      "learning_rate": 7.077e-05,
      "loss": 0.44,
      "step": 7
    },
    {
      "epoch": 0.011611030478955007,
      "grad_norm": 0.1532517969608307,
      "learning_rate": 8.088000000000001e-05,
      "loss": 0.4155,
      "step": 8
    },
    {
      "epoch": 0.013062409288824383,
      "grad_norm": 0.12538368999958038,
      "learning_rate": 9.099000000000001e-05,
      "loss": 0.3613,
      "step": 9
    },
    {
      "epoch": 0.01451378809869376,
      "grad_norm": 0.13840965926647186,
      "learning_rate": 0.0001011,
      "loss": 0.7261,
      "step": 10
    },
    {
      "epoch": 0.015965166908563134,
      "grad_norm": 0.1670045405626297,
      "learning_rate": 0.00010056789473684211,
      "loss": 0.5663,
      "step": 11
    },
    {
      "epoch": 0.01741654571843251,
      "grad_norm": 0.13095274567604065,
      "learning_rate": 0.00010003578947368421,
      "loss": 0.3288,
      "step": 12
    },
    {
      "epoch": 0.018867924528301886,
      "grad_norm": 0.19772979617118835,
      "learning_rate": 9.950368421052632e-05,
      "loss": 0.613,
      "step": 13
    },
    {
      "epoch": 0.020319303338171262,
      "grad_norm": 0.16937138140201569,
      "learning_rate": 9.897157894736842e-05,
      "loss": 0.4953,
      "step": 14
    },
    {
      "epoch": 0.02177068214804064,
      "grad_norm": 0.1333189755678177,
      "learning_rate": 9.843947368421053e-05,
      "loss": 0.2195,
      "step": 15
    },
    {
      "epoch": 0.023222060957910014,
      "grad_norm": 0.1428212672472,
      "learning_rate": 9.790736842105264e-05,
      "loss": 0.2334,
      "step": 16
    },
    {
      "epoch": 0.02467343976777939,
      "grad_norm": 0.14330728352069855,
      "learning_rate": 9.737526315789474e-05,
      "loss": 0.3142,
      "step": 17
    },
    {
      "epoch": 0.026124818577648767,
      "grad_norm": 0.1493055373430252,
      "learning_rate": 9.684315789473684e-05,
      "loss": 0.2551,
      "step": 18
    },
    {
      "epoch": 0.027576197387518143,
      "grad_norm": 0.16706344485282898,
      "learning_rate": 9.631105263157895e-05,
      "loss": 0.5574,
      "step": 19
    },
    {
      "epoch": 0.02902757619738752,
      "grad_norm": 0.11606133729219437,
      "learning_rate": 9.577894736842105e-05,
      "loss": 0.1948,
      "step": 20
    },
    {
      "epoch": 0.030478955007256895,
      "grad_norm": 0.0992949903011322,
      "learning_rate": 9.524684210526317e-05,
      "loss": 0.1042,
      "step": 21
    },
    {
      "epoch": 0.03193033381712627,
      "grad_norm": 0.15178389847278595,
      "learning_rate": 9.471473684210526e-05,
      "loss": 0.4452,
      "step": 22
    },
    {
      "epoch": 0.033381712626995644,
      "grad_norm": 0.15305830538272858,
      "learning_rate": 9.418263157894737e-05,
      "loss": 0.4336,
      "step": 23
    },
    {
      "epoch": 0.03483309143686502,
      "grad_norm": 0.21439702808856964,
      "learning_rate": 9.365052631578948e-05,
      "loss": 0.346,
      "step": 24
    },
    {
      "epoch": 0.036284470246734396,
      "grad_norm": 0.1342068761587143,
      "learning_rate": 9.311842105263157e-05,
      "loss": 0.3454,
      "step": 25
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": 0.1589202582836151,
      "learning_rate": 9.258631578947368e-05,
      "loss": 0.4931,
      "step": 26
    },
    {
      "epoch": 0.03918722786647315,
      "grad_norm": 0.16286569833755493,
      "learning_rate": 9.20542105263158e-05,
      "loss": 0.5843,
      "step": 27
    },
    {
      "epoch": 0.040638606676342524,
      "grad_norm": 0.11265375465154648,
      "learning_rate": 9.15221052631579e-05,
      "loss": 0.2569,
      "step": 28
    },
    {
      "epoch": 0.0420899854862119,
      "grad_norm": 0.18966278433799744,
      "learning_rate": 9.099000000000001e-05,
      "loss": 0.4922,
      "step": 29
    },
    {
      "epoch": 0.04354136429608128,
      "grad_norm": 0.2602640688419342,
      "learning_rate": 9.045789473684212e-05,
      "loss": 0.3959,
      "step": 30
    },
    {
      "epoch": 0.04499274310595065,
      "grad_norm": 0.12830835580825806,
      "learning_rate": 8.992578947368421e-05,
      "loss": 0.3903,
      "step": 31
    },
    {
      "epoch": 0.04644412191582003,
      "grad_norm": 0.10974445939064026,
      "learning_rate": 8.939368421052632e-05,
      "loss": 0.2795,
      "step": 32
    },
    {
      "epoch": 0.047895500725689405,
      "grad_norm": 0.16427350044250488,
      "learning_rate": 8.886157894736841e-05,
      "loss": 0.4776,
      "step": 33
    },
    {
      "epoch": 0.04934687953555878,
      "grad_norm": 0.12569822371006012,
      "learning_rate": 8.832947368421054e-05,
      "loss": 0.2615,
      "step": 34
    },
    {
      "epoch": 0.05079825834542816,
      "grad_norm": 0.10434585809707642,
      "learning_rate": 8.779736842105264e-05,
      "loss": 0.2248,
      "step": 35
    },
    {
      "epoch": 0.05224963715529753,
      "grad_norm": 0.1004101112484932,
      "learning_rate": 8.726526315789474e-05,
      "loss": 0.2055,
      "step": 36
    },
    {
      "epoch": 0.05370101596516691,
      "grad_norm": 0.12491065263748169,
      "learning_rate": 8.673315789473685e-05,
      "loss": 0.2482,
      "step": 37
    },
    {
      "epoch": 0.055152394775036286,
      "grad_norm": 0.11319632083177567,
      "learning_rate": 8.620105263157896e-05,
      "loss": 0.2185,
      "step": 38
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 0.15422259271144867,
      "learning_rate": 8.566894736842105e-05,
      "loss": 0.3448,
      "step": 39
    },
    {
      "epoch": 0.05805515239477504,
      "grad_norm": 0.15866440534591675,
      "learning_rate": 8.513684210526316e-05,
      "loss": 0.6739,
      "step": 40
    },
    {
      "epoch": 0.059506531204644414,
      "grad_norm": 0.1435173898935318,
      "learning_rate": 8.460473684210527e-05,
      "loss": 0.2159,
      "step": 41
    },
    {
      "epoch": 0.06095791001451379,
      "grad_norm": 0.21297410130500793,
      "learning_rate": 8.407263157894738e-05,
      "loss": 0.3077,
      "step": 42
    },
    {
      "epoch": 0.062409288824383166,
      "grad_norm": 0.1251886934041977,
      "learning_rate": 8.354052631578948e-05,
      "loss": 0.2113,
      "step": 43
    },
    {
      "epoch": 0.06386066763425254,
      "grad_norm": 0.1815638542175293,
      "learning_rate": 8.300842105263158e-05,
      "loss": 0.6564,
      "step": 44
    },
    {
      "epoch": 0.06531204644412192,
      "grad_norm": 0.2576989531517029,
      "learning_rate": 8.247631578947369e-05,
      "loss": 0.5205,
      "step": 45
    },
    {
      "epoch": 0.06676342525399129,
      "grad_norm": 0.27275457978248596,
      "learning_rate": 8.19442105263158e-05,
      "loss": 0.9175,
      "step": 46
    },
    {
      "epoch": 0.06821480406386067,
      "grad_norm": 0.26641345024108887,
      "learning_rate": 8.141210526315789e-05,
      "loss": 0.812,
      "step": 47
    },
    {
      "epoch": 0.06966618287373004,
      "grad_norm": 0.2708298861980438,
      "learning_rate": 8.088000000000001e-05,
      "loss": 0.6076,
      "step": 48
    },
    {
      "epoch": 0.07111756168359942,
      "grad_norm": 0.5135082602500916,
      "learning_rate": 8.03478947368421e-05,
      "loss": 0.9538,
      "step": 49
    },
    {
      "epoch": 0.07256894049346879,
      "grad_norm": 0.46205997467041016,
      "learning_rate": 7.981578947368421e-05,
      "loss": 1.1091,
      "step": 50
    },
    {
      "epoch": 0.07256894049346879,
      "eval_loss": 0.24128209054470062,
      "eval_runtime": 146.2789,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 0.499,
      "step": 50
    },
    {
      "epoch": 0.07402031930333818,
      "grad_norm": 0.15042653679847717,
      "learning_rate": 7.928368421052632e-05,
      "loss": 0.5749,
      "step": 51
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.14070290327072144,
      "learning_rate": 7.875157894736842e-05,
      "loss": 0.3815,
      "step": 52
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.12616680562496185,
      "learning_rate": 7.821947368421053e-05,
      "loss": 0.3485,
      "step": 53
    },
    {
      "epoch": 0.0783744557329463,
      "grad_norm": 0.1807371824979782,
      "learning_rate": 7.768736842105263e-05,
      "loss": 0.6332,
      "step": 54
    },
    {
      "epoch": 0.07982583454281568,
      "grad_norm": 0.1610403060913086,
      "learning_rate": 7.715526315789474e-05,
      "loss": 0.4334,
      "step": 55
    },
    {
      "epoch": 0.08127721335268505,
      "grad_norm": 0.16740575432777405,
      "learning_rate": 7.662315789473685e-05,
      "loss": 0.5169,
      "step": 56
    },
    {
      "epoch": 0.08272859216255443,
      "grad_norm": 0.13583853840827942,
      "learning_rate": 7.609105263157895e-05,
      "loss": 0.3515,
      "step": 57
    },
    {
      "epoch": 0.0841799709724238,
      "grad_norm": 0.20852766931056976,
      "learning_rate": 7.555894736842105e-05,
      "loss": 0.8417,
      "step": 58
    },
    {
      "epoch": 0.08563134978229318,
      "grad_norm": 0.12840092182159424,
      "learning_rate": 7.502684210526316e-05,
      "loss": 0.3527,
      "step": 59
    },
    {
      "epoch": 0.08708272859216255,
      "grad_norm": 0.20794260501861572,
      "learning_rate": 7.449473684210526e-05,
      "loss": 0.8209,
      "step": 60
    },
    {
      "epoch": 0.08853410740203194,
      "grad_norm": 0.15332041680812836,
      "learning_rate": 7.396263157894738e-05,
      "loss": 0.5123,
      "step": 61
    },
    {
      "epoch": 0.0899854862119013,
      "grad_norm": 0.12152067571878433,
      "learning_rate": 7.343052631578949e-05,
      "loss": 0.5442,
      "step": 62
    },
    {
      "epoch": 0.09143686502177069,
      "grad_norm": 0.15734325349330902,
      "learning_rate": 7.289842105263158e-05,
      "loss": 0.4926,
      "step": 63
    },
    {
      "epoch": 0.09288824383164006,
      "grad_norm": 0.10759459435939789,
      "learning_rate": 7.236631578947369e-05,
      "loss": 0.2285,
      "step": 64
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 0.11365488916635513,
      "learning_rate": 7.183421052631579e-05,
      "loss": 0.3032,
      "step": 65
    },
    {
      "epoch": 0.09579100145137881,
      "grad_norm": 0.13057614862918854,
      "learning_rate": 7.13021052631579e-05,
      "loss": 0.4789,
      "step": 66
    },
    {
      "epoch": 0.09724238026124818,
      "grad_norm": 0.1509314924478531,
      "learning_rate": 7.077e-05,
      "loss": 0.5571,
      "step": 67
    },
    {
      "epoch": 0.09869375907111756,
      "grad_norm": 0.16016532480716705,
      "learning_rate": 7.023789473684211e-05,
      "loss": 0.2708,
      "step": 68
    },
    {
      "epoch": 0.10014513788098693,
      "grad_norm": 0.2185145616531372,
      "learning_rate": 6.970578947368422e-05,
      "loss": 0.4046,
      "step": 69
    },
    {
      "epoch": 0.10159651669085631,
      "grad_norm": 0.14823275804519653,
      "learning_rate": 6.917368421052633e-05,
      "loss": 0.5717,
      "step": 70
    },
    {
      "epoch": 0.10304789550072568,
      "grad_norm": 0.16261740028858185,
      "learning_rate": 6.864157894736842e-05,
      "loss": 0.3313,
      "step": 71
    },
    {
      "epoch": 0.10449927431059507,
      "grad_norm": 0.1639692485332489,
      "learning_rate": 6.810947368421053e-05,
      "loss": 0.7474,
      "step": 72
    },
    {
      "epoch": 0.10595065312046444,
      "grad_norm": 0.11137572675943375,
      "learning_rate": 6.757736842105264e-05,
      "loss": 0.3237,
      "step": 73
    },
    {
      "epoch": 0.10740203193033382,
      "grad_norm": 0.09403427690267563,
      "learning_rate": 6.704526315789473e-05,
      "loss": 0.213,
      "step": 74
    },
    {
      "epoch": 0.10885341074020319,
      "grad_norm": 0.1198626309633255,
      "learning_rate": 6.651315789473685e-05,
      "loss": 0.3147,
      "step": 75
    },
    {
      "epoch": 0.11030478955007257,
      "grad_norm": 0.18822187185287476,
      "learning_rate": 6.598105263157895e-05,
      "loss": 0.2479,
      "step": 76
    },
    {
      "epoch": 0.11175616835994194,
      "grad_norm": 0.08338137716054916,
      "learning_rate": 6.544894736842106e-05,
      "loss": 0.1284,
      "step": 77
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 0.11395663768053055,
      "learning_rate": 6.491684210526317e-05,
      "loss": 0.304,
      "step": 78
    },
    {
      "epoch": 0.11465892597968069,
      "grad_norm": 0.12172822654247284,
      "learning_rate": 6.438473684210526e-05,
      "loss": 0.5225,
      "step": 79
    },
    {
      "epoch": 0.11611030478955008,
      "grad_norm": 0.18436570465564728,
      "learning_rate": 6.385263157894737e-05,
      "loss": 1.1369,
      "step": 80
    },
    {
      "epoch": 0.11756168359941944,
      "grad_norm": 0.08676780015230179,
      "learning_rate": 6.332052631578948e-05,
      "loss": 0.2241,
      "step": 81
    },
    {
      "epoch": 0.11901306240928883,
      "grad_norm": 0.14665937423706055,
      "learning_rate": 6.278842105263159e-05,
      "loss": 0.4818,
      "step": 82
    },
    {
      "epoch": 0.1204644412191582,
      "grad_norm": 0.12407947331666946,
      "learning_rate": 6.22563157894737e-05,
      "loss": 0.4061,
      "step": 83
    },
    {
      "epoch": 0.12191582002902758,
      "grad_norm": 0.12156087160110474,
      "learning_rate": 6.172421052631579e-05,
      "loss": 0.4842,
      "step": 84
    },
    {
      "epoch": 0.12336719883889695,
      "grad_norm": 0.164754256606102,
      "learning_rate": 6.11921052631579e-05,
      "loss": 0.6039,
      "step": 85
    },
    {
      "epoch": 0.12481857764876633,
      "grad_norm": 0.13035471737384796,
      "learning_rate": 6.066e-05,
      "loss": 0.5963,
      "step": 86
    },
    {
      "epoch": 0.1262699564586357,
      "grad_norm": 0.08667127043008804,
      "learning_rate": 6.012789473684211e-05,
      "loss": 0.104,
      "step": 87
    },
    {
      "epoch": 0.12772133526850507,
      "grad_norm": 0.12500996887683868,
      "learning_rate": 5.959578947368421e-05,
      "loss": 0.1519,
      "step": 88
    },
    {
      "epoch": 0.12917271407837447,
      "grad_norm": 0.1052846610546112,
      "learning_rate": 5.9063684210526324e-05,
      "loss": 0.168,
      "step": 89
    },
    {
      "epoch": 0.13062409288824384,
      "grad_norm": 0.16326619684696198,
      "learning_rate": 5.8531578947368425e-05,
      "loss": 1.0778,
      "step": 90
    },
    {
      "epoch": 0.1320754716981132,
      "grad_norm": 0.18031665682792664,
      "learning_rate": 5.7999473684210527e-05,
      "loss": 0.8578,
      "step": 91
    },
    {
      "epoch": 0.13352685050798258,
      "grad_norm": 0.14327001571655273,
      "learning_rate": 5.7467368421052635e-05,
      "loss": 0.8367,
      "step": 92
    },
    {
      "epoch": 0.13497822931785197,
      "grad_norm": 0.12158166617155075,
      "learning_rate": 5.6935263157894736e-05,
      "loss": 0.2978,
      "step": 93
    },
    {
      "epoch": 0.13642960812772134,
      "grad_norm": 0.17898587882518768,
      "learning_rate": 5.640315789473684e-05,
      "loss": 0.7248,
      "step": 94
    },
    {
      "epoch": 0.1378809869375907,
      "grad_norm": 0.1620013415813446,
      "learning_rate": 5.587105263157895e-05,
      "loss": 0.5909,
      "step": 95
    },
    {
      "epoch": 0.13933236574746008,
      "grad_norm": 0.24596630036830902,
      "learning_rate": 5.533894736842106e-05,
      "loss": 1.3,
      "step": 96
    },
    {
      "epoch": 0.14078374455732948,
      "grad_norm": 0.28974536061286926,
      "learning_rate": 5.480684210526316e-05,
      "loss": 1.0699,
      "step": 97
    },
    {
      "epoch": 0.14223512336719885,
      "grad_norm": 0.2533659338951111,
      "learning_rate": 5.4274736842105264e-05,
      "loss": 0.6266,
      "step": 98
    },
    {
      "epoch": 0.14368650217706821,
      "grad_norm": 0.36984333395957947,
      "learning_rate": 5.374263157894737e-05,
      "loss": 1.3249,
      "step": 99
    },
    {
      "epoch": 0.14513788098693758,
      "grad_norm": 0.4221994876861572,
      "learning_rate": 5.3210526315789474e-05,
      "loss": 0.9726,
      "step": 100
    },
    {
      "epoch": 0.14513788098693758,
      "eval_loss": 0.2286633849143982,
      "eval_runtime": 145.162,
      "eval_samples_per_second": 2.005,
      "eval_steps_per_second": 0.503,
      "step": 100
    },
    {
      "epoch": 0.14658925979680695,
      "grad_norm": 0.13860496878623962,
      "learning_rate": 5.2678421052631576e-05,
      "loss": 0.7931,
      "step": 101
    },
    {
      "epoch": 0.14804063860667635,
      "grad_norm": 0.1530522257089615,
      "learning_rate": 5.214631578947369e-05,
      "loss": 0.4883,
      "step": 102
    },
    {
      "epoch": 0.14949201741654572,
      "grad_norm": 0.09421262890100479,
      "learning_rate": 5.161421052631579e-05,
      "loss": 0.1757,
      "step": 103
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.11253266036510468,
      "learning_rate": 5.10821052631579e-05,
      "loss": 0.4355,
      "step": 104
    },
    {
      "epoch": 0.15239477503628446,
      "grad_norm": 0.11226090788841248,
      "learning_rate": 5.055e-05,
      "loss": 0.3406,
      "step": 105
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.09969495981931686,
      "learning_rate": 5.0017894736842104e-05,
      "loss": 0.33,
      "step": 106
    },
    {
      "epoch": 0.15529753265602322,
      "grad_norm": 0.14994554221630096,
      "learning_rate": 4.948578947368421e-05,
      "loss": 0.7712,
      "step": 107
    },
    {
      "epoch": 0.1567489114658926,
      "grad_norm": 0.16747573018074036,
      "learning_rate": 4.895368421052632e-05,
      "loss": 0.4805,
      "step": 108
    },
    {
      "epoch": 0.15820029027576196,
      "grad_norm": 0.15101346373558044,
      "learning_rate": 4.842157894736842e-05,
      "loss": 0.6745,
      "step": 109
    },
    {
      "epoch": 0.15965166908563136,
      "grad_norm": 0.14325077831745148,
      "learning_rate": 4.7889473684210523e-05,
      "loss": 0.2481,
      "step": 110
    },
    {
      "epoch": 0.16110304789550073,
      "grad_norm": 0.6589614152908325,
      "learning_rate": 4.735736842105263e-05,
      "loss": 0.385,
      "step": 111
    },
    {
      "epoch": 0.1625544267053701,
      "grad_norm": 0.14817237854003906,
      "learning_rate": 4.682526315789474e-05,
      "loss": 0.4519,
      "step": 112
    },
    {
      "epoch": 0.16400580551523947,
      "grad_norm": 0.12075196951627731,
      "learning_rate": 4.629315789473684e-05,
      "loss": 0.32,
      "step": 113
    },
    {
      "epoch": 0.16545718432510886,
      "grad_norm": 0.10896284133195877,
      "learning_rate": 4.576105263157895e-05,
      "loss": 0.252,
      "step": 114
    },
    {
      "epoch": 0.16690856313497823,
      "grad_norm": 0.15797024965286255,
      "learning_rate": 4.522894736842106e-05,
      "loss": 0.7193,
      "step": 115
    },
    {
      "epoch": 0.1683599419448476,
      "grad_norm": 0.12811946868896484,
      "learning_rate": 4.469684210526316e-05,
      "loss": 0.5991,
      "step": 116
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 0.17125706374645233,
      "learning_rate": 4.416473684210527e-05,
      "loss": 0.6612,
      "step": 117
    },
    {
      "epoch": 0.17126269956458637,
      "grad_norm": 0.21033529937267303,
      "learning_rate": 4.363263157894737e-05,
      "loss": 0.637,
      "step": 118
    },
    {
      "epoch": 0.17271407837445574,
      "grad_norm": 0.14343442022800446,
      "learning_rate": 4.310052631578948e-05,
      "loss": 0.3919,
      "step": 119
    },
    {
      "epoch": 0.1741654571843251,
      "grad_norm": 0.09223167598247528,
      "learning_rate": 4.256842105263158e-05,
      "loss": 0.2206,
      "step": 120
    },
    {
      "epoch": 0.17561683599419448,
      "grad_norm": 0.10201866924762726,
      "learning_rate": 4.203631578947369e-05,
      "loss": 0.2657,
      "step": 121
    },
    {
      "epoch": 0.17706821480406387,
      "grad_norm": 0.09830533713102341,
      "learning_rate": 4.150421052631579e-05,
      "loss": 0.1767,
      "step": 122
    },
    {
      "epoch": 0.17851959361393324,
      "grad_norm": 0.11305135488510132,
      "learning_rate": 4.09721052631579e-05,
      "loss": 0.3528,
      "step": 123
    },
    {
      "epoch": 0.1799709724238026,
      "grad_norm": 0.11795450747013092,
      "learning_rate": 4.0440000000000006e-05,
      "loss": 0.2826,
      "step": 124
    },
    {
      "epoch": 0.18142235123367198,
      "grad_norm": 0.10810278356075287,
      "learning_rate": 3.990789473684211e-05,
      "loss": 0.3728,
      "step": 125
    },
    {
      "epoch": 0.18287373004354138,
      "grad_norm": 0.07889194041490555,
      "learning_rate": 3.937578947368421e-05,
      "loss": 0.1485,
      "step": 126
    },
    {
      "epoch": 0.18432510885341075,
      "grad_norm": 0.12167462706565857,
      "learning_rate": 3.884368421052632e-05,
      "loss": 0.3191,
      "step": 127
    },
    {
      "epoch": 0.18577648766328012,
      "grad_norm": 0.13652844727039337,
      "learning_rate": 3.8311578947368426e-05,
      "loss": 0.3272,
      "step": 128
    },
    {
      "epoch": 0.18722786647314948,
      "grad_norm": 0.11355964839458466,
      "learning_rate": 3.777947368421053e-05,
      "loss": 0.2216,
      "step": 129
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 0.12072530388832092,
      "learning_rate": 3.724736842105263e-05,
      "loss": 0.2511,
      "step": 130
    },
    {
      "epoch": 0.19013062409288825,
      "grad_norm": 0.11075890809297562,
      "learning_rate": 3.6715263157894744e-05,
      "loss": 0.1769,
      "step": 131
    },
    {
      "epoch": 0.19158200290275762,
      "grad_norm": 0.09322332590818405,
      "learning_rate": 3.6183157894736845e-05,
      "loss": 0.2052,
      "step": 132
    },
    {
      "epoch": 0.193033381712627,
      "grad_norm": 0.12875616550445557,
      "learning_rate": 3.565105263157895e-05,
      "loss": 0.1961,
      "step": 133
    },
    {
      "epoch": 0.19448476052249636,
      "grad_norm": 0.11314037442207336,
      "learning_rate": 3.5118947368421055e-05,
      "loss": 0.2227,
      "step": 134
    },
    {
      "epoch": 0.19593613933236576,
      "grad_norm": 0.10332886129617691,
      "learning_rate": 3.458684210526316e-05,
      "loss": 0.339,
      "step": 135
    },
    {
      "epoch": 0.19738751814223512,
      "grad_norm": 0.17729254066944122,
      "learning_rate": 3.4054736842105265e-05,
      "loss": 0.2802,
      "step": 136
    },
    {
      "epoch": 0.1988388969521045,
      "grad_norm": 0.08777690678834915,
      "learning_rate": 3.3522631578947366e-05,
      "loss": 0.1391,
      "step": 137
    },
    {
      "epoch": 0.20029027576197386,
      "grad_norm": 0.1536087989807129,
      "learning_rate": 3.2990526315789475e-05,
      "loss": 0.3643,
      "step": 138
    },
    {
      "epoch": 0.20174165457184326,
      "grad_norm": 0.11051812022924423,
      "learning_rate": 3.245842105263158e-05,
      "loss": 0.1991,
      "step": 139
    },
    {
      "epoch": 0.20319303338171263,
      "grad_norm": 0.09295262396335602,
      "learning_rate": 3.1926315789473685e-05,
      "loss": 0.2913,
      "step": 140
    },
    {
      "epoch": 0.204644412191582,
      "grad_norm": 0.13505689799785614,
      "learning_rate": 3.139421052631579e-05,
      "loss": 0.8371,
      "step": 141
    },
    {
      "epoch": 0.20609579100145137,
      "grad_norm": 0.1267169862985611,
      "learning_rate": 3.0862105263157894e-05,
      "loss": 0.6024,
      "step": 142
    },
    {
      "epoch": 0.20754716981132076,
      "grad_norm": 0.13407814502716064,
      "learning_rate": 3.033e-05,
      "loss": 0.4159,
      "step": 143
    },
    {
      "epoch": 0.20899854862119013,
      "grad_norm": 0.11469519138336182,
      "learning_rate": 2.9797894736842104e-05,
      "loss": 0.2402,
      "step": 144
    },
    {
      "epoch": 0.2104499274310595,
      "grad_norm": 0.169059157371521,
      "learning_rate": 2.9265789473684213e-05,
      "loss": 0.3534,
      "step": 145
    },
    {
      "epoch": 0.21190130624092887,
      "grad_norm": 0.19773763418197632,
      "learning_rate": 2.8733684210526317e-05,
      "loss": 0.5001,
      "step": 146
    },
    {
      "epoch": 0.21335268505079827,
      "grad_norm": 0.4277418553829193,
      "learning_rate": 2.820157894736842e-05,
      "loss": 0.7581,
      "step": 147
    },
    {
      "epoch": 0.21480406386066764,
      "grad_norm": 0.2791711688041687,
      "learning_rate": 2.766947368421053e-05,
      "loss": 0.8721,
      "step": 148
    },
    {
      "epoch": 0.216255442670537,
      "grad_norm": 0.40901464223861694,
      "learning_rate": 2.7137368421052632e-05,
      "loss": 0.8766,
      "step": 149
    },
    {
      "epoch": 0.21770682148040638,
      "grad_norm": 0.39813101291656494,
      "learning_rate": 2.6605263157894737e-05,
      "loss": 0.5074,
      "step": 150
    },
    {
      "epoch": 0.21770682148040638,
      "eval_loss": 0.23037858307361603,
      "eval_runtime": 143.626,
      "eval_samples_per_second": 2.026,
      "eval_steps_per_second": 0.508,
      "step": 150
    },
    {
      "epoch": 0.21915820029027577,
      "grad_norm": 0.16082116961479187,
      "learning_rate": 2.6073157894736845e-05,
      "loss": 1.008,
      "step": 151
    },
    {
      "epoch": 0.22060957910014514,
      "grad_norm": 0.17968745529651642,
      "learning_rate": 2.554105263157895e-05,
      "loss": 0.8331,
      "step": 152
    },
    {
      "epoch": 0.2220609579100145,
      "grad_norm": 0.17362633347511292,
      "learning_rate": 2.5008947368421052e-05,
      "loss": 0.5327,
      "step": 153
    },
    {
      "epoch": 0.22351233671988388,
      "grad_norm": 0.1643386036157608,
      "learning_rate": 2.447684210526316e-05,
      "loss": 1.0695,
      "step": 154
    },
    {
      "epoch": 0.22496371552975328,
      "grad_norm": 0.12344465404748917,
      "learning_rate": 2.3944736842105262e-05,
      "loss": 0.5125,
      "step": 155
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 0.2044529914855957,
      "learning_rate": 2.341263157894737e-05,
      "loss": 1.0597,
      "step": 156
    },
    {
      "epoch": 0.22786647314949202,
      "grad_norm": 0.1536094695329666,
      "learning_rate": 2.2880526315789475e-05,
      "loss": 0.2413,
      "step": 157
    },
    {
      "epoch": 0.22931785195936139,
      "grad_norm": 0.16920588910579681,
      "learning_rate": 2.234842105263158e-05,
      "loss": 0.7497,
      "step": 158
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.12118630111217499,
      "learning_rate": 2.1816315789473685e-05,
      "loss": 0.3208,
      "step": 159
    },
    {
      "epoch": 0.23222060957910015,
      "grad_norm": 0.14840605854988098,
      "learning_rate": 2.128421052631579e-05,
      "loss": 0.387,
      "step": 160
    },
    {
      "epoch": 0.23367198838896952,
      "grad_norm": 0.10502210259437561,
      "learning_rate": 2.0752105263157895e-05,
      "loss": 0.4105,
      "step": 161
    },
    {
      "epoch": 0.2351233671988389,
      "grad_norm": 0.23360522091388702,
      "learning_rate": 2.0220000000000003e-05,
      "loss": 0.4883,
      "step": 162
    },
    {
      "epoch": 0.2365747460087083,
      "grad_norm": 0.1557024121284485,
      "learning_rate": 1.9687894736842104e-05,
      "loss": 0.3857,
      "step": 163
    },
    {
      "epoch": 0.23802612481857766,
      "grad_norm": 0.15826496481895447,
      "learning_rate": 1.9155789473684213e-05,
      "loss": 0.8257,
      "step": 164
    },
    {
      "epoch": 0.23947750362844702,
      "grad_norm": 0.12281662970781326,
      "learning_rate": 1.8623684210526314e-05,
      "loss": 0.398,
      "step": 165
    },
    {
      "epoch": 0.2409288824383164,
      "grad_norm": 0.17840005457401276,
      "learning_rate": 1.8091578947368423e-05,
      "loss": 1.0399,
      "step": 166
    },
    {
      "epoch": 0.24238026124818576,
      "grad_norm": 0.2307438999414444,
      "learning_rate": 1.7559473684210528e-05,
      "loss": 0.6128,
      "step": 167
    },
    {
      "epoch": 0.24383164005805516,
      "grad_norm": 0.12274490296840668,
      "learning_rate": 1.7027368421052632e-05,
      "loss": 0.3564,
      "step": 168
    },
    {
      "epoch": 0.24528301886792453,
      "grad_norm": 0.12504906952381134,
      "learning_rate": 1.6495263157894737e-05,
      "loss": 0.5111,
      "step": 169
    },
    {
      "epoch": 0.2467343976777939,
      "grad_norm": 0.10843324661254883,
      "learning_rate": 1.5963157894736842e-05,
      "loss": 0.3324,
      "step": 170
    },
    {
      "epoch": 0.24818577648766327,
      "grad_norm": 0.12919478118419647,
      "learning_rate": 1.5431052631578947e-05,
      "loss": 0.3152,
      "step": 171
    },
    {
      "epoch": 0.24963715529753266,
      "grad_norm": 0.19524158537387848,
      "learning_rate": 1.4898947368421052e-05,
      "loss": 0.4494,
      "step": 172
    },
    {
      "epoch": 0.251088534107402,
      "grad_norm": 0.13108614087104797,
      "learning_rate": 1.4366842105263159e-05,
      "loss": 0.2326,
      "step": 173
    },
    {
      "epoch": 0.2525399129172714,
      "grad_norm": 0.09462467581033707,
      "learning_rate": 1.3834736842105265e-05,
      "loss": 0.3285,
      "step": 174
    },
    {
      "epoch": 0.2539912917271408,
      "grad_norm": 0.11037827283143997,
      "learning_rate": 1.3302631578947369e-05,
      "loss": 0.3239,
      "step": 175
    },
    {
      "epoch": 0.25544267053701014,
      "grad_norm": 0.13191723823547363,
      "learning_rate": 1.2770526315789475e-05,
      "loss": 0.9917,
      "step": 176
    },
    {
      "epoch": 0.25689404934687954,
      "grad_norm": 0.11104253679513931,
      "learning_rate": 1.223842105263158e-05,
      "loss": 0.3113,
      "step": 177
    },
    {
      "epoch": 0.25834542815674894,
      "grad_norm": 0.16667191684246063,
      "learning_rate": 1.1706315789473685e-05,
      "loss": 0.5103,
      "step": 178
    },
    {
      "epoch": 0.2597968069666183,
      "grad_norm": 0.13359755277633667,
      "learning_rate": 1.117421052631579e-05,
      "loss": 0.5022,
      "step": 179
    },
    {
      "epoch": 0.2612481857764877,
      "grad_norm": 0.11774896085262299,
      "learning_rate": 1.0642105263157895e-05,
      "loss": 0.2854,
      "step": 180
    },
    {
      "epoch": 0.262699564586357,
      "grad_norm": 0.14967772364616394,
      "learning_rate": 1.0110000000000001e-05,
      "loss": 0.3724,
      "step": 181
    },
    {
      "epoch": 0.2641509433962264,
      "grad_norm": 0.17375238239765167,
      "learning_rate": 9.577894736842106e-06,
      "loss": 0.5366,
      "step": 182
    },
    {
      "epoch": 0.2656023222060958,
      "grad_norm": 0.12037857621908188,
      "learning_rate": 9.045789473684211e-06,
      "loss": 0.2978,
      "step": 183
    },
    {
      "epoch": 0.26705370101596515,
      "grad_norm": 0.09681455045938492,
      "learning_rate": 8.513684210526316e-06,
      "loss": 0.2166,
      "step": 184
    },
    {
      "epoch": 0.26850507982583455,
      "grad_norm": 0.09586142748594284,
      "learning_rate": 7.981578947368421e-06,
      "loss": 0.655,
      "step": 185
    },
    {
      "epoch": 0.26995645863570394,
      "grad_norm": 0.09345651417970657,
      "learning_rate": 7.449473684210526e-06,
      "loss": 0.2769,
      "step": 186
    },
    {
      "epoch": 0.2714078374455733,
      "grad_norm": 0.09641759097576141,
      "learning_rate": 6.917368421052633e-06,
      "loss": 0.2374,
      "step": 187
    },
    {
      "epoch": 0.2728592162554427,
      "grad_norm": 0.12996430695056915,
      "learning_rate": 6.385263157894738e-06,
      "loss": 0.2477,
      "step": 188
    },
    {
      "epoch": 0.274310595065312,
      "grad_norm": 0.14311741292476654,
      "learning_rate": 5.8531578947368425e-06,
      "loss": 0.2815,
      "step": 189
    },
    {
      "epoch": 0.2757619738751814,
      "grad_norm": 0.12616676092147827,
      "learning_rate": 5.321052631578947e-06,
      "loss": 0.2024,
      "step": 190
    },
    {
      "epoch": 0.2772133526850508,
      "grad_norm": 0.10585512220859528,
      "learning_rate": 4.788947368421053e-06,
      "loss": 0.2822,
      "step": 191
    },
    {
      "epoch": 0.27866473149492016,
      "grad_norm": 0.1168060377240181,
      "learning_rate": 4.256842105263158e-06,
      "loss": 0.1666,
      "step": 192
    },
    {
      "epoch": 0.28011611030478956,
      "grad_norm": 0.12357722222805023,
      "learning_rate": 3.724736842105263e-06,
      "loss": 0.4234,
      "step": 193
    },
    {
      "epoch": 0.28156748911465895,
      "grad_norm": 0.1898827701807022,
      "learning_rate": 3.192631578947369e-06,
      "loss": 0.426,
      "step": 194
    },
    {
      "epoch": 0.2830188679245283,
      "grad_norm": 0.2734042704105377,
      "learning_rate": 2.6605263157894737e-06,
      "loss": 0.8311,
      "step": 195
    },
    {
      "epoch": 0.2844702467343977,
      "grad_norm": 0.23327644169330597,
      "learning_rate": 2.128421052631579e-06,
      "loss": 0.8963,
      "step": 196
    },
    {
      "epoch": 0.28592162554426703,
      "grad_norm": 0.23755201697349548,
      "learning_rate": 1.5963157894736844e-06,
      "loss": 0.6194,
      "step": 197
    },
    {
      "epoch": 0.28737300435413643,
      "grad_norm": 0.3003562390804291,
      "learning_rate": 1.0642105263157895e-06,
      "loss": 0.6794,
      "step": 198
    },
    {
      "epoch": 0.2888243831640058,
      "grad_norm": 0.45043861865997314,
      "learning_rate": 5.321052631578948e-07,
      "loss": 0.6781,
      "step": 199
    },
    {
      "epoch": 0.29027576197387517,
      "grad_norm": 0.43113571405410767,
      "learning_rate": 0.0,
      "loss": 1.0902,
      "step": 200
    },
    {
      "epoch": 0.29027576197387517,
      "eval_loss": 0.22681911289691925,
      "eval_runtime": 144.9273,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 0.504,
      "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": 2.4053840999350272e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}