1JV40 / checkpoint-1200 /trainer_state.json
gotzmann's picture
..
236d374
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5349977708426215,
"eval_steps": 500,
"global_step": 1200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00044583147570218456,
"grad_norm": 0.10423856973648071,
"learning_rate": 3.3333333333333335e-07,
"loss": 1.9488,
"step": 1
},
{
"epoch": 0.0008916629514043691,
"grad_norm": 0.10813002288341522,
"learning_rate": 6.666666666666667e-07,
"loss": 1.9474,
"step": 2
},
{
"epoch": 0.0013374944271065537,
"grad_norm": 0.13352718949317932,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.9654,
"step": 3
},
{
"epoch": 0.0017833259028087382,
"grad_norm": 0.11386530101299286,
"learning_rate": 1.3333333333333334e-06,
"loss": 2.0172,
"step": 4
},
{
"epoch": 0.002229157378510923,
"grad_norm": 0.10593927651643753,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.9729,
"step": 5
},
{
"epoch": 0.0026749888542131075,
"grad_norm": 0.10731954127550125,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9314,
"step": 6
},
{
"epoch": 0.003120820329915292,
"grad_norm": 0.10392794013023376,
"learning_rate": 2.3333333333333336e-06,
"loss": 1.9591,
"step": 7
},
{
"epoch": 0.0035666518056174765,
"grad_norm": 0.10585840791463852,
"learning_rate": 2.666666666666667e-06,
"loss": 1.9559,
"step": 8
},
{
"epoch": 0.004012483281319661,
"grad_norm": 0.10271352529525757,
"learning_rate": 3e-06,
"loss": 1.9194,
"step": 9
},
{
"epoch": 0.004458314757021846,
"grad_norm": 0.11222607642412186,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.9589,
"step": 10
},
{
"epoch": 0.00490414623272403,
"grad_norm": 0.10449521243572235,
"learning_rate": 3.666666666666667e-06,
"loss": 1.9387,
"step": 11
},
{
"epoch": 0.005349977708426215,
"grad_norm": 0.1069161519408226,
"learning_rate": 4.000000000000001e-06,
"loss": 1.9573,
"step": 12
},
{
"epoch": 0.0057958091841284,
"grad_norm": 0.10176628082990646,
"learning_rate": 4.333333333333334e-06,
"loss": 1.9766,
"step": 13
},
{
"epoch": 0.006241640659830584,
"grad_norm": 0.10261520743370056,
"learning_rate": 4.666666666666667e-06,
"loss": 1.8744,
"step": 14
},
{
"epoch": 0.006687472135532769,
"grad_norm": 0.09846219420433044,
"learning_rate": 5e-06,
"loss": 1.9489,
"step": 15
},
{
"epoch": 0.007133303611234953,
"grad_norm": 0.10115073621273041,
"learning_rate": 5.333333333333334e-06,
"loss": 1.9241,
"step": 16
},
{
"epoch": 0.007579135086937138,
"grad_norm": 0.10709471255540848,
"learning_rate": 5.666666666666667e-06,
"loss": 1.936,
"step": 17
},
{
"epoch": 0.008024966562639322,
"grad_norm": 0.09787040203809738,
"learning_rate": 6e-06,
"loss": 1.8657,
"step": 18
},
{
"epoch": 0.008470798038341507,
"grad_norm": 0.09923889487981796,
"learning_rate": 6.333333333333334e-06,
"loss": 1.9763,
"step": 19
},
{
"epoch": 0.008916629514043692,
"grad_norm": 0.095713771879673,
"learning_rate": 6.666666666666667e-06,
"loss": 1.8895,
"step": 20
},
{
"epoch": 0.009362460989745877,
"grad_norm": 0.10209499299526215,
"learning_rate": 7.000000000000001e-06,
"loss": 1.9894,
"step": 21
},
{
"epoch": 0.00980829246544806,
"grad_norm": 0.09892246127128601,
"learning_rate": 7.333333333333334e-06,
"loss": 1.9851,
"step": 22
},
{
"epoch": 0.010254123941150245,
"grad_norm": 0.09476877003908157,
"learning_rate": 7.666666666666667e-06,
"loss": 1.9395,
"step": 23
},
{
"epoch": 0.01069995541685243,
"grad_norm": 0.09823001176118851,
"learning_rate": 8.000000000000001e-06,
"loss": 2.0785,
"step": 24
},
{
"epoch": 0.011145786892554615,
"grad_norm": 0.0935964435338974,
"learning_rate": 8.333333333333334e-06,
"loss": 1.9837,
"step": 25
},
{
"epoch": 0.0115916183682568,
"grad_norm": 0.08850236237049103,
"learning_rate": 8.666666666666668e-06,
"loss": 1.9555,
"step": 26
},
{
"epoch": 0.012037449843958983,
"grad_norm": 0.08738856762647629,
"learning_rate": 9e-06,
"loss": 1.8958,
"step": 27
},
{
"epoch": 0.012483281319661168,
"grad_norm": 0.09425712376832962,
"learning_rate": 9.333333333333334e-06,
"loss": 2.0588,
"step": 28
},
{
"epoch": 0.012929112795363353,
"grad_norm": 0.0860859751701355,
"learning_rate": 9.666666666666667e-06,
"loss": 1.891,
"step": 29
},
{
"epoch": 0.013374944271065538,
"grad_norm": 0.08535051345825195,
"learning_rate": 1e-05,
"loss": 1.9581,
"step": 30
},
{
"epoch": 0.013820775746767721,
"grad_norm": 0.08573435992002487,
"learning_rate": 1.0333333333333333e-05,
"loss": 1.998,
"step": 31
},
{
"epoch": 0.014266607222469906,
"grad_norm": 0.0800488144159317,
"learning_rate": 1.0666666666666667e-05,
"loss": 1.8467,
"step": 32
},
{
"epoch": 0.014712438698172091,
"grad_norm": 0.08866122364997864,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.8928,
"step": 33
},
{
"epoch": 0.015158270173874276,
"grad_norm": 0.09095121175050735,
"learning_rate": 1.1333333333333334e-05,
"loss": 2.0211,
"step": 34
},
{
"epoch": 0.01560410164957646,
"grad_norm": 0.07572831213474274,
"learning_rate": 1.1666666666666668e-05,
"loss": 1.8825,
"step": 35
},
{
"epoch": 0.016049933125278644,
"grad_norm": 0.09133413434028625,
"learning_rate": 1.2e-05,
"loss": 1.8602,
"step": 36
},
{
"epoch": 0.01649576460098083,
"grad_norm": 0.07954571396112442,
"learning_rate": 1.2333333333333334e-05,
"loss": 1.9187,
"step": 37
},
{
"epoch": 0.016941596076683014,
"grad_norm": 0.0792507454752922,
"learning_rate": 1.2666666666666668e-05,
"loss": 1.8477,
"step": 38
},
{
"epoch": 0.017387427552385197,
"grad_norm": 0.08049960434436798,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.9064,
"step": 39
},
{
"epoch": 0.017833259028087384,
"grad_norm": 0.08327354490756989,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.8791,
"step": 40
},
{
"epoch": 0.018279090503789567,
"grad_norm": 0.08076730370521545,
"learning_rate": 1.3666666666666666e-05,
"loss": 1.9301,
"step": 41
},
{
"epoch": 0.018724921979491754,
"grad_norm": 0.08497586846351624,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.9438,
"step": 42
},
{
"epoch": 0.019170753455193937,
"grad_norm": 0.0735197588801384,
"learning_rate": 1.4333333333333334e-05,
"loss": 1.9657,
"step": 43
},
{
"epoch": 0.01961658493089612,
"grad_norm": 0.07074163854122162,
"learning_rate": 1.4666666666666668e-05,
"loss": 1.8078,
"step": 44
},
{
"epoch": 0.020062416406598307,
"grad_norm": 0.07036347687244415,
"learning_rate": 1.5e-05,
"loss": 1.8855,
"step": 45
},
{
"epoch": 0.02050824788230049,
"grad_norm": 0.07190372049808502,
"learning_rate": 1.5333333333333334e-05,
"loss": 1.931,
"step": 46
},
{
"epoch": 0.020954079358002677,
"grad_norm": 0.07255047559738159,
"learning_rate": 1.5666666666666667e-05,
"loss": 1.9214,
"step": 47
},
{
"epoch": 0.02139991083370486,
"grad_norm": 0.07436538487672806,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.8536,
"step": 48
},
{
"epoch": 0.021845742309407043,
"grad_norm": 0.07510672509670258,
"learning_rate": 1.6333333333333335e-05,
"loss": 1.9324,
"step": 49
},
{
"epoch": 0.02229157378510923,
"grad_norm": 0.07370635122060776,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.9828,
"step": 50
},
{
"epoch": 0.022737405260811413,
"grad_norm": 0.07711168378591537,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.8377,
"step": 51
},
{
"epoch": 0.0231832367365136,
"grad_norm": 0.07036629319190979,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.9043,
"step": 52
},
{
"epoch": 0.023629068212215783,
"grad_norm": 0.07015162706375122,
"learning_rate": 1.7666666666666668e-05,
"loss": 1.7712,
"step": 53
},
{
"epoch": 0.024074899687917966,
"grad_norm": 0.06866791844367981,
"learning_rate": 1.8e-05,
"loss": 1.8817,
"step": 54
},
{
"epoch": 0.024520731163620153,
"grad_norm": 0.07089275121688843,
"learning_rate": 1.8333333333333333e-05,
"loss": 1.8644,
"step": 55
},
{
"epoch": 0.024966562639322336,
"grad_norm": 0.07659879326820374,
"learning_rate": 1.866666666666667e-05,
"loss": 1.8811,
"step": 56
},
{
"epoch": 0.02541239411502452,
"grad_norm": 0.07733659446239471,
"learning_rate": 1.9e-05,
"loss": 1.9908,
"step": 57
},
{
"epoch": 0.025858225590726706,
"grad_norm": 0.07130070775747299,
"learning_rate": 1.9333333333333333e-05,
"loss": 1.8858,
"step": 58
},
{
"epoch": 0.02630405706642889,
"grad_norm": 0.07780032604932785,
"learning_rate": 1.9666666666666666e-05,
"loss": 1.9691,
"step": 59
},
{
"epoch": 0.026749888542131076,
"grad_norm": 0.07684481143951416,
"learning_rate": 2e-05,
"loss": 1.8768,
"step": 60
},
{
"epoch": 0.02719572001783326,
"grad_norm": 0.07115636020898819,
"learning_rate": 2.0333333333333334e-05,
"loss": 1.8523,
"step": 61
},
{
"epoch": 0.027641551493535442,
"grad_norm": 0.07196246832609177,
"learning_rate": 2.0666666666666666e-05,
"loss": 1.8914,
"step": 62
},
{
"epoch": 0.02808738296923763,
"grad_norm": 0.07760903984308243,
"learning_rate": 2.1e-05,
"loss": 1.9884,
"step": 63
},
{
"epoch": 0.028533214444939812,
"grad_norm": 0.07473624497652054,
"learning_rate": 2.1333333333333335e-05,
"loss": 1.8086,
"step": 64
},
{
"epoch": 0.028979045920642,
"grad_norm": 0.07975806295871735,
"learning_rate": 2.1666666666666667e-05,
"loss": 1.8901,
"step": 65
},
{
"epoch": 0.029424877396344182,
"grad_norm": 0.07289416342973709,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.875,
"step": 66
},
{
"epoch": 0.029870708872046365,
"grad_norm": 0.07153280079364777,
"learning_rate": 2.2333333333333335e-05,
"loss": 1.7612,
"step": 67
},
{
"epoch": 0.03031654034774855,
"grad_norm": 0.07313098013401031,
"learning_rate": 2.2666666666666668e-05,
"loss": 1.8024,
"step": 68
},
{
"epoch": 0.030762371823450735,
"grad_norm": 0.07462003827095032,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.8417,
"step": 69
},
{
"epoch": 0.03120820329915292,
"grad_norm": 0.07891552895307541,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.8885,
"step": 70
},
{
"epoch": 0.03165403477485511,
"grad_norm": 0.07920385897159576,
"learning_rate": 2.3666666666666668e-05,
"loss": 1.929,
"step": 71
},
{
"epoch": 0.03209986625055729,
"grad_norm": 0.07741603255271912,
"learning_rate": 2.4e-05,
"loss": 1.8428,
"step": 72
},
{
"epoch": 0.032545697726259475,
"grad_norm": 0.0745483934879303,
"learning_rate": 2.4333333333333336e-05,
"loss": 1.8103,
"step": 73
},
{
"epoch": 0.03299152920196166,
"grad_norm": 0.07898657768964767,
"learning_rate": 2.466666666666667e-05,
"loss": 1.8841,
"step": 74
},
{
"epoch": 0.03343736067766384,
"grad_norm": 0.07699943333864212,
"learning_rate": 2.5e-05,
"loss": 1.8779,
"step": 75
},
{
"epoch": 0.03388319215336603,
"grad_norm": 0.07939334958791733,
"learning_rate": 2.5333333333333337e-05,
"loss": 1.8496,
"step": 76
},
{
"epoch": 0.034329023629068214,
"grad_norm": 0.08121130615472794,
"learning_rate": 2.5666666666666666e-05,
"loss": 1.8947,
"step": 77
},
{
"epoch": 0.034774855104770394,
"grad_norm": 0.08611540496349335,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.8245,
"step": 78
},
{
"epoch": 0.03522068658047258,
"grad_norm": 0.07946460694074631,
"learning_rate": 2.633333333333333e-05,
"loss": 1.8388,
"step": 79
},
{
"epoch": 0.03566651805617477,
"grad_norm": 0.08703707158565521,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.8888,
"step": 80
},
{
"epoch": 0.03611234953187695,
"grad_norm": 0.08215127140283585,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.8866,
"step": 81
},
{
"epoch": 0.036558181007579134,
"grad_norm": 0.08106034994125366,
"learning_rate": 2.733333333333333e-05,
"loss": 1.7895,
"step": 82
},
{
"epoch": 0.03700401248328132,
"grad_norm": 0.08074768632650375,
"learning_rate": 2.7666666666666667e-05,
"loss": 1.7427,
"step": 83
},
{
"epoch": 0.03744984395898351,
"grad_norm": 0.08647580444812775,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.8377,
"step": 84
},
{
"epoch": 0.03789567543468569,
"grad_norm": 0.08676984161138535,
"learning_rate": 2.8333333333333335e-05,
"loss": 1.8171,
"step": 85
},
{
"epoch": 0.038341506910387874,
"grad_norm": 0.08840702474117279,
"learning_rate": 2.8666666666666668e-05,
"loss": 1.8944,
"step": 86
},
{
"epoch": 0.03878733838609006,
"grad_norm": 0.08388784527778625,
"learning_rate": 2.9e-05,
"loss": 1.8239,
"step": 87
},
{
"epoch": 0.03923316986179224,
"grad_norm": 0.08576168864965439,
"learning_rate": 2.9333333333333336e-05,
"loss": 1.8192,
"step": 88
},
{
"epoch": 0.03967900133749443,
"grad_norm": 0.09376898407936096,
"learning_rate": 2.9666666666666672e-05,
"loss": 1.8152,
"step": 89
},
{
"epoch": 0.04012483281319661,
"grad_norm": 0.08985846489667892,
"learning_rate": 3e-05,
"loss": 1.8538,
"step": 90
},
{
"epoch": 0.04057066428889879,
"grad_norm": 0.08676113933324814,
"learning_rate": 3.0333333333333337e-05,
"loss": 1.9206,
"step": 91
},
{
"epoch": 0.04101649576460098,
"grad_norm": 0.08664020150899887,
"learning_rate": 3.066666666666667e-05,
"loss": 1.8355,
"step": 92
},
{
"epoch": 0.041462327240303166,
"grad_norm": 0.09110575169324875,
"learning_rate": 3.1e-05,
"loss": 1.8644,
"step": 93
},
{
"epoch": 0.04190815871600535,
"grad_norm": 0.0922502875328064,
"learning_rate": 3.1333333333333334e-05,
"loss": 1.8677,
"step": 94
},
{
"epoch": 0.04235399019170753,
"grad_norm": 0.08949128538370132,
"learning_rate": 3.1666666666666666e-05,
"loss": 1.815,
"step": 95
},
{
"epoch": 0.04279982166740972,
"grad_norm": 0.08968576043844223,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.8415,
"step": 96
},
{
"epoch": 0.043245653143111906,
"grad_norm": 0.08726249635219574,
"learning_rate": 3.233333333333333e-05,
"loss": 1.797,
"step": 97
},
{
"epoch": 0.043691484618814086,
"grad_norm": 0.09136708825826645,
"learning_rate": 3.266666666666667e-05,
"loss": 1.8511,
"step": 98
},
{
"epoch": 0.04413731609451627,
"grad_norm": 0.09381388127803802,
"learning_rate": 3.3e-05,
"loss": 1.9088,
"step": 99
},
{
"epoch": 0.04458314757021846,
"grad_norm": 0.09526460617780685,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.9403,
"step": 100
},
{
"epoch": 0.04502897904592064,
"grad_norm": 0.09598744660615921,
"learning_rate": 3.366666666666667e-05,
"loss": 1.9012,
"step": 101
},
{
"epoch": 0.045474810521622826,
"grad_norm": 0.09727242588996887,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.9029,
"step": 102
},
{
"epoch": 0.04592064199732501,
"grad_norm": 0.09639915078878403,
"learning_rate": 3.433333333333333e-05,
"loss": 1.8091,
"step": 103
},
{
"epoch": 0.0463664734730272,
"grad_norm": 0.10184083878993988,
"learning_rate": 3.466666666666667e-05,
"loss": 1.7931,
"step": 104
},
{
"epoch": 0.04681230494872938,
"grad_norm": 0.10028352588415146,
"learning_rate": 3.5e-05,
"loss": 1.8443,
"step": 105
},
{
"epoch": 0.047258136424431565,
"grad_norm": 0.10898778587579727,
"learning_rate": 3.5333333333333336e-05,
"loss": 1.9108,
"step": 106
},
{
"epoch": 0.04770396790013375,
"grad_norm": 0.10193369537591934,
"learning_rate": 3.566666666666667e-05,
"loss": 1.8807,
"step": 107
},
{
"epoch": 0.04814979937583593,
"grad_norm": 0.09831596165895462,
"learning_rate": 3.6e-05,
"loss": 1.7794,
"step": 108
},
{
"epoch": 0.04859563085153812,
"grad_norm": 0.10062552988529205,
"learning_rate": 3.633333333333333e-05,
"loss": 1.8504,
"step": 109
},
{
"epoch": 0.049041462327240305,
"grad_norm": 0.0957321897149086,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.821,
"step": 110
},
{
"epoch": 0.049487293802942485,
"grad_norm": 0.1039716973900795,
"learning_rate": 3.7e-05,
"loss": 1.8609,
"step": 111
},
{
"epoch": 0.04993312527864467,
"grad_norm": 0.1005842313170433,
"learning_rate": 3.733333333333334e-05,
"loss": 1.8794,
"step": 112
},
{
"epoch": 0.05037895675434686,
"grad_norm": 0.10597317665815353,
"learning_rate": 3.766666666666667e-05,
"loss": 1.7747,
"step": 113
},
{
"epoch": 0.05082478823004904,
"grad_norm": 0.10866290330886841,
"learning_rate": 3.8e-05,
"loss": 1.8174,
"step": 114
},
{
"epoch": 0.051270619705751225,
"grad_norm": 0.09833931922912598,
"learning_rate": 3.8333333333333334e-05,
"loss": 1.8223,
"step": 115
},
{
"epoch": 0.05171645118145341,
"grad_norm": 0.10864105820655823,
"learning_rate": 3.866666666666667e-05,
"loss": 1.9618,
"step": 116
},
{
"epoch": 0.0521622826571556,
"grad_norm": 0.11741501092910767,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.7435,
"step": 117
},
{
"epoch": 0.05260811413285778,
"grad_norm": 0.09669601172208786,
"learning_rate": 3.933333333333333e-05,
"loss": 1.7074,
"step": 118
},
{
"epoch": 0.053053945608559964,
"grad_norm": 0.126326322555542,
"learning_rate": 3.966666666666667e-05,
"loss": 1.8623,
"step": 119
},
{
"epoch": 0.05349977708426215,
"grad_norm": 0.11295739561319351,
"learning_rate": 4e-05,
"loss": 1.8134,
"step": 120
},
{
"epoch": 0.05394560855996433,
"grad_norm": 0.1026206985116005,
"learning_rate": 4.0333333333333336e-05,
"loss": 1.8356,
"step": 121
},
{
"epoch": 0.05439144003566652,
"grad_norm": 0.11249936372041702,
"learning_rate": 4.066666666666667e-05,
"loss": 1.8636,
"step": 122
},
{
"epoch": 0.054837271511368704,
"grad_norm": 0.11658084392547607,
"learning_rate": 4.1e-05,
"loss": 1.8745,
"step": 123
},
{
"epoch": 0.055283102987070884,
"grad_norm": 0.12195635586977005,
"learning_rate": 4.133333333333333e-05,
"loss": 1.8901,
"step": 124
},
{
"epoch": 0.05572893446277307,
"grad_norm": 0.11015114188194275,
"learning_rate": 4.166666666666667e-05,
"loss": 1.9296,
"step": 125
},
{
"epoch": 0.05617476593847526,
"grad_norm": 0.11404122412204742,
"learning_rate": 4.2e-05,
"loss": 1.8388,
"step": 126
},
{
"epoch": 0.056620597414177444,
"grad_norm": 0.13313397765159607,
"learning_rate": 4.233333333333334e-05,
"loss": 1.9823,
"step": 127
},
{
"epoch": 0.057066428889879624,
"grad_norm": 0.12235371023416519,
"learning_rate": 4.266666666666667e-05,
"loss": 1.9226,
"step": 128
},
{
"epoch": 0.05751226036558181,
"grad_norm": 0.11677171289920807,
"learning_rate": 4.3e-05,
"loss": 1.8513,
"step": 129
},
{
"epoch": 0.057958091841284,
"grad_norm": 0.10917484015226364,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.851,
"step": 130
},
{
"epoch": 0.05840392331698618,
"grad_norm": 0.12595924735069275,
"learning_rate": 4.3666666666666666e-05,
"loss": 1.8324,
"step": 131
},
{
"epoch": 0.058849754792688364,
"grad_norm": 0.11695687472820282,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.8382,
"step": 132
},
{
"epoch": 0.05929558626839055,
"grad_norm": 0.11873079836368561,
"learning_rate": 4.433333333333334e-05,
"loss": 1.8008,
"step": 133
},
{
"epoch": 0.05974141774409273,
"grad_norm": 0.12881365418434143,
"learning_rate": 4.466666666666667e-05,
"loss": 1.867,
"step": 134
},
{
"epoch": 0.06018724921979492,
"grad_norm": 0.12599585950374603,
"learning_rate": 4.5e-05,
"loss": 1.8688,
"step": 135
},
{
"epoch": 0.0606330806954971,
"grad_norm": 0.12410257756710052,
"learning_rate": 4.5333333333333335e-05,
"loss": 1.8722,
"step": 136
},
{
"epoch": 0.06107891217119929,
"grad_norm": 0.1163187101483345,
"learning_rate": 4.566666666666667e-05,
"loss": 1.8393,
"step": 137
},
{
"epoch": 0.06152474364690147,
"grad_norm": 0.1377561092376709,
"learning_rate": 4.600000000000001e-05,
"loss": 1.906,
"step": 138
},
{
"epoch": 0.061970575122603656,
"grad_norm": 0.12081141769886017,
"learning_rate": 4.633333333333333e-05,
"loss": 1.8538,
"step": 139
},
{
"epoch": 0.06241640659830584,
"grad_norm": 0.1262594759464264,
"learning_rate": 4.666666666666667e-05,
"loss": 1.782,
"step": 140
},
{
"epoch": 0.06286223807400802,
"grad_norm": 0.1170603558421135,
"learning_rate": 4.7e-05,
"loss": 1.8245,
"step": 141
},
{
"epoch": 0.06330806954971022,
"grad_norm": 0.12051095068454742,
"learning_rate": 4.7333333333333336e-05,
"loss": 1.8787,
"step": 142
},
{
"epoch": 0.0637539010254124,
"grad_norm": 0.11356587707996368,
"learning_rate": 4.766666666666667e-05,
"loss": 1.7262,
"step": 143
},
{
"epoch": 0.06419973250111458,
"grad_norm": 0.12344677001237869,
"learning_rate": 4.8e-05,
"loss": 1.8602,
"step": 144
},
{
"epoch": 0.06464556397681677,
"grad_norm": 0.11943434178829193,
"learning_rate": 4.8333333333333334e-05,
"loss": 1.8279,
"step": 145
},
{
"epoch": 0.06509139545251895,
"grad_norm": 0.12723621726036072,
"learning_rate": 4.866666666666667e-05,
"loss": 1.9011,
"step": 146
},
{
"epoch": 0.06553722692822113,
"grad_norm": 0.11969920247793198,
"learning_rate": 4.9e-05,
"loss": 1.7878,
"step": 147
},
{
"epoch": 0.06598305840392332,
"grad_norm": 0.13341189920902252,
"learning_rate": 4.933333333333334e-05,
"loss": 1.852,
"step": 148
},
{
"epoch": 0.0664288898796255,
"grad_norm": 0.11623668670654297,
"learning_rate": 4.966666666666667e-05,
"loss": 1.7909,
"step": 149
},
{
"epoch": 0.06687472135532768,
"grad_norm": 0.13417744636535645,
"learning_rate": 5e-05,
"loss": 1.8734,
"step": 150
},
{
"epoch": 0.06732055283102988,
"grad_norm": 0.12101396173238754,
"learning_rate": 5.0333333333333335e-05,
"loss": 1.8686,
"step": 151
},
{
"epoch": 0.06776638430673206,
"grad_norm": 0.1301906257867813,
"learning_rate": 5.0666666666666674e-05,
"loss": 1.8364,
"step": 152
},
{
"epoch": 0.06821221578243424,
"grad_norm": 0.12216302007436752,
"learning_rate": 5.1000000000000006e-05,
"loss": 1.803,
"step": 153
},
{
"epoch": 0.06865804725813643,
"grad_norm": 0.1340513676404953,
"learning_rate": 5.133333333333333e-05,
"loss": 1.7806,
"step": 154
},
{
"epoch": 0.06910387873383861,
"grad_norm": 0.12899860739707947,
"learning_rate": 5.166666666666667e-05,
"loss": 1.7417,
"step": 155
},
{
"epoch": 0.06954971020954079,
"grad_norm": 0.12671636044979095,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.7643,
"step": 156
},
{
"epoch": 0.06999554168524298,
"grad_norm": 0.14671508967876434,
"learning_rate": 5.2333333333333336e-05,
"loss": 1.8264,
"step": 157
},
{
"epoch": 0.07044137316094516,
"grad_norm": 0.12344811111688614,
"learning_rate": 5.266666666666666e-05,
"loss": 1.7917,
"step": 158
},
{
"epoch": 0.07088720463664734,
"grad_norm": 0.13115648925304413,
"learning_rate": 5.300000000000001e-05,
"loss": 1.886,
"step": 159
},
{
"epoch": 0.07133303611234953,
"grad_norm": 0.13874903321266174,
"learning_rate": 5.333333333333333e-05,
"loss": 1.8985,
"step": 160
},
{
"epoch": 0.07177886758805171,
"grad_norm": 0.11615196615457535,
"learning_rate": 5.3666666666666666e-05,
"loss": 1.7575,
"step": 161
},
{
"epoch": 0.0722246990637539,
"grad_norm": 0.1384187936782837,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.8556,
"step": 162
},
{
"epoch": 0.07267053053945609,
"grad_norm": 0.11762478202581406,
"learning_rate": 5.433333333333334e-05,
"loss": 1.7721,
"step": 163
},
{
"epoch": 0.07311636201515827,
"grad_norm": 0.16673126816749573,
"learning_rate": 5.466666666666666e-05,
"loss": 1.8555,
"step": 164
},
{
"epoch": 0.07356219349086046,
"grad_norm": 0.11586098372936249,
"learning_rate": 5.500000000000001e-05,
"loss": 1.7665,
"step": 165
},
{
"epoch": 0.07400802496656264,
"grad_norm": 0.14957493543624878,
"learning_rate": 5.5333333333333334e-05,
"loss": 1.7875,
"step": 166
},
{
"epoch": 0.07445385644226482,
"grad_norm": 0.13018527626991272,
"learning_rate": 5.566666666666667e-05,
"loss": 1.836,
"step": 167
},
{
"epoch": 0.07489968791796701,
"grad_norm": 0.14033769071102142,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.8454,
"step": 168
},
{
"epoch": 0.0753455193936692,
"grad_norm": 0.13797248899936676,
"learning_rate": 5.633333333333334e-05,
"loss": 1.8244,
"step": 169
},
{
"epoch": 0.07579135086937137,
"grad_norm": 0.15225331485271454,
"learning_rate": 5.666666666666667e-05,
"loss": 1.8536,
"step": 170
},
{
"epoch": 0.07623718234507357,
"grad_norm": 0.1505601853132248,
"learning_rate": 5.6999999999999996e-05,
"loss": 1.8378,
"step": 171
},
{
"epoch": 0.07668301382077575,
"grad_norm": 0.1284462809562683,
"learning_rate": 5.7333333333333336e-05,
"loss": 1.8491,
"step": 172
},
{
"epoch": 0.07712884529647793,
"grad_norm": 0.16070091724395752,
"learning_rate": 5.766666666666667e-05,
"loss": 1.8559,
"step": 173
},
{
"epoch": 0.07757467677218012,
"grad_norm": 0.13266082108020782,
"learning_rate": 5.8e-05,
"loss": 1.8632,
"step": 174
},
{
"epoch": 0.0780205082478823,
"grad_norm": 0.1411646455526352,
"learning_rate": 5.833333333333334e-05,
"loss": 1.8275,
"step": 175
},
{
"epoch": 0.07846633972358448,
"grad_norm": 0.14225083589553833,
"learning_rate": 5.866666666666667e-05,
"loss": 1.8681,
"step": 176
},
{
"epoch": 0.07891217119928667,
"grad_norm": 0.1431555151939392,
"learning_rate": 5.9e-05,
"loss": 1.8245,
"step": 177
},
{
"epoch": 0.07935800267498885,
"grad_norm": 0.18084998428821564,
"learning_rate": 5.9333333333333343e-05,
"loss": 1.9007,
"step": 178
},
{
"epoch": 0.07980383415069103,
"grad_norm": 0.1489221304655075,
"learning_rate": 5.966666666666667e-05,
"loss": 1.785,
"step": 179
},
{
"epoch": 0.08024966562639323,
"grad_norm": 0.1899333894252777,
"learning_rate": 6e-05,
"loss": 1.9011,
"step": 180
},
{
"epoch": 0.0806954971020954,
"grad_norm": 0.13979852199554443,
"learning_rate": 6.033333333333334e-05,
"loss": 1.7573,
"step": 181
},
{
"epoch": 0.08114132857779759,
"grad_norm": 0.17329728603363037,
"learning_rate": 6.066666666666667e-05,
"loss": 1.8075,
"step": 182
},
{
"epoch": 0.08158716005349978,
"grad_norm": 0.1338491290807724,
"learning_rate": 6.1e-05,
"loss": 1.8439,
"step": 183
},
{
"epoch": 0.08203299152920196,
"grad_norm": 0.15879769623279572,
"learning_rate": 6.133333333333334e-05,
"loss": 1.7403,
"step": 184
},
{
"epoch": 0.08247882300490414,
"grad_norm": 0.12770669162273407,
"learning_rate": 6.166666666666667e-05,
"loss": 1.7707,
"step": 185
},
{
"epoch": 0.08292465448060633,
"grad_norm": 0.1499251127243042,
"learning_rate": 6.2e-05,
"loss": 1.9169,
"step": 186
},
{
"epoch": 0.08337048595630851,
"grad_norm": 0.1674559861421585,
"learning_rate": 6.233333333333334e-05,
"loss": 1.8185,
"step": 187
},
{
"epoch": 0.0838163174320107,
"grad_norm": 0.13924956321716309,
"learning_rate": 6.266666666666667e-05,
"loss": 1.8288,
"step": 188
},
{
"epoch": 0.08426214890771289,
"grad_norm": 0.14640599489212036,
"learning_rate": 6.3e-05,
"loss": 1.7566,
"step": 189
},
{
"epoch": 0.08470798038341507,
"grad_norm": 0.1331615298986435,
"learning_rate": 6.333333333333333e-05,
"loss": 1.9214,
"step": 190
},
{
"epoch": 0.08515381185911726,
"grad_norm": 0.1620808243751526,
"learning_rate": 6.366666666666668e-05,
"loss": 1.8434,
"step": 191
},
{
"epoch": 0.08559964333481944,
"grad_norm": 0.14345990121364594,
"learning_rate": 6.400000000000001e-05,
"loss": 1.8626,
"step": 192
},
{
"epoch": 0.08604547481052162,
"grad_norm": 0.1122003048658371,
"learning_rate": 6.433333333333333e-05,
"loss": 1.7087,
"step": 193
},
{
"epoch": 0.08649130628622381,
"grad_norm": 0.15594986081123352,
"learning_rate": 6.466666666666666e-05,
"loss": 1.7398,
"step": 194
},
{
"epoch": 0.08693713776192599,
"grad_norm": 0.13471178710460663,
"learning_rate": 6.500000000000001e-05,
"loss": 1.8202,
"step": 195
},
{
"epoch": 0.08738296923762817,
"grad_norm": 0.13708141446113586,
"learning_rate": 6.533333333333334e-05,
"loss": 1.8204,
"step": 196
},
{
"epoch": 0.08782880071333037,
"grad_norm": 0.1567596197128296,
"learning_rate": 6.566666666666666e-05,
"loss": 1.8187,
"step": 197
},
{
"epoch": 0.08827463218903255,
"grad_norm": 0.1181827113032341,
"learning_rate": 6.6e-05,
"loss": 1.7645,
"step": 198
},
{
"epoch": 0.08872046366473473,
"grad_norm": 0.1588752120733261,
"learning_rate": 6.633333333333334e-05,
"loss": 1.8384,
"step": 199
},
{
"epoch": 0.08916629514043692,
"grad_norm": 0.12315269559621811,
"learning_rate": 6.666666666666667e-05,
"loss": 1.8093,
"step": 200
},
{
"epoch": 0.0896121266161391,
"grad_norm": 0.1313183754682541,
"learning_rate": 6.7e-05,
"loss": 1.8466,
"step": 201
},
{
"epoch": 0.09005795809184128,
"grad_norm": 0.1488896757364273,
"learning_rate": 6.733333333333333e-05,
"loss": 1.7549,
"step": 202
},
{
"epoch": 0.09050378956754347,
"grad_norm": 0.1486813724040985,
"learning_rate": 6.766666666666667e-05,
"loss": 1.8137,
"step": 203
},
{
"epoch": 0.09094962104324565,
"grad_norm": 0.1451115906238556,
"learning_rate": 6.800000000000001e-05,
"loss": 1.8033,
"step": 204
},
{
"epoch": 0.09139545251894783,
"grad_norm": 0.1392323523759842,
"learning_rate": 6.833333333333333e-05,
"loss": 1.7548,
"step": 205
},
{
"epoch": 0.09184128399465002,
"grad_norm": 0.15712681412696838,
"learning_rate": 6.866666666666666e-05,
"loss": 1.7852,
"step": 206
},
{
"epoch": 0.0922871154703522,
"grad_norm": 0.15463602542877197,
"learning_rate": 6.9e-05,
"loss": 1.8439,
"step": 207
},
{
"epoch": 0.0927329469460544,
"grad_norm": 0.13633595407009125,
"learning_rate": 6.933333333333334e-05,
"loss": 1.8475,
"step": 208
},
{
"epoch": 0.09317877842175658,
"grad_norm": 0.16690847277641296,
"learning_rate": 6.966666666666668e-05,
"loss": 1.7705,
"step": 209
},
{
"epoch": 0.09362460989745876,
"grad_norm": 0.11522694677114487,
"learning_rate": 7e-05,
"loss": 1.7641,
"step": 210
},
{
"epoch": 0.09407044137316095,
"grad_norm": 0.1659361869096756,
"learning_rate": 7.033333333333334e-05,
"loss": 1.8308,
"step": 211
},
{
"epoch": 0.09451627284886313,
"grad_norm": 0.13584838807582855,
"learning_rate": 7.066666666666667e-05,
"loss": 1.8065,
"step": 212
},
{
"epoch": 0.09496210432456531,
"grad_norm": 0.15874630212783813,
"learning_rate": 7.1e-05,
"loss": 1.7892,
"step": 213
},
{
"epoch": 0.0954079358002675,
"grad_norm": 0.1494474858045578,
"learning_rate": 7.133333333333334e-05,
"loss": 1.8047,
"step": 214
},
{
"epoch": 0.09585376727596968,
"grad_norm": 0.13670477271080017,
"learning_rate": 7.166666666666667e-05,
"loss": 1.8259,
"step": 215
},
{
"epoch": 0.09629959875167186,
"grad_norm": 0.16313602030277252,
"learning_rate": 7.2e-05,
"loss": 1.7765,
"step": 216
},
{
"epoch": 0.09674543022737406,
"grad_norm": 0.12147438526153564,
"learning_rate": 7.233333333333335e-05,
"loss": 1.7368,
"step": 217
},
{
"epoch": 0.09719126170307624,
"grad_norm": 0.2051321268081665,
"learning_rate": 7.266666666666667e-05,
"loss": 1.827,
"step": 218
},
{
"epoch": 0.09763709317877842,
"grad_norm": 0.1401163637638092,
"learning_rate": 7.3e-05,
"loss": 1.7851,
"step": 219
},
{
"epoch": 0.09808292465448061,
"grad_norm": 0.16076582670211792,
"learning_rate": 7.333333333333333e-05,
"loss": 1.784,
"step": 220
},
{
"epoch": 0.09852875613018279,
"grad_norm": 0.14635394513607025,
"learning_rate": 7.366666666666668e-05,
"loss": 1.744,
"step": 221
},
{
"epoch": 0.09897458760588497,
"grad_norm": 0.12274181842803955,
"learning_rate": 7.4e-05,
"loss": 1.833,
"step": 222
},
{
"epoch": 0.09942041908158716,
"grad_norm": 0.1957603245973587,
"learning_rate": 7.433333333333333e-05,
"loss": 1.7604,
"step": 223
},
{
"epoch": 0.09986625055728934,
"grad_norm": 0.11970880627632141,
"learning_rate": 7.466666666666667e-05,
"loss": 1.8267,
"step": 224
},
{
"epoch": 0.10031208203299152,
"grad_norm": 0.16194678843021393,
"learning_rate": 7.500000000000001e-05,
"loss": 1.7417,
"step": 225
},
{
"epoch": 0.10075791350869372,
"grad_norm": 0.126894012093544,
"learning_rate": 7.533333333333334e-05,
"loss": 1.7558,
"step": 226
},
{
"epoch": 0.1012037449843959,
"grad_norm": 0.14502179622650146,
"learning_rate": 7.566666666666667e-05,
"loss": 1.801,
"step": 227
},
{
"epoch": 0.10164957646009808,
"grad_norm": 0.113924540579319,
"learning_rate": 7.6e-05,
"loss": 1.7844,
"step": 228
},
{
"epoch": 0.10209540793580027,
"grad_norm": 0.11642418801784515,
"learning_rate": 7.633333333333334e-05,
"loss": 1.8157,
"step": 229
},
{
"epoch": 0.10254123941150245,
"grad_norm": 0.10826003551483154,
"learning_rate": 7.666666666666667e-05,
"loss": 1.7515,
"step": 230
},
{
"epoch": 0.10298707088720464,
"grad_norm": 0.12637439370155334,
"learning_rate": 7.7e-05,
"loss": 1.8847,
"step": 231
},
{
"epoch": 0.10343290236290682,
"grad_norm": 0.12283436954021454,
"learning_rate": 7.733333333333333e-05,
"loss": 1.8646,
"step": 232
},
{
"epoch": 0.103878733838609,
"grad_norm": 0.11507835239171982,
"learning_rate": 7.766666666666667e-05,
"loss": 1.857,
"step": 233
},
{
"epoch": 0.1043245653143112,
"grad_norm": 0.11777415871620178,
"learning_rate": 7.800000000000001e-05,
"loss": 1.8737,
"step": 234
},
{
"epoch": 0.10477039679001338,
"grad_norm": 0.12522348761558533,
"learning_rate": 7.833333333333333e-05,
"loss": 1.8499,
"step": 235
},
{
"epoch": 0.10521622826571556,
"grad_norm": 0.11416588723659515,
"learning_rate": 7.866666666666666e-05,
"loss": 1.8425,
"step": 236
},
{
"epoch": 0.10566205974141775,
"grad_norm": 0.11138550192117691,
"learning_rate": 7.900000000000001e-05,
"loss": 1.6938,
"step": 237
},
{
"epoch": 0.10610789121711993,
"grad_norm": 0.12289931625127792,
"learning_rate": 7.933333333333334e-05,
"loss": 1.8677,
"step": 238
},
{
"epoch": 0.10655372269282211,
"grad_norm": 0.1108877956867218,
"learning_rate": 7.966666666666666e-05,
"loss": 1.8117,
"step": 239
},
{
"epoch": 0.1069995541685243,
"grad_norm": 0.1142394170165062,
"learning_rate": 8e-05,
"loss": 1.7759,
"step": 240
},
{
"epoch": 0.10744538564422648,
"grad_norm": 0.13339267671108246,
"learning_rate": 8.033333333333334e-05,
"loss": 1.6995,
"step": 241
},
{
"epoch": 0.10789121711992866,
"grad_norm": 0.12399157881736755,
"learning_rate": 8.066666666666667e-05,
"loss": 1.862,
"step": 242
},
{
"epoch": 0.10833704859563086,
"grad_norm": 0.1281224489212036,
"learning_rate": 8.1e-05,
"loss": 1.7483,
"step": 243
},
{
"epoch": 0.10878288007133304,
"grad_norm": 0.11970888078212738,
"learning_rate": 8.133333333333334e-05,
"loss": 1.9095,
"step": 244
},
{
"epoch": 0.10922871154703521,
"grad_norm": 0.12157970666885376,
"learning_rate": 8.166666666666667e-05,
"loss": 1.8659,
"step": 245
},
{
"epoch": 0.10967454302273741,
"grad_norm": 0.12563759088516235,
"learning_rate": 8.2e-05,
"loss": 1.7935,
"step": 246
},
{
"epoch": 0.11012037449843959,
"grad_norm": 0.118623748421669,
"learning_rate": 8.233333333333333e-05,
"loss": 1.7327,
"step": 247
},
{
"epoch": 0.11056620597414177,
"grad_norm": 0.13479459285736084,
"learning_rate": 8.266666666666667e-05,
"loss": 1.7999,
"step": 248
},
{
"epoch": 0.11101203744984396,
"grad_norm": 0.11749287694692612,
"learning_rate": 8.3e-05,
"loss": 1.776,
"step": 249
},
{
"epoch": 0.11145786892554614,
"grad_norm": 0.12336032092571259,
"learning_rate": 8.333333333333334e-05,
"loss": 1.8554,
"step": 250
},
{
"epoch": 0.11190370040124833,
"grad_norm": 0.1406543254852295,
"learning_rate": 8.366666666666668e-05,
"loss": 1.8645,
"step": 251
},
{
"epoch": 0.11234953187695051,
"grad_norm": 0.1155284196138382,
"learning_rate": 8.4e-05,
"loss": 1.7941,
"step": 252
},
{
"epoch": 0.1127953633526527,
"grad_norm": 0.12010587006807327,
"learning_rate": 8.433333333333334e-05,
"loss": 1.8269,
"step": 253
},
{
"epoch": 0.11324119482835489,
"grad_norm": 0.124538853764534,
"learning_rate": 8.466666666666667e-05,
"loss": 1.8247,
"step": 254
},
{
"epoch": 0.11368702630405707,
"grad_norm": 0.13230320811271667,
"learning_rate": 8.5e-05,
"loss": 1.8244,
"step": 255
},
{
"epoch": 0.11413285777975925,
"grad_norm": 0.1539606899023056,
"learning_rate": 8.533333333333334e-05,
"loss": 1.8008,
"step": 256
},
{
"epoch": 0.11457868925546144,
"grad_norm": 0.1316884458065033,
"learning_rate": 8.566666666666667e-05,
"loss": 1.7699,
"step": 257
},
{
"epoch": 0.11502452073116362,
"grad_norm": 0.13563507795333862,
"learning_rate": 8.6e-05,
"loss": 1.767,
"step": 258
},
{
"epoch": 0.1154703522068658,
"grad_norm": 0.13702961802482605,
"learning_rate": 8.633333333333334e-05,
"loss": 1.851,
"step": 259
},
{
"epoch": 0.115916183682568,
"grad_norm": 0.13769222795963287,
"learning_rate": 8.666666666666667e-05,
"loss": 1.681,
"step": 260
},
{
"epoch": 0.11636201515827017,
"grad_norm": 0.11334066092967987,
"learning_rate": 8.7e-05,
"loss": 1.7916,
"step": 261
},
{
"epoch": 0.11680784663397235,
"grad_norm": 0.13181573152542114,
"learning_rate": 8.733333333333333e-05,
"loss": 1.8647,
"step": 262
},
{
"epoch": 0.11725367810967455,
"grad_norm": 0.11129307001829147,
"learning_rate": 8.766666666666668e-05,
"loss": 1.7415,
"step": 263
},
{
"epoch": 0.11769950958537673,
"grad_norm": 0.12074168771505356,
"learning_rate": 8.800000000000001e-05,
"loss": 1.7905,
"step": 264
},
{
"epoch": 0.1181453410610789,
"grad_norm": 0.11286748945713043,
"learning_rate": 8.833333333333333e-05,
"loss": 1.7739,
"step": 265
},
{
"epoch": 0.1185911725367811,
"grad_norm": 0.11794724315404892,
"learning_rate": 8.866666666666668e-05,
"loss": 1.7265,
"step": 266
},
{
"epoch": 0.11903700401248328,
"grad_norm": 0.11529921740293503,
"learning_rate": 8.900000000000001e-05,
"loss": 1.7993,
"step": 267
},
{
"epoch": 0.11948283548818546,
"grad_norm": 0.13475288450717926,
"learning_rate": 8.933333333333334e-05,
"loss": 1.7732,
"step": 268
},
{
"epoch": 0.11992866696388765,
"grad_norm": 0.13140885531902313,
"learning_rate": 8.966666666666666e-05,
"loss": 1.8349,
"step": 269
},
{
"epoch": 0.12037449843958983,
"grad_norm": 0.1583992838859558,
"learning_rate": 9e-05,
"loss": 1.8701,
"step": 270
},
{
"epoch": 0.12082032991529201,
"grad_norm": 0.13985374569892883,
"learning_rate": 9.033333333333334e-05,
"loss": 1.8923,
"step": 271
},
{
"epoch": 0.1212661613909942,
"grad_norm": 0.12568551301956177,
"learning_rate": 9.066666666666667e-05,
"loss": 1.8179,
"step": 272
},
{
"epoch": 0.12171199286669639,
"grad_norm": 0.12714029848575592,
"learning_rate": 9.1e-05,
"loss": 1.8186,
"step": 273
},
{
"epoch": 0.12215782434239858,
"grad_norm": 0.12941132485866547,
"learning_rate": 9.133333333333334e-05,
"loss": 1.8174,
"step": 274
},
{
"epoch": 0.12260365581810076,
"grad_norm": 0.11404365301132202,
"learning_rate": 9.166666666666667e-05,
"loss": 1.7675,
"step": 275
},
{
"epoch": 0.12304948729380294,
"grad_norm": 0.12205328792333603,
"learning_rate": 9.200000000000001e-05,
"loss": 1.7443,
"step": 276
},
{
"epoch": 0.12349531876950513,
"grad_norm": 0.1402350813150406,
"learning_rate": 9.233333333333333e-05,
"loss": 1.9471,
"step": 277
},
{
"epoch": 0.12394115024520731,
"grad_norm": 0.1140747219324112,
"learning_rate": 9.266666666666666e-05,
"loss": 1.7876,
"step": 278
},
{
"epoch": 0.12438698172090949,
"grad_norm": 0.13227958977222443,
"learning_rate": 9.300000000000001e-05,
"loss": 1.7642,
"step": 279
},
{
"epoch": 0.12483281319661169,
"grad_norm": 0.14531609416007996,
"learning_rate": 9.333333333333334e-05,
"loss": 1.8271,
"step": 280
},
{
"epoch": 0.12527864467231387,
"grad_norm": 0.11375468969345093,
"learning_rate": 9.366666666666668e-05,
"loss": 1.9269,
"step": 281
},
{
"epoch": 0.12572447614801605,
"grad_norm": 0.1308760941028595,
"learning_rate": 9.4e-05,
"loss": 1.7238,
"step": 282
},
{
"epoch": 0.12617030762371823,
"grad_norm": 0.1319713145494461,
"learning_rate": 9.433333333333334e-05,
"loss": 1.7777,
"step": 283
},
{
"epoch": 0.12661613909942043,
"grad_norm": 0.1134430393576622,
"learning_rate": 9.466666666666667e-05,
"loss": 1.7513,
"step": 284
},
{
"epoch": 0.1270619705751226,
"grad_norm": 0.1186988577246666,
"learning_rate": 9.5e-05,
"loss": 1.7399,
"step": 285
},
{
"epoch": 0.1275078020508248,
"grad_norm": 0.12180072069168091,
"learning_rate": 9.533333333333334e-05,
"loss": 1.8245,
"step": 286
},
{
"epoch": 0.12795363352652697,
"grad_norm": 0.10873981565237045,
"learning_rate": 9.566666666666667e-05,
"loss": 1.726,
"step": 287
},
{
"epoch": 0.12839946500222915,
"grad_norm": 0.11839178204536438,
"learning_rate": 9.6e-05,
"loss": 1.806,
"step": 288
},
{
"epoch": 0.12884529647793133,
"grad_norm": 0.10475391149520874,
"learning_rate": 9.633333333333335e-05,
"loss": 1.7453,
"step": 289
},
{
"epoch": 0.12929112795363354,
"grad_norm": 0.13696043193340302,
"learning_rate": 9.666666666666667e-05,
"loss": 1.7823,
"step": 290
},
{
"epoch": 0.12973695942933572,
"grad_norm": 0.1195741519331932,
"learning_rate": 9.7e-05,
"loss": 1.7831,
"step": 291
},
{
"epoch": 0.1301827909050379,
"grad_norm": 0.10605297237634659,
"learning_rate": 9.733333333333335e-05,
"loss": 1.8378,
"step": 292
},
{
"epoch": 0.13062862238074008,
"grad_norm": 0.12972845137119293,
"learning_rate": 9.766666666666668e-05,
"loss": 1.8112,
"step": 293
},
{
"epoch": 0.13107445385644226,
"grad_norm": 0.10625554621219635,
"learning_rate": 9.8e-05,
"loss": 1.7253,
"step": 294
},
{
"epoch": 0.13152028533214444,
"grad_norm": 0.10895377397537231,
"learning_rate": 9.833333333333333e-05,
"loss": 1.8263,
"step": 295
},
{
"epoch": 0.13196611680784665,
"grad_norm": 0.1321103870868683,
"learning_rate": 9.866666666666668e-05,
"loss": 1.8238,
"step": 296
},
{
"epoch": 0.13241194828354882,
"grad_norm": 0.12189017236232758,
"learning_rate": 9.900000000000001e-05,
"loss": 1.69,
"step": 297
},
{
"epoch": 0.132857779759251,
"grad_norm": 0.11762873828411102,
"learning_rate": 9.933333333333334e-05,
"loss": 1.8002,
"step": 298
},
{
"epoch": 0.13330361123495318,
"grad_norm": 0.12727083265781403,
"learning_rate": 9.966666666666667e-05,
"loss": 1.7544,
"step": 299
},
{
"epoch": 0.13374944271065536,
"grad_norm": 0.11152032017707825,
"learning_rate": 0.0001,
"loss": 1.77,
"step": 300
},
{
"epoch": 0.13419527418635754,
"grad_norm": 0.124668188393116,
"learning_rate": 9.999993464270667e-05,
"loss": 1.8235,
"step": 301
},
{
"epoch": 0.13464110566205975,
"grad_norm": 0.10965289920568466,
"learning_rate": 9.999973857099756e-05,
"loss": 1.6762,
"step": 302
},
{
"epoch": 0.13508693713776193,
"grad_norm": 0.10482870042324066,
"learning_rate": 9.999941178538524e-05,
"loss": 1.7315,
"step": 303
},
{
"epoch": 0.1355327686134641,
"grad_norm": 0.11446752399206161,
"learning_rate": 9.999895428672404e-05,
"loss": 1.8137,
"step": 304
},
{
"epoch": 0.1359786000891663,
"grad_norm": 0.12006917595863342,
"learning_rate": 9.999836607620998e-05,
"loss": 1.8283,
"step": 305
},
{
"epoch": 0.13642443156486847,
"grad_norm": 0.12048275768756866,
"learning_rate": 9.999764715538082e-05,
"loss": 1.7565,
"step": 306
},
{
"epoch": 0.13687026304057068,
"grad_norm": 0.12033381313085556,
"learning_rate": 9.999679752611604e-05,
"loss": 1.7073,
"step": 307
},
{
"epoch": 0.13731609451627286,
"grad_norm": 0.10729365795850754,
"learning_rate": 9.99958171906368e-05,
"loss": 1.7676,
"step": 308
},
{
"epoch": 0.13776192599197504,
"grad_norm": 0.13522760570049286,
"learning_rate": 9.9994706151506e-05,
"loss": 1.7814,
"step": 309
},
{
"epoch": 0.13820775746767722,
"grad_norm": 0.16346925497055054,
"learning_rate": 9.999346441162819e-05,
"loss": 1.7894,
"step": 310
},
{
"epoch": 0.1386535889433794,
"grad_norm": 0.1257331222295761,
"learning_rate": 9.999209197424968e-05,
"loss": 1.8256,
"step": 311
},
{
"epoch": 0.13909942041908158,
"grad_norm": 0.13515764474868774,
"learning_rate": 9.99905888429584e-05,
"loss": 1.7248,
"step": 312
},
{
"epoch": 0.13954525189478378,
"grad_norm": 0.10537850111722946,
"learning_rate": 9.998895502168397e-05,
"loss": 1.8003,
"step": 313
},
{
"epoch": 0.13999108337048596,
"grad_norm": 0.12533985078334808,
"learning_rate": 9.998719051469769e-05,
"loss": 1.7179,
"step": 314
},
{
"epoch": 0.14043691484618814,
"grad_norm": 0.11942809820175171,
"learning_rate": 9.998529532661249e-05,
"loss": 1.7381,
"step": 315
},
{
"epoch": 0.14088274632189032,
"grad_norm": 0.10156239569187164,
"learning_rate": 9.998326946238294e-05,
"loss": 1.7406,
"step": 316
},
{
"epoch": 0.1413285777975925,
"grad_norm": 0.10613414645195007,
"learning_rate": 9.998111292730525e-05,
"loss": 1.7918,
"step": 317
},
{
"epoch": 0.14177440927329468,
"grad_norm": 0.1297304481267929,
"learning_rate": 9.997882572701722e-05,
"loss": 1.7603,
"step": 318
},
{
"epoch": 0.1422202407489969,
"grad_norm": 0.11986740678548813,
"learning_rate": 9.997640786749826e-05,
"loss": 1.8647,
"step": 319
},
{
"epoch": 0.14266607222469907,
"grad_norm": 0.14261440932750702,
"learning_rate": 9.997385935506936e-05,
"loss": 1.8905,
"step": 320
},
{
"epoch": 0.14311190370040125,
"grad_norm": 0.11032776534557343,
"learning_rate": 9.99711801963931e-05,
"loss": 1.7748,
"step": 321
},
{
"epoch": 0.14355773517610343,
"grad_norm": 0.10940748453140259,
"learning_rate": 9.996837039847355e-05,
"loss": 1.7156,
"step": 322
},
{
"epoch": 0.1440035666518056,
"grad_norm": 0.1170743778347969,
"learning_rate": 9.996542996865634e-05,
"loss": 1.8676,
"step": 323
},
{
"epoch": 0.1444493981275078,
"grad_norm": 0.1365002691745758,
"learning_rate": 9.996235891462864e-05,
"loss": 1.8156,
"step": 324
},
{
"epoch": 0.14489522960321,
"grad_norm": 0.12275253236293793,
"learning_rate": 9.995915724441906e-05,
"loss": 1.8111,
"step": 325
},
{
"epoch": 0.14534106107891218,
"grad_norm": 0.15708422660827637,
"learning_rate": 9.995582496639771e-05,
"loss": 1.7917,
"step": 326
},
{
"epoch": 0.14578689255461436,
"grad_norm": 0.1188812181353569,
"learning_rate": 9.995236208927615e-05,
"loss": 1.8679,
"step": 327
},
{
"epoch": 0.14623272403031654,
"grad_norm": 0.11281725019216537,
"learning_rate": 9.994876862210729e-05,
"loss": 1.7569,
"step": 328
},
{
"epoch": 0.14667855550601872,
"grad_norm": 0.1539795994758606,
"learning_rate": 9.994504457428558e-05,
"loss": 1.7055,
"step": 329
},
{
"epoch": 0.14712438698172092,
"grad_norm": 0.1248791366815567,
"learning_rate": 9.99411899555467e-05,
"loss": 1.8482,
"step": 330
},
{
"epoch": 0.1475702184574231,
"grad_norm": 0.12949204444885254,
"learning_rate": 9.993720477596782e-05,
"loss": 1.7653,
"step": 331
},
{
"epoch": 0.14801604993312528,
"grad_norm": 0.11171630769968033,
"learning_rate": 9.99330890459673e-05,
"loss": 1.8116,
"step": 332
},
{
"epoch": 0.14846188140882746,
"grad_norm": 0.11713983863592148,
"learning_rate": 9.992884277630489e-05,
"loss": 1.8032,
"step": 333
},
{
"epoch": 0.14890771288452964,
"grad_norm": 0.12063828110694885,
"learning_rate": 9.992446597808156e-05,
"loss": 1.761,
"step": 334
},
{
"epoch": 0.14935354436023182,
"grad_norm": 0.1251848042011261,
"learning_rate": 9.991995866273955e-05,
"loss": 1.8293,
"step": 335
},
{
"epoch": 0.14979937583593403,
"grad_norm": 0.11480008810758591,
"learning_rate": 9.99153208420623e-05,
"loss": 1.7459,
"step": 336
},
{
"epoch": 0.1502452073116362,
"grad_norm": 0.1392374038696289,
"learning_rate": 9.99105525281744e-05,
"loss": 1.7932,
"step": 337
},
{
"epoch": 0.1506910387873384,
"grad_norm": 0.11574403941631317,
"learning_rate": 9.990565373354167e-05,
"loss": 1.7882,
"step": 338
},
{
"epoch": 0.15113687026304057,
"grad_norm": 0.11816232651472092,
"learning_rate": 9.990062447097092e-05,
"loss": 1.7823,
"step": 339
},
{
"epoch": 0.15158270173874275,
"grad_norm": 0.11845866590738297,
"learning_rate": 9.989546475361015e-05,
"loss": 1.9033,
"step": 340
},
{
"epoch": 0.15202853321444493,
"grad_norm": 0.12563872337341309,
"learning_rate": 9.989017459494836e-05,
"loss": 1.7223,
"step": 341
},
{
"epoch": 0.15247436469014714,
"grad_norm": 0.1071380153298378,
"learning_rate": 9.988475400881556e-05,
"loss": 1.845,
"step": 342
},
{
"epoch": 0.15292019616584931,
"grad_norm": 0.1367650181055069,
"learning_rate": 9.987920300938277e-05,
"loss": 1.7763,
"step": 343
},
{
"epoch": 0.1533660276415515,
"grad_norm": 0.10972041636705399,
"learning_rate": 9.987352161116187e-05,
"loss": 1.8303,
"step": 344
},
{
"epoch": 0.15381185911725367,
"grad_norm": 0.17305706441402435,
"learning_rate": 9.986770982900574e-05,
"loss": 1.7735,
"step": 345
},
{
"epoch": 0.15425769059295585,
"grad_norm": 0.10852725803852081,
"learning_rate": 9.986176767810805e-05,
"loss": 1.8377,
"step": 346
},
{
"epoch": 0.15470352206865803,
"grad_norm": 0.15324626863002777,
"learning_rate": 9.985569517400332e-05,
"loss": 1.8643,
"step": 347
},
{
"epoch": 0.15514935354436024,
"grad_norm": 0.126643568277359,
"learning_rate": 9.984949233256687e-05,
"loss": 1.8354,
"step": 348
},
{
"epoch": 0.15559518502006242,
"grad_norm": 0.14467085897922516,
"learning_rate": 9.984315917001472e-05,
"loss": 1.7846,
"step": 349
},
{
"epoch": 0.1560410164957646,
"grad_norm": 0.11402511596679688,
"learning_rate": 9.983669570290358e-05,
"loss": 1.7808,
"step": 350
},
{
"epoch": 0.15648684797146678,
"grad_norm": 0.12388184666633606,
"learning_rate": 9.983010194813087e-05,
"loss": 1.7218,
"step": 351
},
{
"epoch": 0.15693267944716896,
"grad_norm": 0.11659372597932816,
"learning_rate": 9.982337792293459e-05,
"loss": 1.773,
"step": 352
},
{
"epoch": 0.15737851092287117,
"grad_norm": 0.10896174609661102,
"learning_rate": 9.981652364489328e-05,
"loss": 1.8151,
"step": 353
},
{
"epoch": 0.15782434239857335,
"grad_norm": 0.12702295184135437,
"learning_rate": 9.980953913192604e-05,
"loss": 1.7497,
"step": 354
},
{
"epoch": 0.15827017387427553,
"grad_norm": 0.10169962793588638,
"learning_rate": 9.980242440229242e-05,
"loss": 1.8403,
"step": 355
},
{
"epoch": 0.1587160053499777,
"grad_norm": 0.119049571454525,
"learning_rate": 9.97951794745924e-05,
"loss": 1.778,
"step": 356
},
{
"epoch": 0.1591618368256799,
"grad_norm": 0.10674421489238739,
"learning_rate": 9.978780436776633e-05,
"loss": 1.8004,
"step": 357
},
{
"epoch": 0.15960766830138207,
"grad_norm": 0.11362048983573914,
"learning_rate": 9.978029910109491e-05,
"loss": 1.8319,
"step": 358
},
{
"epoch": 0.16005349977708427,
"grad_norm": 0.09631331264972687,
"learning_rate": 9.977266369419907e-05,
"loss": 1.7074,
"step": 359
},
{
"epoch": 0.16049933125278645,
"grad_norm": 0.1303529292345047,
"learning_rate": 9.976489816704e-05,
"loss": 1.8159,
"step": 360
},
{
"epoch": 0.16094516272848863,
"grad_norm": 0.10787598788738251,
"learning_rate": 9.975700253991907e-05,
"loss": 1.7834,
"step": 361
},
{
"epoch": 0.1613909942041908,
"grad_norm": 0.11350094527006149,
"learning_rate": 9.974897683347772e-05,
"loss": 1.7898,
"step": 362
},
{
"epoch": 0.161836825679893,
"grad_norm": 0.12742607295513153,
"learning_rate": 9.97408210686975e-05,
"loss": 1.776,
"step": 363
},
{
"epoch": 0.16228265715559517,
"grad_norm": 0.10006166249513626,
"learning_rate": 9.973253526689999e-05,
"loss": 1.806,
"step": 364
},
{
"epoch": 0.16272848863129738,
"grad_norm": 0.10663770139217377,
"learning_rate": 9.972411944974664e-05,
"loss": 1.6787,
"step": 365
},
{
"epoch": 0.16317432010699956,
"grad_norm": 0.11871890723705292,
"learning_rate": 9.97155736392389e-05,
"loss": 1.7672,
"step": 366
},
{
"epoch": 0.16362015158270174,
"grad_norm": 0.10863269120454788,
"learning_rate": 9.970689785771798e-05,
"loss": 1.8785,
"step": 367
},
{
"epoch": 0.16406598305840392,
"grad_norm": 0.10666559636592865,
"learning_rate": 9.969809212786491e-05,
"loss": 1.8055,
"step": 368
},
{
"epoch": 0.1645118145341061,
"grad_norm": 0.12114860862493515,
"learning_rate": 9.968915647270048e-05,
"loss": 1.7851,
"step": 369
},
{
"epoch": 0.16495764600980828,
"grad_norm": 0.11494174599647522,
"learning_rate": 9.9680090915585e-05,
"loss": 1.8593,
"step": 370
},
{
"epoch": 0.1654034774855105,
"grad_norm": 0.11581412702798843,
"learning_rate": 9.96708954802186e-05,
"loss": 1.8538,
"step": 371
},
{
"epoch": 0.16584930896121267,
"grad_norm": 0.11794432997703552,
"learning_rate": 9.966157019064074e-05,
"loss": 1.7921,
"step": 372
},
{
"epoch": 0.16629514043691485,
"grad_norm": 0.107793889939785,
"learning_rate": 9.965211507123049e-05,
"loss": 1.8058,
"step": 373
},
{
"epoch": 0.16674097191261703,
"grad_norm": 0.10789332538843155,
"learning_rate": 9.964253014670628e-05,
"loss": 1.7688,
"step": 374
},
{
"epoch": 0.1671868033883192,
"grad_norm": 0.1062360480427742,
"learning_rate": 9.963281544212588e-05,
"loss": 1.7974,
"step": 375
},
{
"epoch": 0.1676326348640214,
"grad_norm": 0.09926211088895798,
"learning_rate": 9.962297098288641e-05,
"loss": 1.7647,
"step": 376
},
{
"epoch": 0.1680784663397236,
"grad_norm": 0.10037009418010712,
"learning_rate": 9.961299679472411e-05,
"loss": 1.7145,
"step": 377
},
{
"epoch": 0.16852429781542577,
"grad_norm": 0.09782075136899948,
"learning_rate": 9.960289290371445e-05,
"loss": 1.7943,
"step": 378
},
{
"epoch": 0.16897012929112795,
"grad_norm": 0.13282179832458496,
"learning_rate": 9.959265933627193e-05,
"loss": 1.8503,
"step": 379
},
{
"epoch": 0.16941596076683013,
"grad_norm": 0.10220073163509369,
"learning_rate": 9.958229611915008e-05,
"loss": 1.7627,
"step": 380
},
{
"epoch": 0.1698617922425323,
"grad_norm": 0.14189738035202026,
"learning_rate": 9.95718032794414e-05,
"loss": 1.7941,
"step": 381
},
{
"epoch": 0.17030762371823452,
"grad_norm": 0.10154666751623154,
"learning_rate": 9.95611808445772e-05,
"loss": 1.7476,
"step": 382
},
{
"epoch": 0.1707534551939367,
"grad_norm": 0.09952086210250854,
"learning_rate": 9.955042884232765e-05,
"loss": 1.7591,
"step": 383
},
{
"epoch": 0.17119928666963888,
"grad_norm": 0.11027457565069199,
"learning_rate": 9.95395473008016e-05,
"loss": 1.6714,
"step": 384
},
{
"epoch": 0.17164511814534106,
"grad_norm": 0.097461998462677,
"learning_rate": 9.952853624844658e-05,
"loss": 1.7296,
"step": 385
},
{
"epoch": 0.17209094962104324,
"grad_norm": 0.10080503672361374,
"learning_rate": 9.95173957140487e-05,
"loss": 1.782,
"step": 386
},
{
"epoch": 0.17253678109674542,
"grad_norm": 0.10462392866611481,
"learning_rate": 9.950612572673255e-05,
"loss": 1.8007,
"step": 387
},
{
"epoch": 0.17298261257244762,
"grad_norm": 0.09910599887371063,
"learning_rate": 9.94947263159612e-05,
"loss": 1.7808,
"step": 388
},
{
"epoch": 0.1734284440481498,
"grad_norm": 0.11452896893024445,
"learning_rate": 9.948319751153599e-05,
"loss": 1.856,
"step": 389
},
{
"epoch": 0.17387427552385198,
"grad_norm": 0.09801609069108963,
"learning_rate": 9.947153934359661e-05,
"loss": 1.7316,
"step": 390
},
{
"epoch": 0.17432010699955416,
"grad_norm": 0.11089462041854858,
"learning_rate": 9.94597518426209e-05,
"loss": 1.727,
"step": 391
},
{
"epoch": 0.17476593847525634,
"grad_norm": 0.09695982933044434,
"learning_rate": 9.944783503942483e-05,
"loss": 1.862,
"step": 392
},
{
"epoch": 0.17521176995095855,
"grad_norm": 0.11888276040554047,
"learning_rate": 9.943578896516239e-05,
"loss": 1.83,
"step": 393
},
{
"epoch": 0.17565760142666073,
"grad_norm": 0.11138911545276642,
"learning_rate": 9.942361365132555e-05,
"loss": 1.7361,
"step": 394
},
{
"epoch": 0.1761034329023629,
"grad_norm": 0.10635440051555634,
"learning_rate": 9.941130912974413e-05,
"loss": 1.7293,
"step": 395
},
{
"epoch": 0.1765492643780651,
"grad_norm": 0.1355292648077011,
"learning_rate": 9.939887543258573e-05,
"loss": 1.7499,
"step": 396
},
{
"epoch": 0.17699509585376727,
"grad_norm": 0.13170644640922546,
"learning_rate": 9.938631259235567e-05,
"loss": 1.7657,
"step": 397
},
{
"epoch": 0.17744092732946945,
"grad_norm": 0.12488769739866257,
"learning_rate": 9.937362064189686e-05,
"loss": 1.7828,
"step": 398
},
{
"epoch": 0.17788675880517166,
"grad_norm": 0.14426769316196442,
"learning_rate": 9.936079961438978e-05,
"loss": 1.7659,
"step": 399
},
{
"epoch": 0.17833259028087384,
"grad_norm": 0.10388638824224472,
"learning_rate": 9.934784954335233e-05,
"loss": 1.835,
"step": 400
},
{
"epoch": 0.17877842175657602,
"grad_norm": 0.13149262964725494,
"learning_rate": 9.933477046263977e-05,
"loss": 1.8815,
"step": 401
},
{
"epoch": 0.1792242532322782,
"grad_norm": 0.1047818511724472,
"learning_rate": 9.932156240644465e-05,
"loss": 1.8103,
"step": 402
},
{
"epoch": 0.17967008470798038,
"grad_norm": 0.10746704041957855,
"learning_rate": 9.930822540929666e-05,
"loss": 1.7569,
"step": 403
},
{
"epoch": 0.18011591618368256,
"grad_norm": 0.10377546399831772,
"learning_rate": 9.929475950606262e-05,
"loss": 1.7987,
"step": 404
},
{
"epoch": 0.18056174765938476,
"grad_norm": 0.1111828088760376,
"learning_rate": 9.92811647319463e-05,
"loss": 1.8406,
"step": 405
},
{
"epoch": 0.18100757913508694,
"grad_norm": 0.11079175770282745,
"learning_rate": 9.926744112248844e-05,
"loss": 1.7925,
"step": 406
},
{
"epoch": 0.18145341061078912,
"grad_norm": 0.11172319948673248,
"learning_rate": 9.925358871356656e-05,
"loss": 1.6484,
"step": 407
},
{
"epoch": 0.1818992420864913,
"grad_norm": 0.1051497757434845,
"learning_rate": 9.923960754139488e-05,
"loss": 1.7545,
"step": 408
},
{
"epoch": 0.18234507356219348,
"grad_norm": 0.12014391273260117,
"learning_rate": 9.922549764252425e-05,
"loss": 1.7793,
"step": 409
},
{
"epoch": 0.18279090503789566,
"grad_norm": 0.11258053779602051,
"learning_rate": 9.921125905384208e-05,
"loss": 1.846,
"step": 410
},
{
"epoch": 0.18323673651359787,
"grad_norm": 0.15552328526973724,
"learning_rate": 9.919689181257219e-05,
"loss": 1.8653,
"step": 411
},
{
"epoch": 0.18368256798930005,
"grad_norm": 0.11162538826465607,
"learning_rate": 9.918239595627474e-05,
"loss": 1.7645,
"step": 412
},
{
"epoch": 0.18412839946500223,
"grad_norm": 0.13449177145957947,
"learning_rate": 9.916777152284615e-05,
"loss": 1.8104,
"step": 413
},
{
"epoch": 0.1845742309407044,
"grad_norm": 0.11493851244449615,
"learning_rate": 9.91530185505189e-05,
"loss": 1.7941,
"step": 414
},
{
"epoch": 0.1850200624164066,
"grad_norm": 0.12892407178878784,
"learning_rate": 9.913813707786163e-05,
"loss": 1.8156,
"step": 415
},
{
"epoch": 0.1854658938921088,
"grad_norm": 0.11245466768741608,
"learning_rate": 9.91231271437788e-05,
"loss": 1.7732,
"step": 416
},
{
"epoch": 0.18591172536781098,
"grad_norm": 0.1221921294927597,
"learning_rate": 9.91079887875108e-05,
"loss": 1.7343,
"step": 417
},
{
"epoch": 0.18635755684351316,
"grad_norm": 0.11518368124961853,
"learning_rate": 9.909272204863367e-05,
"loss": 1.6763,
"step": 418
},
{
"epoch": 0.18680338831921534,
"grad_norm": 0.12438438087701797,
"learning_rate": 9.907732696705914e-05,
"loss": 1.7799,
"step": 419
},
{
"epoch": 0.18724921979491752,
"grad_norm": 0.11922072619199753,
"learning_rate": 9.906180358303443e-05,
"loss": 1.7083,
"step": 420
},
{
"epoch": 0.1876950512706197,
"grad_norm": 0.11506510525941849,
"learning_rate": 9.904615193714222e-05,
"loss": 1.795,
"step": 421
},
{
"epoch": 0.1881408827463219,
"grad_norm": 0.10277034342288971,
"learning_rate": 9.903037207030045e-05,
"loss": 1.6832,
"step": 422
},
{
"epoch": 0.18858671422202408,
"grad_norm": 0.11094953864812851,
"learning_rate": 9.901446402376231e-05,
"loss": 1.8642,
"step": 423
},
{
"epoch": 0.18903254569772626,
"grad_norm": 0.1558915674686432,
"learning_rate": 9.899842783911608e-05,
"loss": 1.7637,
"step": 424
},
{
"epoch": 0.18947837717342844,
"grad_norm": 0.11284621804952621,
"learning_rate": 9.8982263558285e-05,
"loss": 1.8193,
"step": 425
},
{
"epoch": 0.18992420864913062,
"grad_norm": 0.12376314401626587,
"learning_rate": 9.896597122352726e-05,
"loss": 1.712,
"step": 426
},
{
"epoch": 0.1903700401248328,
"grad_norm": 0.1203361228108406,
"learning_rate": 9.894955087743573e-05,
"loss": 1.7843,
"step": 427
},
{
"epoch": 0.190815871600535,
"grad_norm": 0.10657840222120285,
"learning_rate": 9.8933002562938e-05,
"loss": 1.7893,
"step": 428
},
{
"epoch": 0.1912617030762372,
"grad_norm": 0.10462167114019394,
"learning_rate": 9.891632632329621e-05,
"loss": 1.772,
"step": 429
},
{
"epoch": 0.19170753455193937,
"grad_norm": 0.10204766690731049,
"learning_rate": 9.88995222021069e-05,
"loss": 1.7194,
"step": 430
},
{
"epoch": 0.19215336602764155,
"grad_norm": 0.11789607256650925,
"learning_rate": 9.888259024330094e-05,
"loss": 1.8511,
"step": 431
},
{
"epoch": 0.19259919750334373,
"grad_norm": 0.10127758234739304,
"learning_rate": 9.886553049114343e-05,
"loss": 1.8149,
"step": 432
},
{
"epoch": 0.1930450289790459,
"grad_norm": 0.11428545415401459,
"learning_rate": 9.88483429902335e-05,
"loss": 1.6752,
"step": 433
},
{
"epoch": 0.19349086045474811,
"grad_norm": 0.10000619292259216,
"learning_rate": 9.883102778550434e-05,
"loss": 1.8338,
"step": 434
},
{
"epoch": 0.1939366919304503,
"grad_norm": 0.10257402062416077,
"learning_rate": 9.881358492222293e-05,
"loss": 1.7389,
"step": 435
},
{
"epoch": 0.19438252340615247,
"grad_norm": 0.10894675552845001,
"learning_rate": 9.879601444598997e-05,
"loss": 1.7954,
"step": 436
},
{
"epoch": 0.19482835488185465,
"grad_norm": 0.09952058643102646,
"learning_rate": 9.877831640273985e-05,
"loss": 1.7705,
"step": 437
},
{
"epoch": 0.19527418635755683,
"grad_norm": 0.11156906932592392,
"learning_rate": 9.876049083874042e-05,
"loss": 1.7868,
"step": 438
},
{
"epoch": 0.19572001783325904,
"grad_norm": 0.10069166868925095,
"learning_rate": 9.874253780059286e-05,
"loss": 1.7842,
"step": 439
},
{
"epoch": 0.19616584930896122,
"grad_norm": 0.10593489557504654,
"learning_rate": 9.87244573352317e-05,
"loss": 1.6439,
"step": 440
},
{
"epoch": 0.1966116807846634,
"grad_norm": 0.10652976483106613,
"learning_rate": 9.870624948992453e-05,
"loss": 1.7266,
"step": 441
},
{
"epoch": 0.19705751226036558,
"grad_norm": 0.10429206490516663,
"learning_rate": 9.868791431227198e-05,
"loss": 1.7684,
"step": 442
},
{
"epoch": 0.19750334373606776,
"grad_norm": 0.10255853086709976,
"learning_rate": 9.866945185020753e-05,
"loss": 1.7454,
"step": 443
},
{
"epoch": 0.19794917521176994,
"grad_norm": 0.10498002171516418,
"learning_rate": 9.865086215199746e-05,
"loss": 1.7837,
"step": 444
},
{
"epoch": 0.19839500668747215,
"grad_norm": 0.10665781050920486,
"learning_rate": 9.863214526624065e-05,
"loss": 1.8228,
"step": 445
},
{
"epoch": 0.19884083816317433,
"grad_norm": 0.10802847892045975,
"learning_rate": 9.861330124186853e-05,
"loss": 1.8374,
"step": 446
},
{
"epoch": 0.1992866696388765,
"grad_norm": 0.10714347660541534,
"learning_rate": 9.859433012814484e-05,
"loss": 1.7284,
"step": 447
},
{
"epoch": 0.1997325011145787,
"grad_norm": 0.09779908508062363,
"learning_rate": 9.857523197466563e-05,
"loss": 1.7287,
"step": 448
},
{
"epoch": 0.20017833259028087,
"grad_norm": 0.1303940713405609,
"learning_rate": 9.855600683135904e-05,
"loss": 1.7582,
"step": 449
},
{
"epoch": 0.20062416406598305,
"grad_norm": 0.10095707327127457,
"learning_rate": 9.853665474848519e-05,
"loss": 1.7557,
"step": 450
},
{
"epoch": 0.20106999554168525,
"grad_norm": 0.092136912047863,
"learning_rate": 9.851717577663609e-05,
"loss": 1.6016,
"step": 451
},
{
"epoch": 0.20151582701738743,
"grad_norm": 0.1210860088467598,
"learning_rate": 9.849756996673545e-05,
"loss": 1.7308,
"step": 452
},
{
"epoch": 0.2019616584930896,
"grad_norm": 0.09985879063606262,
"learning_rate": 9.847783737003856e-05,
"loss": 1.728,
"step": 453
},
{
"epoch": 0.2024074899687918,
"grad_norm": 0.13490703701972961,
"learning_rate": 9.845797803813221e-05,
"loss": 1.8725,
"step": 454
},
{
"epoch": 0.20285332144449397,
"grad_norm": 0.10359074175357819,
"learning_rate": 9.843799202293447e-05,
"loss": 1.7705,
"step": 455
},
{
"epoch": 0.20329915292019615,
"grad_norm": 0.1110636442899704,
"learning_rate": 9.841787937669461e-05,
"loss": 1.699,
"step": 456
},
{
"epoch": 0.20374498439589836,
"grad_norm": 0.10007648915052414,
"learning_rate": 9.839764015199298e-05,
"loss": 1.7793,
"step": 457
},
{
"epoch": 0.20419081587160054,
"grad_norm": 0.10939273238182068,
"learning_rate": 9.837727440174079e-05,
"loss": 1.7184,
"step": 458
},
{
"epoch": 0.20463664734730272,
"grad_norm": 0.11205507069826126,
"learning_rate": 9.835678217918005e-05,
"loss": 1.7101,
"step": 459
},
{
"epoch": 0.2050824788230049,
"grad_norm": 0.11545661836862564,
"learning_rate": 9.833616353788345e-05,
"loss": 1.8039,
"step": 460
},
{
"epoch": 0.20552831029870708,
"grad_norm": 0.1527920514345169,
"learning_rate": 9.831541853175409e-05,
"loss": 1.7559,
"step": 461
},
{
"epoch": 0.2059741417744093,
"grad_norm": 0.10123451054096222,
"learning_rate": 9.82945472150255e-05,
"loss": 1.7834,
"step": 462
},
{
"epoch": 0.20641997325011147,
"grad_norm": 0.133615180850029,
"learning_rate": 9.827354964226134e-05,
"loss": 1.8258,
"step": 463
},
{
"epoch": 0.20686580472581365,
"grad_norm": 0.10145179182291031,
"learning_rate": 9.825242586835545e-05,
"loss": 1.8397,
"step": 464
},
{
"epoch": 0.20731163620151583,
"grad_norm": 0.10061782598495483,
"learning_rate": 9.82311759485315e-05,
"loss": 1.7741,
"step": 465
},
{
"epoch": 0.207757467677218,
"grad_norm": 0.12411954253911972,
"learning_rate": 9.8209799938343e-05,
"loss": 1.8185,
"step": 466
},
{
"epoch": 0.20820329915292018,
"grad_norm": 0.10785725712776184,
"learning_rate": 9.818829789367307e-05,
"loss": 1.7867,
"step": 467
},
{
"epoch": 0.2086491306286224,
"grad_norm": 0.10486532002687454,
"learning_rate": 9.816666987073433e-05,
"loss": 1.7131,
"step": 468
},
{
"epoch": 0.20909496210432457,
"grad_norm": 0.10094525665044785,
"learning_rate": 9.814491592606874e-05,
"loss": 1.8221,
"step": 469
},
{
"epoch": 0.20954079358002675,
"grad_norm": 0.10427477955818176,
"learning_rate": 9.812303611654745e-05,
"loss": 1.7498,
"step": 470
},
{
"epoch": 0.20998662505572893,
"grad_norm": 0.12335694581270218,
"learning_rate": 9.810103049937068e-05,
"loss": 1.8706,
"step": 471
},
{
"epoch": 0.2104324565314311,
"grad_norm": 0.10109227895736694,
"learning_rate": 9.80788991320675e-05,
"loss": 1.8401,
"step": 472
},
{
"epoch": 0.2108782880071333,
"grad_norm": 0.11577172577381134,
"learning_rate": 9.805664207249581e-05,
"loss": 1.7709,
"step": 473
},
{
"epoch": 0.2113241194828355,
"grad_norm": 0.09947428107261658,
"learning_rate": 9.8034259378842e-05,
"loss": 1.8138,
"step": 474
},
{
"epoch": 0.21176995095853768,
"grad_norm": 0.10954049974679947,
"learning_rate": 9.801175110962103e-05,
"loss": 1.7777,
"step": 475
},
{
"epoch": 0.21221578243423986,
"grad_norm": 0.1118762344121933,
"learning_rate": 9.798911732367603e-05,
"loss": 1.7785,
"step": 476
},
{
"epoch": 0.21266161390994204,
"grad_norm": 0.09822601079940796,
"learning_rate": 9.796635808017833e-05,
"loss": 1.7429,
"step": 477
},
{
"epoch": 0.21310744538564422,
"grad_norm": 0.14918822050094604,
"learning_rate": 9.794347343862724e-05,
"loss": 1.8038,
"step": 478
},
{
"epoch": 0.2135532768613464,
"grad_norm": 0.12590400874614716,
"learning_rate": 9.792046345884988e-05,
"loss": 1.8677,
"step": 479
},
{
"epoch": 0.2139991083370486,
"grad_norm": 0.11536061018705368,
"learning_rate": 9.789732820100106e-05,
"loss": 1.815,
"step": 480
},
{
"epoch": 0.21444493981275078,
"grad_norm": 0.12682761251926422,
"learning_rate": 9.787406772556309e-05,
"loss": 1.7954,
"step": 481
},
{
"epoch": 0.21489077128845296,
"grad_norm": 0.11137998849153519,
"learning_rate": 9.785068209334565e-05,
"loss": 1.7773,
"step": 482
},
{
"epoch": 0.21533660276415514,
"grad_norm": 0.10286463797092438,
"learning_rate": 9.782717136548557e-05,
"loss": 1.7263,
"step": 483
},
{
"epoch": 0.21578243423985732,
"grad_norm": 0.1007862389087677,
"learning_rate": 9.780353560344678e-05,
"loss": 1.8244,
"step": 484
},
{
"epoch": 0.21622826571555953,
"grad_norm": 0.09861966222524643,
"learning_rate": 9.777977486902006e-05,
"loss": 1.7999,
"step": 485
},
{
"epoch": 0.2166740971912617,
"grad_norm": 0.10864880681037903,
"learning_rate": 9.775588922432288e-05,
"loss": 1.8355,
"step": 486
},
{
"epoch": 0.2171199286669639,
"grad_norm": 0.10150966048240662,
"learning_rate": 9.77318787317993e-05,
"loss": 1.7598,
"step": 487
},
{
"epoch": 0.21756576014266607,
"grad_norm": 0.10420972108840942,
"learning_rate": 9.770774345421976e-05,
"loss": 1.7318,
"step": 488
},
{
"epoch": 0.21801159161836825,
"grad_norm": 0.09552264213562012,
"learning_rate": 9.768348345468089e-05,
"loss": 1.7206,
"step": 489
},
{
"epoch": 0.21845742309407043,
"grad_norm": 0.09572545439004898,
"learning_rate": 9.765909879660541e-05,
"loss": 1.7111,
"step": 490
},
{
"epoch": 0.21890325456977264,
"grad_norm": 0.09580688178539276,
"learning_rate": 9.763458954374197e-05,
"loss": 1.8152,
"step": 491
},
{
"epoch": 0.21934908604547482,
"grad_norm": 0.10338671505451202,
"learning_rate": 9.760995576016488e-05,
"loss": 1.848,
"step": 492
},
{
"epoch": 0.219794917521177,
"grad_norm": 0.09643546491861343,
"learning_rate": 9.758519751027401e-05,
"loss": 1.6534,
"step": 493
},
{
"epoch": 0.22024074899687918,
"grad_norm": 0.10433247685432434,
"learning_rate": 9.756031485879468e-05,
"loss": 1.7254,
"step": 494
},
{
"epoch": 0.22068658047258136,
"grad_norm": 0.09419728815555573,
"learning_rate": 9.753530787077741e-05,
"loss": 1.6872,
"step": 495
},
{
"epoch": 0.22113241194828354,
"grad_norm": 0.10806705057621002,
"learning_rate": 9.751017661159772e-05,
"loss": 1.8332,
"step": 496
},
{
"epoch": 0.22157824342398574,
"grad_norm": 0.09453105181455612,
"learning_rate": 9.748492114695609e-05,
"loss": 1.6668,
"step": 497
},
{
"epoch": 0.22202407489968792,
"grad_norm": 0.09785551577806473,
"learning_rate": 9.745954154287767e-05,
"loss": 1.7075,
"step": 498
},
{
"epoch": 0.2224699063753901,
"grad_norm": 0.1000019833445549,
"learning_rate": 9.743403786571214e-05,
"loss": 1.7483,
"step": 499
},
{
"epoch": 0.22291573785109228,
"grad_norm": 0.10058484971523285,
"learning_rate": 9.740841018213354e-05,
"loss": 1.7789,
"step": 500
},
{
"epoch": 0.22336156932679446,
"grad_norm": 0.1096552163362503,
"learning_rate": 9.738265855914013e-05,
"loss": 1.8599,
"step": 501
},
{
"epoch": 0.22380740080249667,
"grad_norm": 0.10602924972772598,
"learning_rate": 9.735678306405416e-05,
"loss": 1.8476,
"step": 502
},
{
"epoch": 0.22425323227819885,
"grad_norm": 0.09995143860578537,
"learning_rate": 9.733078376452171e-05,
"loss": 1.7444,
"step": 503
},
{
"epoch": 0.22469906375390103,
"grad_norm": 0.10269878059625626,
"learning_rate": 9.730466072851257e-05,
"loss": 1.8108,
"step": 504
},
{
"epoch": 0.2251448952296032,
"grad_norm": 0.09927020221948624,
"learning_rate": 9.727841402431991e-05,
"loss": 1.7838,
"step": 505
},
{
"epoch": 0.2255907267053054,
"grad_norm": 0.09740092605352402,
"learning_rate": 9.725204372056036e-05,
"loss": 1.804,
"step": 506
},
{
"epoch": 0.22603655818100757,
"grad_norm": 0.10727602988481522,
"learning_rate": 9.722554988617352e-05,
"loss": 1.7847,
"step": 507
},
{
"epoch": 0.22648238965670978,
"grad_norm": 0.10434549301862717,
"learning_rate": 9.719893259042201e-05,
"loss": 1.7938,
"step": 508
},
{
"epoch": 0.22692822113241196,
"grad_norm": 0.1154603660106659,
"learning_rate": 9.717219190289124e-05,
"loss": 1.8032,
"step": 509
},
{
"epoch": 0.22737405260811414,
"grad_norm": 0.09667083621025085,
"learning_rate": 9.714532789348915e-05,
"loss": 1.7554,
"step": 510
},
{
"epoch": 0.22781988408381632,
"grad_norm": 0.11698783934116364,
"learning_rate": 9.711834063244609e-05,
"loss": 1.7963,
"step": 511
},
{
"epoch": 0.2282657155595185,
"grad_norm": 0.10345514863729477,
"learning_rate": 9.709123019031464e-05,
"loss": 1.6855,
"step": 512
},
{
"epoch": 0.22871154703522067,
"grad_norm": 0.11783094704151154,
"learning_rate": 9.706399663796941e-05,
"loss": 1.6386,
"step": 513
},
{
"epoch": 0.22915737851092288,
"grad_norm": 0.11354560405015945,
"learning_rate": 9.703664004660683e-05,
"loss": 1.815,
"step": 514
},
{
"epoch": 0.22960320998662506,
"grad_norm": 0.1055736318230629,
"learning_rate": 9.700916048774505e-05,
"loss": 1.7958,
"step": 515
},
{
"epoch": 0.23004904146232724,
"grad_norm": 0.11516160517930984,
"learning_rate": 9.698155803322359e-05,
"loss": 1.8297,
"step": 516
},
{
"epoch": 0.23049487293802942,
"grad_norm": 0.0924014076590538,
"learning_rate": 9.69538327552034e-05,
"loss": 1.6806,
"step": 517
},
{
"epoch": 0.2309407044137316,
"grad_norm": 0.11584834009408951,
"learning_rate": 9.692598472616637e-05,
"loss": 1.8029,
"step": 518
},
{
"epoch": 0.23138653588943378,
"grad_norm": 0.10804828256368637,
"learning_rate": 9.689801401891543e-05,
"loss": 1.8082,
"step": 519
},
{
"epoch": 0.231832367365136,
"grad_norm": 0.10432989150285721,
"learning_rate": 9.686992070657413e-05,
"loss": 1.7286,
"step": 520
},
{
"epoch": 0.23227819884083817,
"grad_norm": 0.10536886751651764,
"learning_rate": 9.68417048625866e-05,
"loss": 1.7879,
"step": 521
},
{
"epoch": 0.23272403031654035,
"grad_norm": 0.09892881661653519,
"learning_rate": 9.68133665607173e-05,
"loss": 1.7874,
"step": 522
},
{
"epoch": 0.23316986179224253,
"grad_norm": 0.108803391456604,
"learning_rate": 9.678490587505078e-05,
"loss": 1.74,
"step": 523
},
{
"epoch": 0.2336156932679447,
"grad_norm": 0.0954183042049408,
"learning_rate": 9.67563228799916e-05,
"loss": 1.6863,
"step": 524
},
{
"epoch": 0.23406152474364691,
"grad_norm": 0.09981938451528549,
"learning_rate": 9.672761765026406e-05,
"loss": 1.7495,
"step": 525
},
{
"epoch": 0.2345073562193491,
"grad_norm": 0.1061968058347702,
"learning_rate": 9.669879026091198e-05,
"loss": 1.8133,
"step": 526
},
{
"epoch": 0.23495318769505127,
"grad_norm": 0.11043399572372437,
"learning_rate": 9.66698407872986e-05,
"loss": 1.8532,
"step": 527
},
{
"epoch": 0.23539901917075345,
"grad_norm": 0.10422837734222412,
"learning_rate": 9.664076930510624e-05,
"loss": 1.7448,
"step": 528
},
{
"epoch": 0.23584485064645563,
"grad_norm": 0.10506264120340347,
"learning_rate": 9.661157589033627e-05,
"loss": 1.8226,
"step": 529
},
{
"epoch": 0.2362906821221578,
"grad_norm": 0.10886254161596298,
"learning_rate": 9.65822606193088e-05,
"loss": 1.7375,
"step": 530
},
{
"epoch": 0.23673651359786002,
"grad_norm": 0.10376360267400742,
"learning_rate": 9.655282356866247e-05,
"loss": 1.8129,
"step": 531
},
{
"epoch": 0.2371823450735622,
"grad_norm": 0.11177878081798553,
"learning_rate": 9.652326481535435e-05,
"loss": 1.7591,
"step": 532
},
{
"epoch": 0.23762817654926438,
"grad_norm": 0.10007914155721664,
"learning_rate": 9.64935844366596e-05,
"loss": 1.7799,
"step": 533
},
{
"epoch": 0.23807400802496656,
"grad_norm": 0.10296649485826492,
"learning_rate": 9.646378251017143e-05,
"loss": 1.812,
"step": 534
},
{
"epoch": 0.23851983950066874,
"grad_norm": 0.10503607988357544,
"learning_rate": 9.643385911380076e-05,
"loss": 1.7583,
"step": 535
},
{
"epoch": 0.23896567097637092,
"grad_norm": 0.09877045452594757,
"learning_rate": 9.640381432577609e-05,
"loss": 1.7517,
"step": 536
},
{
"epoch": 0.23941150245207313,
"grad_norm": 0.0969356968998909,
"learning_rate": 9.637364822464323e-05,
"loss": 1.778,
"step": 537
},
{
"epoch": 0.2398573339277753,
"grad_norm": 0.10515077412128448,
"learning_rate": 9.634336088926519e-05,
"loss": 1.8594,
"step": 538
},
{
"epoch": 0.2403031654034775,
"grad_norm": 0.10064911097288132,
"learning_rate": 9.63129523988219e-05,
"loss": 1.7246,
"step": 539
},
{
"epoch": 0.24074899687917967,
"grad_norm": 0.10037011653184891,
"learning_rate": 9.628242283281001e-05,
"loss": 1.7333,
"step": 540
},
{
"epoch": 0.24119482835488185,
"grad_norm": 0.11000026762485504,
"learning_rate": 9.625177227104271e-05,
"loss": 1.7553,
"step": 541
},
{
"epoch": 0.24164065983058403,
"grad_norm": 0.10352633148431778,
"learning_rate": 9.622100079364956e-05,
"loss": 1.7039,
"step": 542
},
{
"epoch": 0.24208649130628623,
"grad_norm": 0.10331304371356964,
"learning_rate": 9.61901084810761e-05,
"loss": 1.7822,
"step": 543
},
{
"epoch": 0.2425323227819884,
"grad_norm": 0.10469511151313782,
"learning_rate": 9.615909541408393e-05,
"loss": 1.7547,
"step": 544
},
{
"epoch": 0.2429781542576906,
"grad_norm": 0.10332876443862915,
"learning_rate": 9.612796167375018e-05,
"loss": 1.7111,
"step": 545
},
{
"epoch": 0.24342398573339277,
"grad_norm": 0.09848453104496002,
"learning_rate": 9.609670734146758e-05,
"loss": 1.7534,
"step": 546
},
{
"epoch": 0.24386981720909495,
"grad_norm": 0.10669830441474915,
"learning_rate": 9.606533249894405e-05,
"loss": 1.7884,
"step": 547
},
{
"epoch": 0.24431564868479716,
"grad_norm": 0.10300056636333466,
"learning_rate": 9.60338372282026e-05,
"loss": 1.7938,
"step": 548
},
{
"epoch": 0.24476148016049934,
"grad_norm": 0.10064051300287247,
"learning_rate": 9.600222161158104e-05,
"loss": 1.7611,
"step": 549
},
{
"epoch": 0.24520731163620152,
"grad_norm": 0.1035415306687355,
"learning_rate": 9.597048573173179e-05,
"loss": 1.7826,
"step": 550
},
{
"epoch": 0.2456531431119037,
"grad_norm": 0.09879010170698166,
"learning_rate": 9.593862967162176e-05,
"loss": 1.7996,
"step": 551
},
{
"epoch": 0.24609897458760588,
"grad_norm": 0.10481975227594376,
"learning_rate": 9.590665351453195e-05,
"loss": 1.8005,
"step": 552
},
{
"epoch": 0.24654480606330806,
"grad_norm": 0.09874304383993149,
"learning_rate": 9.587455734405735e-05,
"loss": 1.6885,
"step": 553
},
{
"epoch": 0.24699063753901027,
"grad_norm": 0.09937682002782822,
"learning_rate": 9.584234124410674e-05,
"loss": 1.712,
"step": 554
},
{
"epoch": 0.24743646901471245,
"grad_norm": 0.10098837316036224,
"learning_rate": 9.581000529890238e-05,
"loss": 1.8059,
"step": 555
},
{
"epoch": 0.24788230049041463,
"grad_norm": 0.09516670554876328,
"learning_rate": 9.577754959297989e-05,
"loss": 1.6813,
"step": 556
},
{
"epoch": 0.2483281319661168,
"grad_norm": 0.10069796442985535,
"learning_rate": 9.574497421118793e-05,
"loss": 1.7759,
"step": 557
},
{
"epoch": 0.24877396344181898,
"grad_norm": 0.10863727331161499,
"learning_rate": 9.571227923868806e-05,
"loss": 1.8615,
"step": 558
},
{
"epoch": 0.24921979491752116,
"grad_norm": 0.09395399689674377,
"learning_rate": 9.567946476095447e-05,
"loss": 1.7796,
"step": 559
},
{
"epoch": 0.24966562639322337,
"grad_norm": 0.10641838610172272,
"learning_rate": 9.56465308637738e-05,
"loss": 1.7415,
"step": 560
},
{
"epoch": 0.2501114578689255,
"grad_norm": 0.1218976229429245,
"learning_rate": 9.561347763324484e-05,
"loss": 1.7625,
"step": 561
},
{
"epoch": 0.25055728934462773,
"grad_norm": 0.10557776689529419,
"learning_rate": 9.55803051557784e-05,
"loss": 1.8792,
"step": 562
},
{
"epoch": 0.25100312082032994,
"grad_norm": 0.10291140526533127,
"learning_rate": 9.554701351809699e-05,
"loss": 1.7841,
"step": 563
},
{
"epoch": 0.2514489522960321,
"grad_norm": 0.11566982418298721,
"learning_rate": 9.551360280723468e-05,
"loss": 1.7505,
"step": 564
},
{
"epoch": 0.2518947837717343,
"grad_norm": 0.10798952728509903,
"learning_rate": 9.54800731105368e-05,
"loss": 1.7658,
"step": 565
},
{
"epoch": 0.25234061524743645,
"grad_norm": 0.10329020768404007,
"learning_rate": 9.544642451565979e-05,
"loss": 1.7718,
"step": 566
},
{
"epoch": 0.25278644672313866,
"grad_norm": 0.11663586646318436,
"learning_rate": 9.541265711057085e-05,
"loss": 1.7697,
"step": 567
},
{
"epoch": 0.25323227819884087,
"grad_norm": 0.12301573902368546,
"learning_rate": 9.537877098354786e-05,
"loss": 1.7592,
"step": 568
},
{
"epoch": 0.253678109674543,
"grad_norm": 0.11213916540145874,
"learning_rate": 9.534476622317902e-05,
"loss": 1.7233,
"step": 569
},
{
"epoch": 0.2541239411502452,
"grad_norm": 0.1298297941684723,
"learning_rate": 9.531064291836272e-05,
"loss": 1.8142,
"step": 570
},
{
"epoch": 0.2545697726259474,
"grad_norm": 0.10630843788385391,
"learning_rate": 9.527640115830722e-05,
"loss": 1.759,
"step": 571
},
{
"epoch": 0.2550156041016496,
"grad_norm": 0.10889295488595963,
"learning_rate": 9.524204103253046e-05,
"loss": 1.687,
"step": 572
},
{
"epoch": 0.25546143557735174,
"grad_norm": 0.11184940487146378,
"learning_rate": 9.520756263085984e-05,
"loss": 1.7896,
"step": 573
},
{
"epoch": 0.25590726705305394,
"grad_norm": 0.11805959790945053,
"learning_rate": 9.517296604343198e-05,
"loss": 1.7935,
"step": 574
},
{
"epoch": 0.25635309852875615,
"grad_norm": 0.10778935998678207,
"learning_rate": 9.513825136069242e-05,
"loss": 1.7705,
"step": 575
},
{
"epoch": 0.2567989300044583,
"grad_norm": 0.11594793200492859,
"learning_rate": 9.510341867339549e-05,
"loss": 1.7849,
"step": 576
},
{
"epoch": 0.2572447614801605,
"grad_norm": 0.1344304084777832,
"learning_rate": 9.506846807260398e-05,
"loss": 1.8054,
"step": 577
},
{
"epoch": 0.25769059295586266,
"grad_norm": 0.10295383632183075,
"learning_rate": 9.503339964968898e-05,
"loss": 1.8318,
"step": 578
},
{
"epoch": 0.25813642443156487,
"grad_norm": 0.10751260817050934,
"learning_rate": 9.499821349632954e-05,
"loss": 1.7701,
"step": 579
},
{
"epoch": 0.2585822559072671,
"grad_norm": 0.11230424046516418,
"learning_rate": 9.496290970451258e-05,
"loss": 1.8024,
"step": 580
},
{
"epoch": 0.25902808738296923,
"grad_norm": 0.10016710311174393,
"learning_rate": 9.492748836653247e-05,
"loss": 1.7464,
"step": 581
},
{
"epoch": 0.25947391885867144,
"grad_norm": 0.10333780199289322,
"learning_rate": 9.489194957499094e-05,
"loss": 1.7395,
"step": 582
},
{
"epoch": 0.2599197503343736,
"grad_norm": 0.11180590093135834,
"learning_rate": 9.485629342279678e-05,
"loss": 1.7252,
"step": 583
},
{
"epoch": 0.2603655818100758,
"grad_norm": 0.1132645308971405,
"learning_rate": 9.482052000316552e-05,
"loss": 1.7613,
"step": 584
},
{
"epoch": 0.26081141328577795,
"grad_norm": 0.09877246618270874,
"learning_rate": 9.478462940961935e-05,
"loss": 1.7275,
"step": 585
},
{
"epoch": 0.26125724476148016,
"grad_norm": 0.09782719612121582,
"learning_rate": 9.474862173598676e-05,
"loss": 1.7107,
"step": 586
},
{
"epoch": 0.26170307623718236,
"grad_norm": 0.1147351935505867,
"learning_rate": 9.471249707640228e-05,
"loss": 1.7902,
"step": 587
},
{
"epoch": 0.2621489077128845,
"grad_norm": 0.11956936866044998,
"learning_rate": 9.467625552530633e-05,
"loss": 1.9301,
"step": 588
},
{
"epoch": 0.2625947391885867,
"grad_norm": 0.11668745428323746,
"learning_rate": 9.46398971774449e-05,
"loss": 1.8152,
"step": 589
},
{
"epoch": 0.2630405706642889,
"grad_norm": 0.11700372397899628,
"learning_rate": 9.460342212786932e-05,
"loss": 1.7475,
"step": 590
},
{
"epoch": 0.2634864021399911,
"grad_norm": 0.10470305383205414,
"learning_rate": 9.456683047193601e-05,
"loss": 1.8155,
"step": 591
},
{
"epoch": 0.2639322336156933,
"grad_norm": 0.10678225755691528,
"learning_rate": 9.453012230530623e-05,
"loss": 1.7535,
"step": 592
},
{
"epoch": 0.26437806509139544,
"grad_norm": 0.10009190440177917,
"learning_rate": 9.449329772394583e-05,
"loss": 1.7347,
"step": 593
},
{
"epoch": 0.26482389656709765,
"grad_norm": 0.09668190032243729,
"learning_rate": 9.445635682412501e-05,
"loss": 1.6987,
"step": 594
},
{
"epoch": 0.2652697280427998,
"grad_norm": 0.11986253410577774,
"learning_rate": 9.441929970241807e-05,
"loss": 1.7334,
"step": 595
},
{
"epoch": 0.265715559518502,
"grad_norm": 0.11259319633245468,
"learning_rate": 9.438212645570312e-05,
"loss": 1.6829,
"step": 596
},
{
"epoch": 0.2661613909942042,
"grad_norm": 0.10347830504179001,
"learning_rate": 9.43448371811619e-05,
"loss": 1.7448,
"step": 597
},
{
"epoch": 0.26660722246990637,
"grad_norm": 0.10251055657863617,
"learning_rate": 9.43074319762794e-05,
"loss": 1.7388,
"step": 598
},
{
"epoch": 0.2670530539456086,
"grad_norm": 0.10402775555849075,
"learning_rate": 9.42699109388438e-05,
"loss": 1.8039,
"step": 599
},
{
"epoch": 0.26749888542131073,
"grad_norm": 0.10319799929857254,
"learning_rate": 9.4232274166946e-05,
"loss": 1.7369,
"step": 600
},
{
"epoch": 0.26794471689701294,
"grad_norm": 0.13266697525978088,
"learning_rate": 9.419452175897951e-05,
"loss": 1.7386,
"step": 601
},
{
"epoch": 0.2683905483727151,
"grad_norm": 0.10923372954130173,
"learning_rate": 9.415665381364013e-05,
"loss": 1.6451,
"step": 602
},
{
"epoch": 0.2688363798484173,
"grad_norm": 0.1264653503894806,
"learning_rate": 9.411867042992575e-05,
"loss": 1.8005,
"step": 603
},
{
"epoch": 0.2692822113241195,
"grad_norm": 0.12177695333957672,
"learning_rate": 9.408057170713597e-05,
"loss": 1.7846,
"step": 604
},
{
"epoch": 0.26972804279982165,
"grad_norm": 0.09421692043542862,
"learning_rate": 9.404235774487201e-05,
"loss": 1.6672,
"step": 605
},
{
"epoch": 0.27017387427552386,
"grad_norm": 0.12999457120895386,
"learning_rate": 9.400402864303628e-05,
"loss": 1.6792,
"step": 606
},
{
"epoch": 0.270619705751226,
"grad_norm": 0.10277573019266129,
"learning_rate": 9.396558450183226e-05,
"loss": 1.6691,
"step": 607
},
{
"epoch": 0.2710655372269282,
"grad_norm": 0.13512097299098969,
"learning_rate": 9.392702542176411e-05,
"loss": 1.7776,
"step": 608
},
{
"epoch": 0.27151136870263043,
"grad_norm": 0.11266525089740753,
"learning_rate": 9.388835150363656e-05,
"loss": 1.8094,
"step": 609
},
{
"epoch": 0.2719572001783326,
"grad_norm": 0.10716194659471512,
"learning_rate": 9.384956284855451e-05,
"loss": 1.7369,
"step": 610
},
{
"epoch": 0.2724030316540348,
"grad_norm": 0.13045336306095123,
"learning_rate": 9.381065955792279e-05,
"loss": 1.7207,
"step": 611
},
{
"epoch": 0.27284886312973694,
"grad_norm": 0.10751914978027344,
"learning_rate": 9.377164173344597e-05,
"loss": 1.7664,
"step": 612
},
{
"epoch": 0.27329469460543915,
"grad_norm": 0.11501648277044296,
"learning_rate": 9.373250947712801e-05,
"loss": 1.6887,
"step": 613
},
{
"epoch": 0.27374052608114136,
"grad_norm": 0.11839734017848969,
"learning_rate": 9.369326289127208e-05,
"loss": 1.6888,
"step": 614
},
{
"epoch": 0.2741863575568435,
"grad_norm": 0.10788834095001221,
"learning_rate": 9.365390207848017e-05,
"loss": 1.8236,
"step": 615
},
{
"epoch": 0.2746321890325457,
"grad_norm": 0.17978796362876892,
"learning_rate": 9.361442714165296e-05,
"loss": 1.7788,
"step": 616
},
{
"epoch": 0.27507802050824787,
"grad_norm": 0.09851440042257309,
"learning_rate": 9.357483818398941e-05,
"loss": 1.6821,
"step": 617
},
{
"epoch": 0.2755238519839501,
"grad_norm": 0.12011748552322388,
"learning_rate": 9.353513530898664e-05,
"loss": 1.7793,
"step": 618
},
{
"epoch": 0.2759696834596522,
"grad_norm": 0.11903136223554611,
"learning_rate": 9.349531862043952e-05,
"loss": 1.7077,
"step": 619
},
{
"epoch": 0.27641551493535443,
"grad_norm": 0.09823181480169296,
"learning_rate": 9.345538822244052e-05,
"loss": 1.8155,
"step": 620
},
{
"epoch": 0.27686134641105664,
"grad_norm": 0.12731784582138062,
"learning_rate": 9.341534421937932e-05,
"loss": 1.7296,
"step": 621
},
{
"epoch": 0.2773071778867588,
"grad_norm": 0.10990069806575775,
"learning_rate": 9.337518671594264e-05,
"loss": 1.728,
"step": 622
},
{
"epoch": 0.277753009362461,
"grad_norm": 0.11084982007741928,
"learning_rate": 9.333491581711391e-05,
"loss": 1.7316,
"step": 623
},
{
"epoch": 0.27819884083816315,
"grad_norm": 0.1286562830209732,
"learning_rate": 9.329453162817302e-05,
"loss": 1.8244,
"step": 624
},
{
"epoch": 0.27864467231386536,
"grad_norm": 0.10190364718437195,
"learning_rate": 9.3254034254696e-05,
"loss": 1.6568,
"step": 625
},
{
"epoch": 0.27909050378956757,
"grad_norm": 0.1281125694513321,
"learning_rate": 9.32134238025548e-05,
"loss": 1.6819,
"step": 626
},
{
"epoch": 0.2795363352652697,
"grad_norm": 0.09961622953414917,
"learning_rate": 9.317270037791701e-05,
"loss": 1.701,
"step": 627
},
{
"epoch": 0.2799821667409719,
"grad_norm": 0.11898019164800644,
"learning_rate": 9.313186408724552e-05,
"loss": 1.8417,
"step": 628
},
{
"epoch": 0.2804279982166741,
"grad_norm": 0.09727369993925095,
"learning_rate": 9.309091503729832e-05,
"loss": 1.7277,
"step": 629
},
{
"epoch": 0.2808738296923763,
"grad_norm": 0.10436810553073883,
"learning_rate": 9.304985333512816e-05,
"loss": 1.7431,
"step": 630
},
{
"epoch": 0.28131966116807844,
"grad_norm": 0.10497339069843292,
"learning_rate": 9.300867908808233e-05,
"loss": 1.7598,
"step": 631
},
{
"epoch": 0.28176549264378065,
"grad_norm": 0.10627975314855576,
"learning_rate": 9.296739240380229e-05,
"loss": 1.838,
"step": 632
},
{
"epoch": 0.28221132411948285,
"grad_norm": 0.10740294307470322,
"learning_rate": 9.292599339022351e-05,
"loss": 1.8158,
"step": 633
},
{
"epoch": 0.282657155595185,
"grad_norm": 0.09920445829629898,
"learning_rate": 9.288448215557508e-05,
"loss": 1.7993,
"step": 634
},
{
"epoch": 0.2831029870708872,
"grad_norm": 0.11240369826555252,
"learning_rate": 9.284285880837946e-05,
"loss": 1.7373,
"step": 635
},
{
"epoch": 0.28354881854658937,
"grad_norm": 0.09972943365573883,
"learning_rate": 9.280112345745225e-05,
"loss": 1.7783,
"step": 636
},
{
"epoch": 0.2839946500222916,
"grad_norm": 0.10276699811220169,
"learning_rate": 9.275927621190182e-05,
"loss": 1.7574,
"step": 637
},
{
"epoch": 0.2844404814979938,
"grad_norm": 0.10892293602228165,
"learning_rate": 9.271731718112909e-05,
"loss": 1.8024,
"step": 638
},
{
"epoch": 0.28488631297369593,
"grad_norm": 0.09949132800102234,
"learning_rate": 9.267524647482718e-05,
"loss": 1.7966,
"step": 639
},
{
"epoch": 0.28533214444939814,
"grad_norm": 0.10552310943603516,
"learning_rate": 9.26330642029812e-05,
"loss": 1.7942,
"step": 640
},
{
"epoch": 0.2857779759251003,
"grad_norm": 0.0973183810710907,
"learning_rate": 9.259077047586791e-05,
"loss": 1.7071,
"step": 641
},
{
"epoch": 0.2862238074008025,
"grad_norm": 0.1038060411810875,
"learning_rate": 9.254836540405548e-05,
"loss": 1.7795,
"step": 642
},
{
"epoch": 0.2866696388765047,
"grad_norm": 0.10009002685546875,
"learning_rate": 9.250584909840312e-05,
"loss": 1.7206,
"step": 643
},
{
"epoch": 0.28711547035220686,
"grad_norm": 0.10105922818183899,
"learning_rate": 9.246322167006085e-05,
"loss": 1.8153,
"step": 644
},
{
"epoch": 0.28756130182790907,
"grad_norm": 0.10735410451889038,
"learning_rate": 9.242048323046922e-05,
"loss": 1.6993,
"step": 645
},
{
"epoch": 0.2880071333036112,
"grad_norm": 0.10262249410152435,
"learning_rate": 9.237763389135895e-05,
"loss": 1.7954,
"step": 646
},
{
"epoch": 0.2884529647793134,
"grad_norm": 0.0978655070066452,
"learning_rate": 9.233467376475074e-05,
"loss": 1.6637,
"step": 647
},
{
"epoch": 0.2888987962550156,
"grad_norm": 0.09992211312055588,
"learning_rate": 9.229160296295488e-05,
"loss": 1.7779,
"step": 648
},
{
"epoch": 0.2893446277307178,
"grad_norm": 0.10095684975385666,
"learning_rate": 9.224842159857101e-05,
"loss": 1.7613,
"step": 649
},
{
"epoch": 0.28979045920642,
"grad_norm": 0.10354265570640564,
"learning_rate": 9.220512978448783e-05,
"loss": 1.7798,
"step": 650
},
{
"epoch": 0.29023629068212214,
"grad_norm": 0.10295833647251129,
"learning_rate": 9.216172763388277e-05,
"loss": 1.8473,
"step": 651
},
{
"epoch": 0.29068212215782435,
"grad_norm": 0.11315377056598663,
"learning_rate": 9.211821526022169e-05,
"loss": 1.7302,
"step": 652
},
{
"epoch": 0.2911279536335265,
"grad_norm": 0.10181237012147903,
"learning_rate": 9.207459277725865e-05,
"loss": 1.7379,
"step": 653
},
{
"epoch": 0.2915737851092287,
"grad_norm": 0.09915487468242645,
"learning_rate": 9.203086029903555e-05,
"loss": 1.7095,
"step": 654
},
{
"epoch": 0.2920196165849309,
"grad_norm": 0.11117501556873322,
"learning_rate": 9.198701793988182e-05,
"loss": 1.7644,
"step": 655
},
{
"epoch": 0.29246544806063307,
"grad_norm": 0.11145615577697754,
"learning_rate": 9.19430658144142e-05,
"loss": 1.8052,
"step": 656
},
{
"epoch": 0.2929112795363353,
"grad_norm": 0.10658877342939377,
"learning_rate": 9.189900403753637e-05,
"loss": 1.7516,
"step": 657
},
{
"epoch": 0.29335711101203743,
"grad_norm": 0.10004567354917526,
"learning_rate": 9.185483272443867e-05,
"loss": 1.703,
"step": 658
},
{
"epoch": 0.29380294248773964,
"grad_norm": 0.10918276011943817,
"learning_rate": 9.181055199059778e-05,
"loss": 1.833,
"step": 659
},
{
"epoch": 0.29424877396344185,
"grad_norm": 0.10067199170589447,
"learning_rate": 9.176616195177647e-05,
"loss": 1.8387,
"step": 660
},
{
"epoch": 0.294694605439144,
"grad_norm": 0.10059603303670883,
"learning_rate": 9.172166272402323e-05,
"loss": 1.7104,
"step": 661
},
{
"epoch": 0.2951404369148462,
"grad_norm": 0.105819933116436,
"learning_rate": 9.167705442367205e-05,
"loss": 1.8195,
"step": 662
},
{
"epoch": 0.29558626839054836,
"grad_norm": 0.1009010523557663,
"learning_rate": 9.163233716734205e-05,
"loss": 1.6715,
"step": 663
},
{
"epoch": 0.29603209986625056,
"grad_norm": 0.1113704964518547,
"learning_rate": 9.158751107193715e-05,
"loss": 1.7876,
"step": 664
},
{
"epoch": 0.2964779313419527,
"grad_norm": 0.11176806688308716,
"learning_rate": 9.154257625464586e-05,
"loss": 1.8244,
"step": 665
},
{
"epoch": 0.2969237628176549,
"grad_norm": 0.10417098551988602,
"learning_rate": 9.149753283294089e-05,
"loss": 1.8423,
"step": 666
},
{
"epoch": 0.29736959429335713,
"grad_norm": 0.14246045053005219,
"learning_rate": 9.145238092457891e-05,
"loss": 1.7231,
"step": 667
},
{
"epoch": 0.2978154257690593,
"grad_norm": 0.10592841356992722,
"learning_rate": 9.140712064760015e-05,
"loss": 1.5981,
"step": 668
},
{
"epoch": 0.2982612572447615,
"grad_norm": 0.12447135895490646,
"learning_rate": 9.136175212032818e-05,
"loss": 1.7673,
"step": 669
},
{
"epoch": 0.29870708872046364,
"grad_norm": 0.10616061836481094,
"learning_rate": 9.13162754613696e-05,
"loss": 1.7584,
"step": 670
},
{
"epoch": 0.29915292019616585,
"grad_norm": 0.11225946247577667,
"learning_rate": 9.127069078961363e-05,
"loss": 1.7267,
"step": 671
},
{
"epoch": 0.29959875167186806,
"grad_norm": 0.12012822926044464,
"learning_rate": 9.122499822423192e-05,
"loss": 1.7901,
"step": 672
},
{
"epoch": 0.3000445831475702,
"grad_norm": 0.10362541675567627,
"learning_rate": 9.117919788467814e-05,
"loss": 1.7764,
"step": 673
},
{
"epoch": 0.3004904146232724,
"grad_norm": 0.1028263196349144,
"learning_rate": 9.113328989068777e-05,
"loss": 1.7554,
"step": 674
},
{
"epoch": 0.30093624609897457,
"grad_norm": 0.10624345391988754,
"learning_rate": 9.108727436227769e-05,
"loss": 1.674,
"step": 675
},
{
"epoch": 0.3013820775746768,
"grad_norm": 0.10278113186359406,
"learning_rate": 9.10411514197459e-05,
"loss": 1.7295,
"step": 676
},
{
"epoch": 0.301827909050379,
"grad_norm": 0.10787946730852127,
"learning_rate": 9.099492118367123e-05,
"loss": 1.8075,
"step": 677
},
{
"epoch": 0.30227374052608114,
"grad_norm": 0.10508739948272705,
"learning_rate": 9.094858377491302e-05,
"loss": 1.7407,
"step": 678
},
{
"epoch": 0.30271957200178334,
"grad_norm": 0.1076112911105156,
"learning_rate": 9.090213931461078e-05,
"loss": 1.8355,
"step": 679
},
{
"epoch": 0.3031654034774855,
"grad_norm": 0.10336123406887054,
"learning_rate": 9.085558792418385e-05,
"loss": 1.7438,
"step": 680
},
{
"epoch": 0.3036112349531877,
"grad_norm": 0.10836680233478546,
"learning_rate": 9.080892972533118e-05,
"loss": 1.7572,
"step": 681
},
{
"epoch": 0.30405706642888986,
"grad_norm": 0.10023204982280731,
"learning_rate": 9.076216484003088e-05,
"loss": 1.7863,
"step": 682
},
{
"epoch": 0.30450289790459206,
"grad_norm": 0.10532896965742111,
"learning_rate": 9.071529339054001e-05,
"loss": 1.8234,
"step": 683
},
{
"epoch": 0.30494872938029427,
"grad_norm": 0.10081358253955841,
"learning_rate": 9.066831549939424e-05,
"loss": 1.7181,
"step": 684
},
{
"epoch": 0.3053945608559964,
"grad_norm": 0.10051680356264114,
"learning_rate": 9.062123128940745e-05,
"loss": 1.7803,
"step": 685
},
{
"epoch": 0.30584039233169863,
"grad_norm": 0.10239288210868835,
"learning_rate": 9.05740408836715e-05,
"loss": 1.7236,
"step": 686
},
{
"epoch": 0.3062862238074008,
"grad_norm": 0.10214550048112869,
"learning_rate": 9.052674440555591e-05,
"loss": 1.7361,
"step": 687
},
{
"epoch": 0.306732055283103,
"grad_norm": 0.10382306575775146,
"learning_rate": 9.047934197870745e-05,
"loss": 1.7391,
"step": 688
},
{
"epoch": 0.3071778867588052,
"grad_norm": 0.09891895949840546,
"learning_rate": 9.04318337270499e-05,
"loss": 1.751,
"step": 689
},
{
"epoch": 0.30762371823450735,
"grad_norm": 0.10158421099185944,
"learning_rate": 9.038421977478368e-05,
"loss": 1.7981,
"step": 690
},
{
"epoch": 0.30806954971020956,
"grad_norm": 0.11618820577859879,
"learning_rate": 9.033650024638556e-05,
"loss": 1.8077,
"step": 691
},
{
"epoch": 0.3085153811859117,
"grad_norm": 0.10197657346725464,
"learning_rate": 9.02886752666083e-05,
"loss": 1.7542,
"step": 692
},
{
"epoch": 0.3089612126616139,
"grad_norm": 0.10608278214931488,
"learning_rate": 9.024074496048036e-05,
"loss": 1.699,
"step": 693
},
{
"epoch": 0.30940704413731607,
"grad_norm": 0.12072121351957321,
"learning_rate": 9.019270945330553e-05,
"loss": 1.8274,
"step": 694
},
{
"epoch": 0.3098528756130183,
"grad_norm": 0.10368560254573822,
"learning_rate": 9.014456887066265e-05,
"loss": 1.7176,
"step": 695
},
{
"epoch": 0.3102987070887205,
"grad_norm": 0.11684264242649078,
"learning_rate": 9.009632333840526e-05,
"loss": 1.7334,
"step": 696
},
{
"epoch": 0.31074453856442263,
"grad_norm": 0.12157313525676727,
"learning_rate": 9.004797298266121e-05,
"loss": 1.6811,
"step": 697
},
{
"epoch": 0.31119037004012484,
"grad_norm": 0.10719422250986099,
"learning_rate": 8.999951792983249e-05,
"loss": 1.861,
"step": 698
},
{
"epoch": 0.311636201515827,
"grad_norm": 0.1389751136302948,
"learning_rate": 8.995095830659471e-05,
"loss": 1.8158,
"step": 699
},
{
"epoch": 0.3120820329915292,
"grad_norm": 0.10673972964286804,
"learning_rate": 8.990229423989691e-05,
"loss": 1.7408,
"step": 700
},
{
"epoch": 0.3125278644672314,
"grad_norm": 0.13494205474853516,
"learning_rate": 8.985352585696115e-05,
"loss": 1.7022,
"step": 701
},
{
"epoch": 0.31297369594293356,
"grad_norm": 0.10108482092618942,
"learning_rate": 8.980465328528219e-05,
"loss": 1.7795,
"step": 702
},
{
"epoch": 0.31341952741863577,
"grad_norm": 0.1139780655503273,
"learning_rate": 8.975567665262722e-05,
"loss": 1.7743,
"step": 703
},
{
"epoch": 0.3138653588943379,
"grad_norm": 0.11329539865255356,
"learning_rate": 8.970659608703544e-05,
"loss": 1.7211,
"step": 704
},
{
"epoch": 0.3143111903700401,
"grad_norm": 0.11979568749666214,
"learning_rate": 8.965741171681777e-05,
"loss": 1.7155,
"step": 705
},
{
"epoch": 0.31475702184574234,
"grad_norm": 0.11180669069290161,
"learning_rate": 8.960812367055646e-05,
"loss": 1.7385,
"step": 706
},
{
"epoch": 0.3152028533214445,
"grad_norm": 0.10925803333520889,
"learning_rate": 8.955873207710491e-05,
"loss": 1.7446,
"step": 707
},
{
"epoch": 0.3156486847971467,
"grad_norm": 0.11179474741220474,
"learning_rate": 8.950923706558712e-05,
"loss": 1.7988,
"step": 708
},
{
"epoch": 0.31609451627284885,
"grad_norm": 0.10495036840438843,
"learning_rate": 8.945963876539747e-05,
"loss": 1.7294,
"step": 709
},
{
"epoch": 0.31654034774855105,
"grad_norm": 0.10598697513341904,
"learning_rate": 8.940993730620043e-05,
"loss": 1.8047,
"step": 710
},
{
"epoch": 0.3169861792242532,
"grad_norm": 0.09499679505825043,
"learning_rate": 8.936013281793006e-05,
"loss": 1.7609,
"step": 711
},
{
"epoch": 0.3174320106999554,
"grad_norm": 0.10312512516975403,
"learning_rate": 8.931022543078988e-05,
"loss": 1.7815,
"step": 712
},
{
"epoch": 0.3178778421756576,
"grad_norm": 0.0959397554397583,
"learning_rate": 8.926021527525232e-05,
"loss": 1.7275,
"step": 713
},
{
"epoch": 0.3183236736513598,
"grad_norm": 0.10189943760633469,
"learning_rate": 8.921010248205852e-05,
"loss": 1.719,
"step": 714
},
{
"epoch": 0.318769505127062,
"grad_norm": 0.11259514838457108,
"learning_rate": 8.915988718221795e-05,
"loss": 1.7694,
"step": 715
},
{
"epoch": 0.31921533660276413,
"grad_norm": 0.09886849671602249,
"learning_rate": 8.910956950700807e-05,
"loss": 1.7336,
"step": 716
},
{
"epoch": 0.31966116807846634,
"grad_norm": 0.10284537822008133,
"learning_rate": 8.905914958797394e-05,
"loss": 1.6911,
"step": 717
},
{
"epoch": 0.32010699955416855,
"grad_norm": 0.10941079258918762,
"learning_rate": 8.900862755692793e-05,
"loss": 1.7933,
"step": 718
},
{
"epoch": 0.3205528310298707,
"grad_norm": 0.10098347067832947,
"learning_rate": 8.89580035459494e-05,
"loss": 1.7171,
"step": 719
},
{
"epoch": 0.3209986625055729,
"grad_norm": 0.10070615261793137,
"learning_rate": 8.890727768738424e-05,
"loss": 1.7475,
"step": 720
},
{
"epoch": 0.32144449398127506,
"grad_norm": 0.1005801260471344,
"learning_rate": 8.885645011384467e-05,
"loss": 1.6891,
"step": 721
},
{
"epoch": 0.32189032545697727,
"grad_norm": 0.11231444031000137,
"learning_rate": 8.88055209582088e-05,
"loss": 1.7646,
"step": 722
},
{
"epoch": 0.3223361569326795,
"grad_norm": 0.10064563155174255,
"learning_rate": 8.87544903536203e-05,
"loss": 1.7614,
"step": 723
},
{
"epoch": 0.3227819884083816,
"grad_norm": 0.12413723766803741,
"learning_rate": 8.870335843348803e-05,
"loss": 1.833,
"step": 724
},
{
"epoch": 0.32322781988408383,
"grad_norm": 0.10709035396575928,
"learning_rate": 8.865212533148578e-05,
"loss": 1.8072,
"step": 725
},
{
"epoch": 0.323673651359786,
"grad_norm": 0.10878479480743408,
"learning_rate": 8.86007911815518e-05,
"loss": 1.7746,
"step": 726
},
{
"epoch": 0.3241194828354882,
"grad_norm": 0.10093686729669571,
"learning_rate": 8.854935611788856e-05,
"loss": 1.7114,
"step": 727
},
{
"epoch": 0.32456531431119034,
"grad_norm": 0.104001484811306,
"learning_rate": 8.84978202749623e-05,
"loss": 1.7267,
"step": 728
},
{
"epoch": 0.32501114578689255,
"grad_norm": 0.10399822145700455,
"learning_rate": 8.844618378750274e-05,
"loss": 1.6674,
"step": 729
},
{
"epoch": 0.32545697726259476,
"grad_norm": 0.10074197500944138,
"learning_rate": 8.839444679050276e-05,
"loss": 1.8201,
"step": 730
},
{
"epoch": 0.3259028087382969,
"grad_norm": 0.0986226350069046,
"learning_rate": 8.834260941921793e-05,
"loss": 1.7204,
"step": 731
},
{
"epoch": 0.3263486402139991,
"grad_norm": 0.09890744090080261,
"learning_rate": 8.829067180916626e-05,
"loss": 1.7293,
"step": 732
},
{
"epoch": 0.32679447168970127,
"grad_norm": 0.10762915015220642,
"learning_rate": 8.823863409612785e-05,
"loss": 1.7617,
"step": 733
},
{
"epoch": 0.3272403031654035,
"grad_norm": 0.10301407426595688,
"learning_rate": 8.818649641614442e-05,
"loss": 1.7908,
"step": 734
},
{
"epoch": 0.3276861346411057,
"grad_norm": 0.11062656342983246,
"learning_rate": 8.81342589055191e-05,
"loss": 1.8814,
"step": 735
},
{
"epoch": 0.32813196611680784,
"grad_norm": 0.09678314626216888,
"learning_rate": 8.808192170081598e-05,
"loss": 1.7229,
"step": 736
},
{
"epoch": 0.32857779759251005,
"grad_norm": 0.11262750625610352,
"learning_rate": 8.802948493885979e-05,
"loss": 1.7935,
"step": 737
},
{
"epoch": 0.3290236290682122,
"grad_norm": 0.10415447503328323,
"learning_rate": 8.797694875673549e-05,
"loss": 1.803,
"step": 738
},
{
"epoch": 0.3294694605439144,
"grad_norm": 0.10533297061920166,
"learning_rate": 8.792431329178801e-05,
"loss": 1.7182,
"step": 739
},
{
"epoch": 0.32991529201961656,
"grad_norm": 0.12811556458473206,
"learning_rate": 8.787157868162184e-05,
"loss": 1.7461,
"step": 740
},
{
"epoch": 0.33036112349531876,
"grad_norm": 0.10370204597711563,
"learning_rate": 8.781874506410058e-05,
"loss": 1.6425,
"step": 741
},
{
"epoch": 0.330806954971021,
"grad_norm": 0.12818044424057007,
"learning_rate": 8.776581257734673e-05,
"loss": 1.7587,
"step": 742
},
{
"epoch": 0.3312527864467231,
"grad_norm": 0.10504760593175888,
"learning_rate": 8.771278135974129e-05,
"loss": 1.7205,
"step": 743
},
{
"epoch": 0.33169861792242533,
"grad_norm": 0.11437215656042099,
"learning_rate": 8.76596515499233e-05,
"loss": 1.7635,
"step": 744
},
{
"epoch": 0.3321444493981275,
"grad_norm": 0.12294165045022964,
"learning_rate": 8.760642328678961e-05,
"loss": 1.7693,
"step": 745
},
{
"epoch": 0.3325902808738297,
"grad_norm": 0.11856231838464737,
"learning_rate": 8.755309670949438e-05,
"loss": 1.7543,
"step": 746
},
{
"epoch": 0.3330361123495319,
"grad_norm": 0.1157640665769577,
"learning_rate": 8.749967195744891e-05,
"loss": 1.7417,
"step": 747
},
{
"epoch": 0.33348194382523405,
"grad_norm": 0.10265911370515823,
"learning_rate": 8.744614917032102e-05,
"loss": 1.8101,
"step": 748
},
{
"epoch": 0.33392777530093626,
"grad_norm": 0.11393480747938156,
"learning_rate": 8.739252848803494e-05,
"loss": 1.827,
"step": 749
},
{
"epoch": 0.3343736067766384,
"grad_norm": 0.11828850209712982,
"learning_rate": 8.733881005077073e-05,
"loss": 1.7994,
"step": 750
},
{
"epoch": 0.3348194382523406,
"grad_norm": 0.13639211654663086,
"learning_rate": 8.728499399896411e-05,
"loss": 1.8083,
"step": 751
},
{
"epoch": 0.3352652697280428,
"grad_norm": 0.1207522377371788,
"learning_rate": 8.723108047330591e-05,
"loss": 1.849,
"step": 752
},
{
"epoch": 0.335711101203745,
"grad_norm": 0.10233356058597565,
"learning_rate": 8.71770696147418e-05,
"loss": 1.7851,
"step": 753
},
{
"epoch": 0.3361569326794472,
"grad_norm": 0.12627649307250977,
"learning_rate": 8.712296156447195e-05,
"loss": 1.7407,
"step": 754
},
{
"epoch": 0.33660276415514934,
"grad_norm": 0.11139927059412003,
"learning_rate": 8.706875646395056e-05,
"loss": 1.7328,
"step": 755
},
{
"epoch": 0.33704859563085154,
"grad_norm": 0.10584481805562973,
"learning_rate": 8.701445445488559e-05,
"loss": 1.8498,
"step": 756
},
{
"epoch": 0.3374944271065537,
"grad_norm": 0.12187878787517548,
"learning_rate": 8.696005567923835e-05,
"loss": 1.8176,
"step": 757
},
{
"epoch": 0.3379402585822559,
"grad_norm": 0.10171040147542953,
"learning_rate": 8.690556027922309e-05,
"loss": 1.7123,
"step": 758
},
{
"epoch": 0.3383860900579581,
"grad_norm": 0.10234849154949188,
"learning_rate": 8.685096839730669e-05,
"loss": 1.6689,
"step": 759
},
{
"epoch": 0.33883192153366026,
"grad_norm": 0.1236603707075119,
"learning_rate": 8.679628017620826e-05,
"loss": 1.7884,
"step": 760
},
{
"epoch": 0.33927775300936247,
"grad_norm": 0.10490363091230392,
"learning_rate": 8.674149575889874e-05,
"loss": 1.6872,
"step": 761
},
{
"epoch": 0.3397235844850646,
"grad_norm": 0.1045655757188797,
"learning_rate": 8.66866152886006e-05,
"loss": 1.8306,
"step": 762
},
{
"epoch": 0.34016941596076683,
"grad_norm": 0.12073557823896408,
"learning_rate": 8.663163890878741e-05,
"loss": 1.7083,
"step": 763
},
{
"epoch": 0.34061524743646904,
"grad_norm": 0.10340608656406403,
"learning_rate": 8.657656676318346e-05,
"loss": 1.762,
"step": 764
},
{
"epoch": 0.3410610789121712,
"grad_norm": 0.1112038865685463,
"learning_rate": 8.652139899576338e-05,
"loss": 1.7414,
"step": 765
},
{
"epoch": 0.3415069103878734,
"grad_norm": 0.10261017829179764,
"learning_rate": 8.646613575075183e-05,
"loss": 1.6622,
"step": 766
},
{
"epoch": 0.34195274186357555,
"grad_norm": 0.10223604738712311,
"learning_rate": 8.641077717262304e-05,
"loss": 1.7472,
"step": 767
},
{
"epoch": 0.34239857333927776,
"grad_norm": 0.12250372767448425,
"learning_rate": 8.635532340610052e-05,
"loss": 1.8064,
"step": 768
},
{
"epoch": 0.34284440481497996,
"grad_norm": 0.09999125450849533,
"learning_rate": 8.629977459615655e-05,
"loss": 1.8215,
"step": 769
},
{
"epoch": 0.3432902362906821,
"grad_norm": 0.11505675315856934,
"learning_rate": 8.624413088801195e-05,
"loss": 1.7155,
"step": 770
},
{
"epoch": 0.3437360677663843,
"grad_norm": 0.11126726865768433,
"learning_rate": 8.61883924271356e-05,
"loss": 1.7364,
"step": 771
},
{
"epoch": 0.3441818992420865,
"grad_norm": 0.12990163266658783,
"learning_rate": 8.613255935924407e-05,
"loss": 1.7978,
"step": 772
},
{
"epoch": 0.3446277307177887,
"grad_norm": 0.10395561903715134,
"learning_rate": 8.607663183030133e-05,
"loss": 1.7903,
"step": 773
},
{
"epoch": 0.34507356219349083,
"grad_norm": 0.09887439757585526,
"learning_rate": 8.602060998651824e-05,
"loss": 1.8127,
"step": 774
},
{
"epoch": 0.34551939366919304,
"grad_norm": 0.10434427112340927,
"learning_rate": 8.596449397435225e-05,
"loss": 1.753,
"step": 775
},
{
"epoch": 0.34596522514489525,
"grad_norm": 0.09902716428041458,
"learning_rate": 8.590828394050696e-05,
"loss": 1.7167,
"step": 776
},
{
"epoch": 0.3464110566205974,
"grad_norm": 0.09984233975410461,
"learning_rate": 8.585198003193182e-05,
"loss": 1.7583,
"step": 777
},
{
"epoch": 0.3468568880962996,
"grad_norm": 0.10259772092103958,
"learning_rate": 8.579558239582169e-05,
"loss": 1.7546,
"step": 778
},
{
"epoch": 0.34730271957200176,
"grad_norm": 0.10787268728017807,
"learning_rate": 8.57390911796164e-05,
"loss": 1.8332,
"step": 779
},
{
"epoch": 0.34774855104770397,
"grad_norm": 0.09571395814418793,
"learning_rate": 8.568250653100049e-05,
"loss": 1.7568,
"step": 780
},
{
"epoch": 0.3481943825234062,
"grad_norm": 0.1108977273106575,
"learning_rate": 8.562582859790276e-05,
"loss": 1.8004,
"step": 781
},
{
"epoch": 0.34864021399910833,
"grad_norm": 0.10714055597782135,
"learning_rate": 8.556905752849585e-05,
"loss": 1.7684,
"step": 782
},
{
"epoch": 0.34908604547481054,
"grad_norm": 0.0989801436662674,
"learning_rate": 8.551219347119587e-05,
"loss": 1.7697,
"step": 783
},
{
"epoch": 0.3495318769505127,
"grad_norm": 0.108929343521595,
"learning_rate": 8.545523657466208e-05,
"loss": 1.7389,
"step": 784
},
{
"epoch": 0.3499777084262149,
"grad_norm": 0.10202984511852264,
"learning_rate": 8.539818698779642e-05,
"loss": 1.7065,
"step": 785
},
{
"epoch": 0.3504235399019171,
"grad_norm": 0.10615679621696472,
"learning_rate": 8.534104485974315e-05,
"loss": 1.7559,
"step": 786
},
{
"epoch": 0.35086937137761925,
"grad_norm": 0.09619362652301788,
"learning_rate": 8.528381033988847e-05,
"loss": 1.6943,
"step": 787
},
{
"epoch": 0.35131520285332146,
"grad_norm": 0.11341307312250137,
"learning_rate": 8.522648357786012e-05,
"loss": 1.8292,
"step": 788
},
{
"epoch": 0.3517610343290236,
"grad_norm": 0.1040128841996193,
"learning_rate": 8.516906472352695e-05,
"loss": 1.7282,
"step": 789
},
{
"epoch": 0.3522068658047258,
"grad_norm": 0.10357475280761719,
"learning_rate": 8.511155392699861e-05,
"loss": 1.7556,
"step": 790
},
{
"epoch": 0.352652697280428,
"grad_norm": 0.1057363897562027,
"learning_rate": 8.505395133862512e-05,
"loss": 1.7416,
"step": 791
},
{
"epoch": 0.3530985287561302,
"grad_norm": 0.10828213393688202,
"learning_rate": 8.499625710899643e-05,
"loss": 1.7946,
"step": 792
},
{
"epoch": 0.3535443602318324,
"grad_norm": 0.10245328396558762,
"learning_rate": 8.493847138894209e-05,
"loss": 1.7229,
"step": 793
},
{
"epoch": 0.35399019170753454,
"grad_norm": 0.09904945641756058,
"learning_rate": 8.488059432953083e-05,
"loss": 1.6658,
"step": 794
},
{
"epoch": 0.35443602318323675,
"grad_norm": 0.10616844892501831,
"learning_rate": 8.482262608207016e-05,
"loss": 1.7807,
"step": 795
},
{
"epoch": 0.3548818546589389,
"grad_norm": 0.100911445915699,
"learning_rate": 8.476456679810603e-05,
"loss": 1.7845,
"step": 796
},
{
"epoch": 0.3553276861346411,
"grad_norm": 0.10363345593214035,
"learning_rate": 8.470641662942229e-05,
"loss": 1.7841,
"step": 797
},
{
"epoch": 0.3557735176103433,
"grad_norm": 0.11251815408468246,
"learning_rate": 8.464817572804048e-05,
"loss": 1.8003,
"step": 798
},
{
"epoch": 0.35621934908604547,
"grad_norm": 0.10455453395843506,
"learning_rate": 8.45898442462193e-05,
"loss": 1.7326,
"step": 799
},
{
"epoch": 0.3566651805617477,
"grad_norm": 0.10756085067987442,
"learning_rate": 8.453142233645426e-05,
"loss": 1.7837,
"step": 800
},
{
"epoch": 0.3571110120374498,
"grad_norm": 0.11072846502065659,
"learning_rate": 8.447291015147728e-05,
"loss": 1.6734,
"step": 801
},
{
"epoch": 0.35755684351315203,
"grad_norm": 0.1010904461145401,
"learning_rate": 8.441430784425628e-05,
"loss": 1.7014,
"step": 802
},
{
"epoch": 0.3580026749888542,
"grad_norm": 0.10389654338359833,
"learning_rate": 8.435561556799476e-05,
"loss": 1.721,
"step": 803
},
{
"epoch": 0.3584485064645564,
"grad_norm": 0.12034213542938232,
"learning_rate": 8.42968334761315e-05,
"loss": 1.8055,
"step": 804
},
{
"epoch": 0.3588943379402586,
"grad_norm": 0.10815682262182236,
"learning_rate": 8.423796172234e-05,
"loss": 1.7042,
"step": 805
},
{
"epoch": 0.35934016941596075,
"grad_norm": 0.11416835337877274,
"learning_rate": 8.417900046052822e-05,
"loss": 1.803,
"step": 806
},
{
"epoch": 0.35978600089166296,
"grad_norm": 0.10993671417236328,
"learning_rate": 8.411994984483809e-05,
"loss": 1.8025,
"step": 807
},
{
"epoch": 0.3602318323673651,
"grad_norm": 0.10727176070213318,
"learning_rate": 8.406081002964516e-05,
"loss": 1.8108,
"step": 808
},
{
"epoch": 0.3606776638430673,
"grad_norm": 0.12041471898555756,
"learning_rate": 8.400158116955813e-05,
"loss": 1.8352,
"step": 809
},
{
"epoch": 0.3611234953187695,
"grad_norm": 0.1135798841714859,
"learning_rate": 8.394226341941855e-05,
"loss": 1.7065,
"step": 810
},
{
"epoch": 0.3615693267944717,
"grad_norm": 0.10153985023498535,
"learning_rate": 8.38828569343003e-05,
"loss": 1.698,
"step": 811
},
{
"epoch": 0.3620151582701739,
"grad_norm": 0.1046518012881279,
"learning_rate": 8.382336186950928e-05,
"loss": 1.8206,
"step": 812
},
{
"epoch": 0.36246098974587604,
"grad_norm": 0.12123867124319077,
"learning_rate": 8.376377838058293e-05,
"loss": 1.7826,
"step": 813
},
{
"epoch": 0.36290682122157825,
"grad_norm": 0.10180552303791046,
"learning_rate": 8.370410662328992e-05,
"loss": 1.7394,
"step": 814
},
{
"epoch": 0.36335265269728045,
"grad_norm": 0.11939540505409241,
"learning_rate": 8.364434675362955e-05,
"loss": 1.6841,
"step": 815
},
{
"epoch": 0.3637984841729826,
"grad_norm": 0.09830567240715027,
"learning_rate": 8.358449892783162e-05,
"loss": 1.6928,
"step": 816
},
{
"epoch": 0.3642443156486848,
"grad_norm": 0.11208126693964005,
"learning_rate": 8.352456330235578e-05,
"loss": 1.7631,
"step": 817
},
{
"epoch": 0.36469014712438697,
"grad_norm": 0.10451742261648178,
"learning_rate": 8.346454003389126e-05,
"loss": 1.687,
"step": 818
},
{
"epoch": 0.3651359786000892,
"grad_norm": 0.10860004276037216,
"learning_rate": 8.340442927935634e-05,
"loss": 1.8163,
"step": 819
},
{
"epoch": 0.3655818100757913,
"grad_norm": 0.11413165181875229,
"learning_rate": 8.334423119589814e-05,
"loss": 1.7119,
"step": 820
},
{
"epoch": 0.36602764155149353,
"grad_norm": 0.10770432651042938,
"learning_rate": 8.328394594089198e-05,
"loss": 1.6936,
"step": 821
},
{
"epoch": 0.36647347302719574,
"grad_norm": 0.10249630361795425,
"learning_rate": 8.322357367194109e-05,
"loss": 1.7624,
"step": 822
},
{
"epoch": 0.3669193045028979,
"grad_norm": 0.11303991824388504,
"learning_rate": 8.316311454687622e-05,
"loss": 1.7155,
"step": 823
},
{
"epoch": 0.3673651359786001,
"grad_norm": 0.11809582263231277,
"learning_rate": 8.310256872375513e-05,
"loss": 1.7404,
"step": 824
},
{
"epoch": 0.36781096745430225,
"grad_norm": 0.11696501076221466,
"learning_rate": 8.304193636086231e-05,
"loss": 1.8064,
"step": 825
},
{
"epoch": 0.36825679893000446,
"grad_norm": 0.10870379209518433,
"learning_rate": 8.298121761670838e-05,
"loss": 1.7048,
"step": 826
},
{
"epoch": 0.36870263040570667,
"grad_norm": 0.1033722534775734,
"learning_rate": 8.292041265002991e-05,
"loss": 1.7168,
"step": 827
},
{
"epoch": 0.3691484618814088,
"grad_norm": 0.12060517072677612,
"learning_rate": 8.28595216197888e-05,
"loss": 1.7298,
"step": 828
},
{
"epoch": 0.369594293357111,
"grad_norm": 0.10030078887939453,
"learning_rate": 8.279854468517197e-05,
"loss": 1.6818,
"step": 829
},
{
"epoch": 0.3700401248328132,
"grad_norm": 0.10428495705127716,
"learning_rate": 8.273748200559091e-05,
"loss": 1.7219,
"step": 830
},
{
"epoch": 0.3704859563085154,
"grad_norm": 0.10251472890377045,
"learning_rate": 8.267633374068128e-05,
"loss": 1.6958,
"step": 831
},
{
"epoch": 0.3709317877842176,
"grad_norm": 0.09608680009841919,
"learning_rate": 8.261510005030248e-05,
"loss": 1.6923,
"step": 832
},
{
"epoch": 0.37137761925991974,
"grad_norm": 0.11226716637611389,
"learning_rate": 8.255378109453727e-05,
"loss": 1.6901,
"step": 833
},
{
"epoch": 0.37182345073562195,
"grad_norm": 0.10870599746704102,
"learning_rate": 8.249237703369124e-05,
"loss": 1.8445,
"step": 834
},
{
"epoch": 0.3722692822113241,
"grad_norm": 0.09965885430574417,
"learning_rate": 8.243088802829255e-05,
"loss": 1.7454,
"step": 835
},
{
"epoch": 0.3727151136870263,
"grad_norm": 0.10317207127809525,
"learning_rate": 8.236931423909138e-05,
"loss": 1.6892,
"step": 836
},
{
"epoch": 0.37316094516272846,
"grad_norm": 0.11535860598087311,
"learning_rate": 8.230765582705962e-05,
"loss": 1.7708,
"step": 837
},
{
"epoch": 0.37360677663843067,
"grad_norm": 0.11052210628986359,
"learning_rate": 8.224591295339029e-05,
"loss": 1.7287,
"step": 838
},
{
"epoch": 0.3740526081141329,
"grad_norm": 0.11029904335737228,
"learning_rate": 8.218408577949731e-05,
"loss": 1.6476,
"step": 839
},
{
"epoch": 0.37449843958983503,
"grad_norm": 0.09702277183532715,
"learning_rate": 8.212217446701493e-05,
"loss": 1.6835,
"step": 840
},
{
"epoch": 0.37494427106553724,
"grad_norm": 0.11581635475158691,
"learning_rate": 8.206017917779742e-05,
"loss": 1.664,
"step": 841
},
{
"epoch": 0.3753901025412394,
"grad_norm": 0.11711280047893524,
"learning_rate": 8.199810007391851e-05,
"loss": 1.791,
"step": 842
},
{
"epoch": 0.3758359340169416,
"grad_norm": 0.11244585365056992,
"learning_rate": 8.19359373176711e-05,
"loss": 1.7739,
"step": 843
},
{
"epoch": 0.3762817654926438,
"grad_norm": 0.11165203154087067,
"learning_rate": 8.187369107156677e-05,
"loss": 1.7156,
"step": 844
},
{
"epoch": 0.37672759696834596,
"grad_norm": 0.12729769945144653,
"learning_rate": 8.18113614983354e-05,
"loss": 1.7991,
"step": 845
},
{
"epoch": 0.37717342844404816,
"grad_norm": 0.12019409239292145,
"learning_rate": 8.17489487609246e-05,
"loss": 1.8176,
"step": 846
},
{
"epoch": 0.3776192599197503,
"grad_norm": 0.11194216459989548,
"learning_rate": 8.168645302249955e-05,
"loss": 1.7708,
"step": 847
},
{
"epoch": 0.3780650913954525,
"grad_norm": 0.1206713616847992,
"learning_rate": 8.16238744464423e-05,
"loss": 1.766,
"step": 848
},
{
"epoch": 0.3785109228711547,
"grad_norm": 0.12124496698379517,
"learning_rate": 8.156121319635154e-05,
"loss": 1.7569,
"step": 849
},
{
"epoch": 0.3789567543468569,
"grad_norm": 0.09880439937114716,
"learning_rate": 8.149846943604203e-05,
"loss": 1.7735,
"step": 850
},
{
"epoch": 0.3794025858225591,
"grad_norm": 0.10147947072982788,
"learning_rate": 8.143564332954425e-05,
"loss": 1.6676,
"step": 851
},
{
"epoch": 0.37984841729826124,
"grad_norm": 0.11051192134618759,
"learning_rate": 8.137273504110401e-05,
"loss": 1.8027,
"step": 852
},
{
"epoch": 0.38029424877396345,
"grad_norm": 0.10278802365064621,
"learning_rate": 8.130974473518189e-05,
"loss": 1.7454,
"step": 853
},
{
"epoch": 0.3807400802496656,
"grad_norm": 0.10420636832714081,
"learning_rate": 8.124667257645295e-05,
"loss": 1.7277,
"step": 854
},
{
"epoch": 0.3811859117253678,
"grad_norm": 0.10417424887418747,
"learning_rate": 8.118351872980622e-05,
"loss": 1.7438,
"step": 855
},
{
"epoch": 0.38163174320107,
"grad_norm": 0.10878739506006241,
"learning_rate": 8.112028336034424e-05,
"loss": 1.8723,
"step": 856
},
{
"epoch": 0.38207757467677217,
"grad_norm": 0.1156105324625969,
"learning_rate": 8.105696663338278e-05,
"loss": 1.773,
"step": 857
},
{
"epoch": 0.3825234061524744,
"grad_norm": 0.10178980976343155,
"learning_rate": 8.099356871445017e-05,
"loss": 1.8089,
"step": 858
},
{
"epoch": 0.38296923762817653,
"grad_norm": 0.09697715938091278,
"learning_rate": 8.093008976928711e-05,
"loss": 1.7698,
"step": 859
},
{
"epoch": 0.38341506910387874,
"grad_norm": 0.12025973200798035,
"learning_rate": 8.086652996384605e-05,
"loss": 1.7726,
"step": 860
},
{
"epoch": 0.38386090057958094,
"grad_norm": 0.10172765702009201,
"learning_rate": 8.080288946429089e-05,
"loss": 1.7617,
"step": 861
},
{
"epoch": 0.3843067320552831,
"grad_norm": 0.10850796103477478,
"learning_rate": 8.073916843699642e-05,
"loss": 1.763,
"step": 862
},
{
"epoch": 0.3847525635309853,
"grad_norm": 0.09900850802659988,
"learning_rate": 8.067536704854806e-05,
"loss": 1.7959,
"step": 863
},
{
"epoch": 0.38519839500668746,
"grad_norm": 0.10934197157621384,
"learning_rate": 8.061148546574119e-05,
"loss": 1.6899,
"step": 864
},
{
"epoch": 0.38564422648238966,
"grad_norm": 0.10856257379055023,
"learning_rate": 8.054752385558096e-05,
"loss": 1.6949,
"step": 865
},
{
"epoch": 0.3860900579580918,
"grad_norm": 0.09824354201555252,
"learning_rate": 8.048348238528162e-05,
"loss": 1.7959,
"step": 866
},
{
"epoch": 0.386535889433794,
"grad_norm": 0.1041949912905693,
"learning_rate": 8.041936122226628e-05,
"loss": 1.7235,
"step": 867
},
{
"epoch": 0.38698172090949623,
"grad_norm": 0.11082298308610916,
"learning_rate": 8.035516053416639e-05,
"loss": 1.8256,
"step": 868
},
{
"epoch": 0.3874275523851984,
"grad_norm": 0.1017066240310669,
"learning_rate": 8.029088048882126e-05,
"loss": 1.824,
"step": 869
},
{
"epoch": 0.3878733838609006,
"grad_norm": 0.10484788566827774,
"learning_rate": 8.022652125427767e-05,
"loss": 1.7068,
"step": 870
},
{
"epoch": 0.38831921533660274,
"grad_norm": 0.10868432372808456,
"learning_rate": 8.016208299878946e-05,
"loss": 1.7908,
"step": 871
},
{
"epoch": 0.38876504681230495,
"grad_norm": 0.10017553716897964,
"learning_rate": 8.009756589081702e-05,
"loss": 1.7462,
"step": 872
},
{
"epoch": 0.38921087828800716,
"grad_norm": 0.10471358895301819,
"learning_rate": 8.003297009902689e-05,
"loss": 1.6814,
"step": 873
},
{
"epoch": 0.3896567097637093,
"grad_norm": 0.10709407180547714,
"learning_rate": 7.996829579229129e-05,
"loss": 1.7381,
"step": 874
},
{
"epoch": 0.3901025412394115,
"grad_norm": 0.10078425705432892,
"learning_rate": 7.990354313968774e-05,
"loss": 1.8174,
"step": 875
},
{
"epoch": 0.39054837271511367,
"grad_norm": 0.11307930946350098,
"learning_rate": 7.98387123104986e-05,
"loss": 1.6826,
"step": 876
},
{
"epoch": 0.3909942041908159,
"grad_norm": 0.12270081043243408,
"learning_rate": 7.97738034742105e-05,
"loss": 1.8393,
"step": 877
},
{
"epoch": 0.3914400356665181,
"grad_norm": 0.09995368123054504,
"learning_rate": 7.970881680051415e-05,
"loss": 1.7451,
"step": 878
},
{
"epoch": 0.39188586714222023,
"grad_norm": 0.12107348442077637,
"learning_rate": 7.964375245930364e-05,
"loss": 1.7117,
"step": 879
},
{
"epoch": 0.39233169861792244,
"grad_norm": 0.135823056101799,
"learning_rate": 7.957861062067614e-05,
"loss": 1.7305,
"step": 880
},
{
"epoch": 0.3927775300936246,
"grad_norm": 0.12123044580221176,
"learning_rate": 7.95133914549314e-05,
"loss": 1.8042,
"step": 881
},
{
"epoch": 0.3932233615693268,
"grad_norm": 0.12587501108646393,
"learning_rate": 7.944809513257136e-05,
"loss": 1.6705,
"step": 882
},
{
"epoch": 0.39366919304502895,
"grad_norm": 0.11547011882066727,
"learning_rate": 7.938272182429969e-05,
"loss": 1.7793,
"step": 883
},
{
"epoch": 0.39411502452073116,
"grad_norm": 0.12046027183532715,
"learning_rate": 7.931727170102123e-05,
"loss": 1.742,
"step": 884
},
{
"epoch": 0.39456085599643337,
"grad_norm": 0.13458503782749176,
"learning_rate": 7.925174493384175e-05,
"loss": 1.685,
"step": 885
},
{
"epoch": 0.3950066874721355,
"grad_norm": 0.09983829408884048,
"learning_rate": 7.918614169406731e-05,
"loss": 1.7114,
"step": 886
},
{
"epoch": 0.39545251894783773,
"grad_norm": 0.10733943432569504,
"learning_rate": 7.91204621532039e-05,
"loss": 1.7349,
"step": 887
},
{
"epoch": 0.3958983504235399,
"grad_norm": 0.13182266056537628,
"learning_rate": 7.905470648295703e-05,
"loss": 1.8216,
"step": 888
},
{
"epoch": 0.3963441818992421,
"grad_norm": 0.10008315742015839,
"learning_rate": 7.898887485523121e-05,
"loss": 1.7765,
"step": 889
},
{
"epoch": 0.3967900133749443,
"grad_norm": 0.11194812506437302,
"learning_rate": 7.892296744212949e-05,
"loss": 1.8017,
"step": 890
},
{
"epoch": 0.39723584485064645,
"grad_norm": 0.11453627049922943,
"learning_rate": 7.88569844159531e-05,
"loss": 1.7742,
"step": 891
},
{
"epoch": 0.39768167632634865,
"grad_norm": 0.10469194501638412,
"learning_rate": 7.87909259492009e-05,
"loss": 1.7731,
"step": 892
},
{
"epoch": 0.3981275078020508,
"grad_norm": 0.12564517557621002,
"learning_rate": 7.872479221456901e-05,
"loss": 1.7969,
"step": 893
},
{
"epoch": 0.398573339277753,
"grad_norm": 0.10213175415992737,
"learning_rate": 7.86585833849503e-05,
"loss": 1.7788,
"step": 894
},
{
"epoch": 0.3990191707534552,
"grad_norm": 0.10134770721197128,
"learning_rate": 7.859229963343396e-05,
"loss": 1.734,
"step": 895
},
{
"epoch": 0.3994650022291574,
"grad_norm": 0.10407637059688568,
"learning_rate": 7.852594113330507e-05,
"loss": 1.7997,
"step": 896
},
{
"epoch": 0.3999108337048596,
"grad_norm": 0.12344498932361603,
"learning_rate": 7.84595080580441e-05,
"loss": 1.7263,
"step": 897
},
{
"epoch": 0.40035666518056173,
"grad_norm": 0.09978921711444855,
"learning_rate": 7.839300058132646e-05,
"loss": 1.7498,
"step": 898
},
{
"epoch": 0.40080249665626394,
"grad_norm": 0.10168612003326416,
"learning_rate": 7.832641887702215e-05,
"loss": 1.7377,
"step": 899
},
{
"epoch": 0.4012483281319661,
"grad_norm": 0.10925289243459702,
"learning_rate": 7.825976311919514e-05,
"loss": 1.7709,
"step": 900
},
{
"epoch": 0.4016941596076683,
"grad_norm": 0.09782040864229202,
"learning_rate": 7.819303348210301e-05,
"loss": 1.6763,
"step": 901
},
{
"epoch": 0.4021399910833705,
"grad_norm": 0.11235174536705017,
"learning_rate": 7.812623014019654e-05,
"loss": 1.8178,
"step": 902
},
{
"epoch": 0.40258582255907266,
"grad_norm": 0.10949194431304932,
"learning_rate": 7.805935326811912e-05,
"loss": 1.6997,
"step": 903
},
{
"epoch": 0.40303165403477487,
"grad_norm": 0.10270405560731888,
"learning_rate": 7.799240304070644e-05,
"loss": 1.6857,
"step": 904
},
{
"epoch": 0.403477485510477,
"grad_norm": 0.10442759096622467,
"learning_rate": 7.792537963298588e-05,
"loss": 1.7305,
"step": 905
},
{
"epoch": 0.4039233169861792,
"grad_norm": 0.10635087639093399,
"learning_rate": 7.785828322017619e-05,
"loss": 1.7457,
"step": 906
},
{
"epoch": 0.40436914846188143,
"grad_norm": 0.10277074575424194,
"learning_rate": 7.779111397768702e-05,
"loss": 1.8433,
"step": 907
},
{
"epoch": 0.4048149799375836,
"grad_norm": 0.14527611434459686,
"learning_rate": 7.772387208111829e-05,
"loss": 1.7629,
"step": 908
},
{
"epoch": 0.4052608114132858,
"grad_norm": 0.10182760655879974,
"learning_rate": 7.765655770625997e-05,
"loss": 1.73,
"step": 909
},
{
"epoch": 0.40570664288898795,
"grad_norm": 0.10519295930862427,
"learning_rate": 7.758917102909149e-05,
"loss": 1.6893,
"step": 910
},
{
"epoch": 0.40615247436469015,
"grad_norm": 0.10474564880132675,
"learning_rate": 7.752171222578126e-05,
"loss": 1.7359,
"step": 911
},
{
"epoch": 0.4065983058403923,
"grad_norm": 0.11640966683626175,
"learning_rate": 7.745418147268628e-05,
"loss": 1.7324,
"step": 912
},
{
"epoch": 0.4070441373160945,
"grad_norm": 0.10456699132919312,
"learning_rate": 7.738657894635166e-05,
"loss": 1.7251,
"step": 913
},
{
"epoch": 0.4074899687917967,
"grad_norm": 0.10772830247879028,
"learning_rate": 7.731890482351007e-05,
"loss": 1.7782,
"step": 914
},
{
"epoch": 0.40793580026749887,
"grad_norm": 0.10231928527355194,
"learning_rate": 7.725115928108147e-05,
"loss": 1.6776,
"step": 915
},
{
"epoch": 0.4083816317432011,
"grad_norm": 0.1091284230351448,
"learning_rate": 7.718334249617242e-05,
"loss": 1.7308,
"step": 916
},
{
"epoch": 0.40882746321890323,
"grad_norm": 0.10097773373126984,
"learning_rate": 7.711545464607583e-05,
"loss": 1.6829,
"step": 917
},
{
"epoch": 0.40927329469460544,
"grad_norm": 0.10814758390188217,
"learning_rate": 7.704749590827031e-05,
"loss": 1.7772,
"step": 918
},
{
"epoch": 0.40971912617030765,
"grad_norm": 0.11410879343748093,
"learning_rate": 7.697946646041983e-05,
"loss": 1.7914,
"step": 919
},
{
"epoch": 0.4101649576460098,
"grad_norm": 0.10181721299886703,
"learning_rate": 7.691136648037323e-05,
"loss": 1.8624,
"step": 920
},
{
"epoch": 0.410610789121712,
"grad_norm": 0.11508486419916153,
"learning_rate": 7.68431961461637e-05,
"loss": 1.7383,
"step": 921
},
{
"epoch": 0.41105662059741416,
"grad_norm": 0.1035197377204895,
"learning_rate": 7.67749556360084e-05,
"loss": 1.6701,
"step": 922
},
{
"epoch": 0.41150245207311636,
"grad_norm": 0.10268811881542206,
"learning_rate": 7.670664512830795e-05,
"loss": 1.7915,
"step": 923
},
{
"epoch": 0.4119482835488186,
"grad_norm": 0.1045726016163826,
"learning_rate": 7.663826480164591e-05,
"loss": 1.7613,
"step": 924
},
{
"epoch": 0.4123941150245207,
"grad_norm": 0.10786459594964981,
"learning_rate": 7.656981483478842e-05,
"loss": 1.725,
"step": 925
},
{
"epoch": 0.41283994650022293,
"grad_norm": 0.0991087257862091,
"learning_rate": 7.650129540668366e-05,
"loss": 1.7125,
"step": 926
},
{
"epoch": 0.4132857779759251,
"grad_norm": 0.1012926772236824,
"learning_rate": 7.643270669646139e-05,
"loss": 1.732,
"step": 927
},
{
"epoch": 0.4137316094516273,
"grad_norm": 0.11466870456933975,
"learning_rate": 7.636404888343254e-05,
"loss": 1.736,
"step": 928
},
{
"epoch": 0.41417744092732944,
"grad_norm": 0.10373403877019882,
"learning_rate": 7.629532214708863e-05,
"loss": 1.7281,
"step": 929
},
{
"epoch": 0.41462327240303165,
"grad_norm": 0.0952754020690918,
"learning_rate": 7.622652666710142e-05,
"loss": 1.7324,
"step": 930
},
{
"epoch": 0.41506910387873386,
"grad_norm": 0.12399623543024063,
"learning_rate": 7.615766262332235e-05,
"loss": 1.7118,
"step": 931
},
{
"epoch": 0.415514935354436,
"grad_norm": 0.10459206998348236,
"learning_rate": 7.608873019578213e-05,
"loss": 1.6998,
"step": 932
},
{
"epoch": 0.4159607668301382,
"grad_norm": 0.10095109045505524,
"learning_rate": 7.601972956469023e-05,
"loss": 1.6593,
"step": 933
},
{
"epoch": 0.41640659830584037,
"grad_norm": 0.10682646185159683,
"learning_rate": 7.595066091043443e-05,
"loss": 1.6368,
"step": 934
},
{
"epoch": 0.4168524297815426,
"grad_norm": 0.10391956567764282,
"learning_rate": 7.588152441358036e-05,
"loss": 1.7122,
"step": 935
},
{
"epoch": 0.4172982612572448,
"grad_norm": 0.10885828733444214,
"learning_rate": 7.581232025487097e-05,
"loss": 1.821,
"step": 936
},
{
"epoch": 0.41774409273294694,
"grad_norm": 0.10067553073167801,
"learning_rate": 7.574304861522613e-05,
"loss": 1.6445,
"step": 937
},
{
"epoch": 0.41818992420864914,
"grad_norm": 0.10583972930908203,
"learning_rate": 7.56737096757421e-05,
"loss": 1.6759,
"step": 938
},
{
"epoch": 0.4186357556843513,
"grad_norm": 0.10121052712202072,
"learning_rate": 7.560430361769112e-05,
"loss": 1.7127,
"step": 939
},
{
"epoch": 0.4190815871600535,
"grad_norm": 0.10300959646701813,
"learning_rate": 7.553483062252086e-05,
"loss": 1.7523,
"step": 940
},
{
"epoch": 0.4195274186357557,
"grad_norm": 0.10437580943107605,
"learning_rate": 7.546529087185398e-05,
"loss": 1.7558,
"step": 941
},
{
"epoch": 0.41997325011145786,
"grad_norm": 0.10165751725435257,
"learning_rate": 7.539568454748771e-05,
"loss": 1.7411,
"step": 942
},
{
"epoch": 0.42041908158716007,
"grad_norm": 0.10225626826286316,
"learning_rate": 7.532601183139329e-05,
"loss": 1.7106,
"step": 943
},
{
"epoch": 0.4208649130628622,
"grad_norm": 0.10220157355070114,
"learning_rate": 7.525627290571548e-05,
"loss": 1.6801,
"step": 944
},
{
"epoch": 0.42131074453856443,
"grad_norm": 0.10341238975524902,
"learning_rate": 7.518646795277222e-05,
"loss": 1.7248,
"step": 945
},
{
"epoch": 0.4217565760142666,
"grad_norm": 0.0989287719130516,
"learning_rate": 7.511659715505399e-05,
"loss": 1.6682,
"step": 946
},
{
"epoch": 0.4222024074899688,
"grad_norm": 0.10885773599147797,
"learning_rate": 7.504666069522348e-05,
"loss": 1.7329,
"step": 947
},
{
"epoch": 0.422648238965671,
"grad_norm": 0.10581452399492264,
"learning_rate": 7.497665875611496e-05,
"loss": 1.6973,
"step": 948
},
{
"epoch": 0.42309407044137315,
"grad_norm": 0.09856841713190079,
"learning_rate": 7.490659152073393e-05,
"loss": 1.7109,
"step": 949
},
{
"epoch": 0.42353990191707536,
"grad_norm": 0.11418459564447403,
"learning_rate": 7.483645917225657e-05,
"loss": 1.7239,
"step": 950
},
{
"epoch": 0.4239857333927775,
"grad_norm": 0.09815758466720581,
"learning_rate": 7.476626189402935e-05,
"loss": 1.7385,
"step": 951
},
{
"epoch": 0.4244315648684797,
"grad_norm": 0.10807161778211594,
"learning_rate": 7.46959998695684e-05,
"loss": 1.7986,
"step": 952
},
{
"epoch": 0.4248773963441819,
"grad_norm": 0.10402785986661911,
"learning_rate": 7.462567328255915e-05,
"loss": 1.7664,
"step": 953
},
{
"epoch": 0.4253232278198841,
"grad_norm": 0.10258588939905167,
"learning_rate": 7.45552823168558e-05,
"loss": 1.6883,
"step": 954
},
{
"epoch": 0.4257690592955863,
"grad_norm": 0.10306514799594879,
"learning_rate": 7.448482715648091e-05,
"loss": 1.7705,
"step": 955
},
{
"epoch": 0.42621489077128843,
"grad_norm": 0.09964229166507721,
"learning_rate": 7.441430798562477e-05,
"loss": 1.7301,
"step": 956
},
{
"epoch": 0.42666072224699064,
"grad_norm": 0.11213322728872299,
"learning_rate": 7.434372498864512e-05,
"loss": 1.75,
"step": 957
},
{
"epoch": 0.4271065537226928,
"grad_norm": 0.10760463774204254,
"learning_rate": 7.427307835006648e-05,
"loss": 1.8366,
"step": 958
},
{
"epoch": 0.427552385198395,
"grad_norm": 0.10547094792127609,
"learning_rate": 7.420236825457976e-05,
"loss": 1.7509,
"step": 959
},
{
"epoch": 0.4279982166740972,
"grad_norm": 0.1085076704621315,
"learning_rate": 7.41315948870418e-05,
"loss": 1.8143,
"step": 960
},
{
"epoch": 0.42844404814979936,
"grad_norm": 0.10108537971973419,
"learning_rate": 7.40607584324748e-05,
"loss": 1.6559,
"step": 961
},
{
"epoch": 0.42888987962550157,
"grad_norm": 0.09640628844499588,
"learning_rate": 7.398985907606597e-05,
"loss": 1.6969,
"step": 962
},
{
"epoch": 0.4293357111012037,
"grad_norm": 0.11157038807868958,
"learning_rate": 7.391889700316686e-05,
"loss": 1.7665,
"step": 963
},
{
"epoch": 0.42978154257690593,
"grad_norm": 0.11129970103502274,
"learning_rate": 7.384787239929306e-05,
"loss": 1.7608,
"step": 964
},
{
"epoch": 0.43022737405260814,
"grad_norm": 0.11040521413087845,
"learning_rate": 7.37767854501236e-05,
"loss": 1.7051,
"step": 965
},
{
"epoch": 0.4306732055283103,
"grad_norm": 0.10680396854877472,
"learning_rate": 7.370563634150049e-05,
"loss": 1.7713,
"step": 966
},
{
"epoch": 0.4311190370040125,
"grad_norm": 0.10174407064914703,
"learning_rate": 7.363442525942826e-05,
"loss": 1.7686,
"step": 967
},
{
"epoch": 0.43156486847971465,
"grad_norm": 0.12041493505239487,
"learning_rate": 7.356315239007347e-05,
"loss": 1.748,
"step": 968
},
{
"epoch": 0.43201069995541685,
"grad_norm": 0.09997862577438354,
"learning_rate": 7.349181791976419e-05,
"loss": 1.7256,
"step": 969
},
{
"epoch": 0.43245653143111906,
"grad_norm": 0.10042174160480499,
"learning_rate": 7.342042203498951e-05,
"loss": 1.66,
"step": 970
},
{
"epoch": 0.4329023629068212,
"grad_norm": 0.10617858916521072,
"learning_rate": 7.334896492239913e-05,
"loss": 1.744,
"step": 971
},
{
"epoch": 0.4333481943825234,
"grad_norm": 0.10458917170763016,
"learning_rate": 7.327744676880278e-05,
"loss": 1.7612,
"step": 972
},
{
"epoch": 0.4337940258582256,
"grad_norm": 0.09675281494855881,
"learning_rate": 7.320586776116977e-05,
"loss": 1.6433,
"step": 973
},
{
"epoch": 0.4342398573339278,
"grad_norm": 0.10298484563827515,
"learning_rate": 7.31342280866285e-05,
"loss": 1.7117,
"step": 974
},
{
"epoch": 0.43468568880962993,
"grad_norm": 0.1019211933016777,
"learning_rate": 7.306252793246601e-05,
"loss": 1.7035,
"step": 975
},
{
"epoch": 0.43513152028533214,
"grad_norm": 0.10027551651000977,
"learning_rate": 7.29907674861274e-05,
"loss": 1.6851,
"step": 976
},
{
"epoch": 0.43557735176103435,
"grad_norm": 0.10205865651369095,
"learning_rate": 7.291894693521542e-05,
"loss": 1.7492,
"step": 977
},
{
"epoch": 0.4360231832367365,
"grad_norm": 0.10458935052156448,
"learning_rate": 7.284706646748992e-05,
"loss": 1.751,
"step": 978
},
{
"epoch": 0.4364690147124387,
"grad_norm": 0.09699039906263351,
"learning_rate": 7.277512627086744e-05,
"loss": 1.7876,
"step": 979
},
{
"epoch": 0.43691484618814086,
"grad_norm": 0.10053695738315582,
"learning_rate": 7.270312653342063e-05,
"loss": 1.7761,
"step": 980
},
{
"epoch": 0.43736067766384307,
"grad_norm": 0.10371427237987518,
"learning_rate": 7.263106744337782e-05,
"loss": 1.7904,
"step": 981
},
{
"epoch": 0.4378065091395453,
"grad_norm": 0.10344696044921875,
"learning_rate": 7.255894918912248e-05,
"loss": 1.7567,
"step": 982
},
{
"epoch": 0.4382523406152474,
"grad_norm": 0.1011638194322586,
"learning_rate": 7.248677195919276e-05,
"loss": 1.7013,
"step": 983
},
{
"epoch": 0.43869817209094963,
"grad_norm": 0.10408765822649002,
"learning_rate": 7.2414535942281e-05,
"loss": 1.6341,
"step": 984
},
{
"epoch": 0.4391440035666518,
"grad_norm": 0.1022600382566452,
"learning_rate": 7.234224132723323e-05,
"loss": 1.7453,
"step": 985
},
{
"epoch": 0.439589835042354,
"grad_norm": 0.11873215436935425,
"learning_rate": 7.226988830304865e-05,
"loss": 1.7666,
"step": 986
},
{
"epoch": 0.4400356665180562,
"grad_norm": 0.10322696715593338,
"learning_rate": 7.219747705887922e-05,
"loss": 1.7081,
"step": 987
},
{
"epoch": 0.44048149799375835,
"grad_norm": 0.09788621217012405,
"learning_rate": 7.212500778402897e-05,
"loss": 1.6201,
"step": 988
},
{
"epoch": 0.44092732946946056,
"grad_norm": 0.10933342576026917,
"learning_rate": 7.205248066795381e-05,
"loss": 1.6985,
"step": 989
},
{
"epoch": 0.4413731609451627,
"grad_norm": 0.098977230489254,
"learning_rate": 7.197989590026075e-05,
"loss": 1.7787,
"step": 990
},
{
"epoch": 0.4418189924208649,
"grad_norm": 0.10732100903987885,
"learning_rate": 7.190725367070751e-05,
"loss": 1.7978,
"step": 991
},
{
"epoch": 0.44226482389656707,
"grad_norm": 0.10650354623794556,
"learning_rate": 7.183455416920215e-05,
"loss": 1.7234,
"step": 992
},
{
"epoch": 0.4427106553722693,
"grad_norm": 0.0988219678401947,
"learning_rate": 7.17617975858023e-05,
"loss": 1.6638,
"step": 993
},
{
"epoch": 0.4431564868479715,
"grad_norm": 0.10519258677959442,
"learning_rate": 7.168898411071492e-05,
"loss": 1.7927,
"step": 994
},
{
"epoch": 0.44360231832367364,
"grad_norm": 0.1089719757437706,
"learning_rate": 7.16161139342957e-05,
"loss": 1.7929,
"step": 995
},
{
"epoch": 0.44404814979937585,
"grad_norm": 0.10617087036371231,
"learning_rate": 7.154318724704853e-05,
"loss": 1.7283,
"step": 996
},
{
"epoch": 0.444493981275078,
"grad_norm": 0.09845620393753052,
"learning_rate": 7.147020423962501e-05,
"loss": 1.6853,
"step": 997
},
{
"epoch": 0.4449398127507802,
"grad_norm": 0.11220590025186539,
"learning_rate": 7.139716510282407e-05,
"loss": 1.7339,
"step": 998
},
{
"epoch": 0.4453856442264824,
"grad_norm": 0.10506834834814072,
"learning_rate": 7.132407002759125e-05,
"loss": 1.7172,
"step": 999
},
{
"epoch": 0.44583147570218457,
"grad_norm": 0.10992158204317093,
"learning_rate": 7.125091920501847e-05,
"loss": 1.8022,
"step": 1000
},
{
"epoch": 0.4462773071778868,
"grad_norm": 0.10462715476751328,
"learning_rate": 7.11777128263433e-05,
"loss": 1.8029,
"step": 1001
},
{
"epoch": 0.4467231386535889,
"grad_norm": 0.10067321360111237,
"learning_rate": 7.110445108294854e-05,
"loss": 1.7459,
"step": 1002
},
{
"epoch": 0.44716897012929113,
"grad_norm": 0.11223577708005905,
"learning_rate": 7.10311341663618e-05,
"loss": 1.7758,
"step": 1003
},
{
"epoch": 0.44761480160499334,
"grad_norm": 0.10029196739196777,
"learning_rate": 7.095776226825486e-05,
"loss": 1.7417,
"step": 1004
},
{
"epoch": 0.4480606330806955,
"grad_norm": 0.10604588687419891,
"learning_rate": 7.088433558044327e-05,
"loss": 1.7169,
"step": 1005
},
{
"epoch": 0.4485064645563977,
"grad_norm": 0.11488178372383118,
"learning_rate": 7.081085429488583e-05,
"loss": 1.7458,
"step": 1006
},
{
"epoch": 0.44895229603209985,
"grad_norm": 0.11303173005580902,
"learning_rate": 7.073731860368407e-05,
"loss": 1.668,
"step": 1007
},
{
"epoch": 0.44939812750780206,
"grad_norm": 0.1100694090127945,
"learning_rate": 7.06637286990817e-05,
"loss": 1.713,
"step": 1008
},
{
"epoch": 0.4498439589835042,
"grad_norm": 0.10482168942689896,
"learning_rate": 7.059008477346422e-05,
"loss": 1.7409,
"step": 1009
},
{
"epoch": 0.4502897904592064,
"grad_norm": 0.10336344689130783,
"learning_rate": 7.051638701935833e-05,
"loss": 1.749,
"step": 1010
},
{
"epoch": 0.4507356219349086,
"grad_norm": 0.10747478902339935,
"learning_rate": 7.044263562943147e-05,
"loss": 1.7395,
"step": 1011
},
{
"epoch": 0.4511814534106108,
"grad_norm": 0.11005301028490067,
"learning_rate": 7.036883079649128e-05,
"loss": 1.8074,
"step": 1012
},
{
"epoch": 0.451627284886313,
"grad_norm": 0.0953366607427597,
"learning_rate": 7.029497271348513e-05,
"loss": 1.574,
"step": 1013
},
{
"epoch": 0.45207311636201514,
"grad_norm": 0.11766484379768372,
"learning_rate": 7.022106157349959e-05,
"loss": 1.7247,
"step": 1014
},
{
"epoch": 0.45251894783771734,
"grad_norm": 0.10898303985595703,
"learning_rate": 7.014709756975995e-05,
"loss": 1.7074,
"step": 1015
},
{
"epoch": 0.45296477931341955,
"grad_norm": 0.1084798127412796,
"learning_rate": 7.007308089562968e-05,
"loss": 1.6806,
"step": 1016
},
{
"epoch": 0.4534106107891217,
"grad_norm": 0.1093379482626915,
"learning_rate": 6.999901174460997e-05,
"loss": 1.7762,
"step": 1017
},
{
"epoch": 0.4538564422648239,
"grad_norm": 0.11260844767093658,
"learning_rate": 6.992489031033918e-05,
"loss": 1.7003,
"step": 1018
},
{
"epoch": 0.45430227374052606,
"grad_norm": 0.11622101813554764,
"learning_rate": 6.985071678659238e-05,
"loss": 1.7769,
"step": 1019
},
{
"epoch": 0.45474810521622827,
"grad_norm": 0.10713599622249603,
"learning_rate": 6.977649136728078e-05,
"loss": 1.7716,
"step": 1020
},
{
"epoch": 0.4551939366919304,
"grad_norm": 0.1327657252550125,
"learning_rate": 6.970221424645129e-05,
"loss": 1.7822,
"step": 1021
},
{
"epoch": 0.45563976816763263,
"grad_norm": 0.11515428870916367,
"learning_rate": 6.962788561828598e-05,
"loss": 1.7949,
"step": 1022
},
{
"epoch": 0.45608559964333484,
"grad_norm": 0.13047051429748535,
"learning_rate": 6.955350567710155e-05,
"loss": 1.7963,
"step": 1023
},
{
"epoch": 0.456531431119037,
"grad_norm": 0.12113373726606369,
"learning_rate": 6.947907461734891e-05,
"loss": 1.7579,
"step": 1024
},
{
"epoch": 0.4569772625947392,
"grad_norm": 0.10157129913568497,
"learning_rate": 6.940459263361249e-05,
"loss": 1.7507,
"step": 1025
},
{
"epoch": 0.45742309407044135,
"grad_norm": 0.11166101694107056,
"learning_rate": 6.933005992060998e-05,
"loss": 1.7347,
"step": 1026
},
{
"epoch": 0.45786892554614356,
"grad_norm": 0.13206972181797028,
"learning_rate": 6.925547667319161e-05,
"loss": 1.6469,
"step": 1027
},
{
"epoch": 0.45831475702184576,
"grad_norm": 0.11255645006895065,
"learning_rate": 6.918084308633978e-05,
"loss": 1.7787,
"step": 1028
},
{
"epoch": 0.4587605884975479,
"grad_norm": 0.11060569435358047,
"learning_rate": 6.910615935516842e-05,
"loss": 1.8547,
"step": 1029
},
{
"epoch": 0.4592064199732501,
"grad_norm": 0.11540091037750244,
"learning_rate": 6.903142567492262e-05,
"loss": 1.7386,
"step": 1030
},
{
"epoch": 0.4596522514489523,
"grad_norm": 0.11963297426700592,
"learning_rate": 6.895664224097799e-05,
"loss": 1.6619,
"step": 1031
},
{
"epoch": 0.4600980829246545,
"grad_norm": 0.11087245494127274,
"learning_rate": 6.888180924884028e-05,
"loss": 1.7288,
"step": 1032
},
{
"epoch": 0.4605439144003567,
"grad_norm": 0.10754108428955078,
"learning_rate": 6.880692689414473e-05,
"loss": 1.7049,
"step": 1033
},
{
"epoch": 0.46098974587605884,
"grad_norm": 0.10990439355373383,
"learning_rate": 6.87319953726557e-05,
"loss": 1.765,
"step": 1034
},
{
"epoch": 0.46143557735176105,
"grad_norm": 0.11399084329605103,
"learning_rate": 6.865701488026601e-05,
"loss": 1.7461,
"step": 1035
},
{
"epoch": 0.4618814088274632,
"grad_norm": 0.12000394612550735,
"learning_rate": 6.858198561299656e-05,
"loss": 1.7357,
"step": 1036
},
{
"epoch": 0.4623272403031654,
"grad_norm": 0.102603979408741,
"learning_rate": 6.850690776699573e-05,
"loss": 1.6752,
"step": 1037
},
{
"epoch": 0.46277307177886756,
"grad_norm": 0.10022717714309692,
"learning_rate": 6.843178153853892e-05,
"loss": 1.707,
"step": 1038
},
{
"epoch": 0.46321890325456977,
"grad_norm": 0.11002365499734879,
"learning_rate": 6.8356607124028e-05,
"loss": 1.7159,
"step": 1039
},
{
"epoch": 0.463664734730272,
"grad_norm": 0.11824753880500793,
"learning_rate": 6.828138471999084e-05,
"loss": 1.7939,
"step": 1040
},
{
"epoch": 0.46411056620597413,
"grad_norm": 0.10815898329019547,
"learning_rate": 6.820611452308075e-05,
"loss": 1.6987,
"step": 1041
},
{
"epoch": 0.46455639768167634,
"grad_norm": 0.10861074924468994,
"learning_rate": 6.813079673007596e-05,
"loss": 1.7421,
"step": 1042
},
{
"epoch": 0.4650022291573785,
"grad_norm": 0.11027023196220398,
"learning_rate": 6.805543153787916e-05,
"loss": 1.7138,
"step": 1043
},
{
"epoch": 0.4654480606330807,
"grad_norm": 0.10646670311689377,
"learning_rate": 6.798001914351695e-05,
"loss": 1.7639,
"step": 1044
},
{
"epoch": 0.4658938921087829,
"grad_norm": 0.10153870284557343,
"learning_rate": 6.790455974413934e-05,
"loss": 1.7928,
"step": 1045
},
{
"epoch": 0.46633972358448506,
"grad_norm": 0.10399957746267319,
"learning_rate": 6.782905353701921e-05,
"loss": 1.7043,
"step": 1046
},
{
"epoch": 0.46678555506018726,
"grad_norm": 0.11583542078733444,
"learning_rate": 6.775350071955183e-05,
"loss": 1.7508,
"step": 1047
},
{
"epoch": 0.4672313865358894,
"grad_norm": 0.1150580644607544,
"learning_rate": 6.767790148925425e-05,
"loss": 1.7776,
"step": 1048
},
{
"epoch": 0.4676772180115916,
"grad_norm": 0.10754206776618958,
"learning_rate": 6.760225604376496e-05,
"loss": 1.7663,
"step": 1049
},
{
"epoch": 0.46812304948729383,
"grad_norm": 0.11345209926366806,
"learning_rate": 6.752656458084322e-05,
"loss": 1.7515,
"step": 1050
},
{
"epoch": 0.468568880962996,
"grad_norm": 0.11287328600883484,
"learning_rate": 6.745082729836858e-05,
"loss": 1.7855,
"step": 1051
},
{
"epoch": 0.4690147124386982,
"grad_norm": 0.10804345458745956,
"learning_rate": 6.737504439434039e-05,
"loss": 1.7305,
"step": 1052
},
{
"epoch": 0.46946054391440034,
"grad_norm": 0.1034819558262825,
"learning_rate": 6.72992160668773e-05,
"loss": 1.8025,
"step": 1053
},
{
"epoch": 0.46990637539010255,
"grad_norm": 0.10323302447795868,
"learning_rate": 6.722334251421665e-05,
"loss": 1.5798,
"step": 1054
},
{
"epoch": 0.4703522068658047,
"grad_norm": 0.10375598073005676,
"learning_rate": 6.714742393471405e-05,
"loss": 1.6239,
"step": 1055
},
{
"epoch": 0.4707980383415069,
"grad_norm": 0.11727172881364822,
"learning_rate": 6.707146052684281e-05,
"loss": 1.745,
"step": 1056
},
{
"epoch": 0.4712438698172091,
"grad_norm": 0.10087629407644272,
"learning_rate": 6.699545248919344e-05,
"loss": 1.6909,
"step": 1057
},
{
"epoch": 0.47168970129291127,
"grad_norm": 0.11136236041784286,
"learning_rate": 6.691940002047314e-05,
"loss": 1.7767,
"step": 1058
},
{
"epoch": 0.4721355327686135,
"grad_norm": 0.10630472004413605,
"learning_rate": 6.684330331950522e-05,
"loss": 1.7596,
"step": 1059
},
{
"epoch": 0.4725813642443156,
"grad_norm": 0.11284103989601135,
"learning_rate": 6.676716258522869e-05,
"loss": 1.7408,
"step": 1060
},
{
"epoch": 0.47302719572001783,
"grad_norm": 0.10337649285793304,
"learning_rate": 6.669097801669763e-05,
"loss": 1.7321,
"step": 1061
},
{
"epoch": 0.47347302719572004,
"grad_norm": 0.1130218505859375,
"learning_rate": 6.661474981308071e-05,
"loss": 1.7613,
"step": 1062
},
{
"epoch": 0.4739188586714222,
"grad_norm": 0.11629295349121094,
"learning_rate": 6.653847817366072e-05,
"loss": 1.7464,
"step": 1063
},
{
"epoch": 0.4743646901471244,
"grad_norm": 0.10781564563512802,
"learning_rate": 6.646216329783396e-05,
"loss": 1.6771,
"step": 1064
},
{
"epoch": 0.47481052162282655,
"grad_norm": 0.10097536444664001,
"learning_rate": 6.638580538510978e-05,
"loss": 1.8097,
"step": 1065
},
{
"epoch": 0.47525635309852876,
"grad_norm": 0.10500414669513702,
"learning_rate": 6.630940463511004e-05,
"loss": 1.7065,
"step": 1066
},
{
"epoch": 0.4757021845742309,
"grad_norm": 0.10623206198215485,
"learning_rate": 6.623296124756857e-05,
"loss": 1.6457,
"step": 1067
},
{
"epoch": 0.4761480160499331,
"grad_norm": 0.10557615756988525,
"learning_rate": 6.615647542233074e-05,
"loss": 1.7904,
"step": 1068
},
{
"epoch": 0.47659384752563533,
"grad_norm": 0.10423476248979568,
"learning_rate": 6.607994735935278e-05,
"loss": 1.7551,
"step": 1069
},
{
"epoch": 0.4770396790013375,
"grad_norm": 0.10633677989244461,
"learning_rate": 6.600337725870135e-05,
"loss": 1.7012,
"step": 1070
},
{
"epoch": 0.4774855104770397,
"grad_norm": 0.09895249456167221,
"learning_rate": 6.592676532055306e-05,
"loss": 1.7048,
"step": 1071
},
{
"epoch": 0.47793134195274184,
"grad_norm": 0.10984545946121216,
"learning_rate": 6.585011174519387e-05,
"loss": 1.7684,
"step": 1072
},
{
"epoch": 0.47837717342844405,
"grad_norm": 0.10548101365566254,
"learning_rate": 6.577341673301856e-05,
"loss": 1.6768,
"step": 1073
},
{
"epoch": 0.47882300490414625,
"grad_norm": 0.10471886396408081,
"learning_rate": 6.569668048453029e-05,
"loss": 1.6654,
"step": 1074
},
{
"epoch": 0.4792688363798484,
"grad_norm": 0.09934554249048233,
"learning_rate": 6.561990320034e-05,
"loss": 1.7461,
"step": 1075
},
{
"epoch": 0.4797146678555506,
"grad_norm": 0.10605472326278687,
"learning_rate": 6.554308508116589e-05,
"loss": 1.7059,
"step": 1076
},
{
"epoch": 0.48016049933125277,
"grad_norm": 0.10622227936983109,
"learning_rate": 6.546622632783294e-05,
"loss": 1.7792,
"step": 1077
},
{
"epoch": 0.480606330806955,
"grad_norm": 0.10901618748903275,
"learning_rate": 6.538932714127237e-05,
"loss": 1.7157,
"step": 1078
},
{
"epoch": 0.4810521622826572,
"grad_norm": 0.09955921024084091,
"learning_rate": 6.531238772252108e-05,
"loss": 1.6929,
"step": 1079
},
{
"epoch": 0.48149799375835933,
"grad_norm": 0.10353855788707733,
"learning_rate": 6.523540827272114e-05,
"loss": 1.7628,
"step": 1080
},
{
"epoch": 0.48194382523406154,
"grad_norm": 0.11193034052848816,
"learning_rate": 6.515838899311932e-05,
"loss": 1.6402,
"step": 1081
},
{
"epoch": 0.4823896567097637,
"grad_norm": 0.10143030434846878,
"learning_rate": 6.508133008506647e-05,
"loss": 1.796,
"step": 1082
},
{
"epoch": 0.4828354881854659,
"grad_norm": 0.10662831366062164,
"learning_rate": 6.500423175001705e-05,
"loss": 1.6963,
"step": 1083
},
{
"epoch": 0.48328131966116805,
"grad_norm": 0.11801926791667938,
"learning_rate": 6.49270941895286e-05,
"loss": 1.7451,
"step": 1084
},
{
"epoch": 0.48372715113687026,
"grad_norm": 0.10104748606681824,
"learning_rate": 6.484991760526121e-05,
"loss": 1.6657,
"step": 1085
},
{
"epoch": 0.48417298261257247,
"grad_norm": 0.10664571076631546,
"learning_rate": 6.4772702198977e-05,
"loss": 1.7085,
"step": 1086
},
{
"epoch": 0.4846188140882746,
"grad_norm": 0.12337417155504227,
"learning_rate": 6.469544817253954e-05,
"loss": 1.7443,
"step": 1087
},
{
"epoch": 0.4850646455639768,
"grad_norm": 0.09773636609315872,
"learning_rate": 6.461815572791342e-05,
"loss": 1.7102,
"step": 1088
},
{
"epoch": 0.485510477039679,
"grad_norm": 0.11911724507808685,
"learning_rate": 6.454082506716361e-05,
"loss": 1.8079,
"step": 1089
},
{
"epoch": 0.4859563085153812,
"grad_norm": 0.09927862137556076,
"learning_rate": 6.446345639245506e-05,
"loss": 1.6132,
"step": 1090
},
{
"epoch": 0.4864021399910834,
"grad_norm": 0.09860575199127197,
"learning_rate": 6.438604990605203e-05,
"loss": 1.7327,
"step": 1091
},
{
"epoch": 0.48684797146678555,
"grad_norm": 0.10163085907697678,
"learning_rate": 6.430860581031766e-05,
"loss": 1.7649,
"step": 1092
},
{
"epoch": 0.48729380294248775,
"grad_norm": 0.10834555327892303,
"learning_rate": 6.423112430771339e-05,
"loss": 1.7798,
"step": 1093
},
{
"epoch": 0.4877396344181899,
"grad_norm": 0.09685652703046799,
"learning_rate": 6.415360560079848e-05,
"loss": 1.5396,
"step": 1094
},
{
"epoch": 0.4881854658938921,
"grad_norm": 0.09764835983514786,
"learning_rate": 6.407604989222948e-05,
"loss": 1.667,
"step": 1095
},
{
"epoch": 0.4886312973695943,
"grad_norm": 0.10408106446266174,
"learning_rate": 6.399845738475963e-05,
"loss": 1.7502,
"step": 1096
},
{
"epoch": 0.48907712884529647,
"grad_norm": 0.10968370735645294,
"learning_rate": 6.392082828123833e-05,
"loss": 1.8114,
"step": 1097
},
{
"epoch": 0.4895229603209987,
"grad_norm": 0.10337293148040771,
"learning_rate": 6.384316278461076e-05,
"loss": 1.7727,
"step": 1098
},
{
"epoch": 0.48996879179670083,
"grad_norm": 0.11161931604146957,
"learning_rate": 6.376546109791714e-05,
"loss": 1.8031,
"step": 1099
},
{
"epoch": 0.49041462327240304,
"grad_norm": 0.09923950582742691,
"learning_rate": 6.368772342429238e-05,
"loss": 1.6651,
"step": 1100
},
{
"epoch": 0.4908604547481052,
"grad_norm": 0.10208352655172348,
"learning_rate": 6.360994996696544e-05,
"loss": 1.6447,
"step": 1101
},
{
"epoch": 0.4913062862238074,
"grad_norm": 0.11259648203849792,
"learning_rate": 6.353214092925878e-05,
"loss": 1.6883,
"step": 1102
},
{
"epoch": 0.4917521176995096,
"grad_norm": 0.10408410429954529,
"learning_rate": 6.3454296514588e-05,
"loss": 1.6868,
"step": 1103
},
{
"epoch": 0.49219794917521176,
"grad_norm": 0.10580252856016159,
"learning_rate": 6.337641692646106e-05,
"loss": 1.7466,
"step": 1104
},
{
"epoch": 0.49264378065091396,
"grad_norm": 0.10221690684556961,
"learning_rate": 6.32985023684779e-05,
"loss": 1.6768,
"step": 1105
},
{
"epoch": 0.4930896121266161,
"grad_norm": 0.10130845010280609,
"learning_rate": 6.322055304432997e-05,
"loss": 1.7068,
"step": 1106
},
{
"epoch": 0.4935354436023183,
"grad_norm": 0.1036425456404686,
"learning_rate": 6.314256915779948e-05,
"loss": 1.6869,
"step": 1107
},
{
"epoch": 0.49398127507802053,
"grad_norm": 0.1028156578540802,
"learning_rate": 6.306455091275912e-05,
"loss": 1.7106,
"step": 1108
},
{
"epoch": 0.4944271065537227,
"grad_norm": 0.10539206117391586,
"learning_rate": 6.29864985131713e-05,
"loss": 1.7558,
"step": 1109
},
{
"epoch": 0.4948729380294249,
"grad_norm": 0.10090222954750061,
"learning_rate": 6.290841216308777e-05,
"loss": 1.6676,
"step": 1110
},
{
"epoch": 0.49531876950512704,
"grad_norm": 0.10262907296419144,
"learning_rate": 6.283029206664903e-05,
"loss": 1.7363,
"step": 1111
},
{
"epoch": 0.49576460098082925,
"grad_norm": 0.11014319211244583,
"learning_rate": 6.275213842808383e-05,
"loss": 1.7144,
"step": 1112
},
{
"epoch": 0.49621043245653146,
"grad_norm": 0.10196888446807861,
"learning_rate": 6.267395145170854e-05,
"loss": 1.752,
"step": 1113
},
{
"epoch": 0.4966562639322336,
"grad_norm": 0.11600615084171295,
"learning_rate": 6.259573134192675e-05,
"loss": 1.7079,
"step": 1114
},
{
"epoch": 0.4971020954079358,
"grad_norm": 0.09944573789834976,
"learning_rate": 6.251747830322865e-05,
"loss": 1.7305,
"step": 1115
},
{
"epoch": 0.49754792688363797,
"grad_norm": 0.10492048412561417,
"learning_rate": 6.243919254019049e-05,
"loss": 1.7558,
"step": 1116
},
{
"epoch": 0.4979937583593402,
"grad_norm": 0.09876780211925507,
"learning_rate": 6.23608742574741e-05,
"loss": 1.7066,
"step": 1117
},
{
"epoch": 0.49843958983504233,
"grad_norm": 0.10529439896345139,
"learning_rate": 6.228252365982634e-05,
"loss": 1.782,
"step": 1118
},
{
"epoch": 0.49888542131074454,
"grad_norm": 0.10732155293226242,
"learning_rate": 6.220414095207853e-05,
"loss": 1.7018,
"step": 1119
},
{
"epoch": 0.49933125278644674,
"grad_norm": 0.1048203706741333,
"learning_rate": 6.21257263391459e-05,
"loss": 1.6891,
"step": 1120
},
{
"epoch": 0.4997770842621489,
"grad_norm": 0.10606954246759415,
"learning_rate": 6.204728002602713e-05,
"loss": 1.7749,
"step": 1121
},
{
"epoch": 0.500222915737851,
"grad_norm": 0.10162214934825897,
"learning_rate": 6.19688022178038e-05,
"loss": 1.7096,
"step": 1122
},
{
"epoch": 0.5006687472135533,
"grad_norm": 0.11303394287824631,
"learning_rate": 6.189029311963977e-05,
"loss": 1.7303,
"step": 1123
},
{
"epoch": 0.5011145786892555,
"grad_norm": 0.10265006870031357,
"learning_rate": 6.181175293678075e-05,
"loss": 1.6749,
"step": 1124
},
{
"epoch": 0.5015604101649577,
"grad_norm": 0.10273852944374084,
"learning_rate": 6.173318187455367e-05,
"loss": 1.7008,
"step": 1125
},
{
"epoch": 0.5020062416406599,
"grad_norm": 0.11862947791814804,
"learning_rate": 6.16545801383662e-05,
"loss": 1.636,
"step": 1126
},
{
"epoch": 0.502452073116362,
"grad_norm": 0.10472943633794785,
"learning_rate": 6.157594793370623e-05,
"loss": 1.7104,
"step": 1127
},
{
"epoch": 0.5028979045920642,
"grad_norm": 0.11847833544015884,
"learning_rate": 6.149728546614127e-05,
"loss": 1.7904,
"step": 1128
},
{
"epoch": 0.5033437360677664,
"grad_norm": 0.11799414455890656,
"learning_rate": 6.141859294131797e-05,
"loss": 1.5836,
"step": 1129
},
{
"epoch": 0.5037895675434686,
"grad_norm": 0.10194052755832672,
"learning_rate": 6.133987056496153e-05,
"loss": 1.7451,
"step": 1130
},
{
"epoch": 0.5042353990191708,
"grad_norm": 0.10454517602920532,
"learning_rate": 6.126111854287523e-05,
"loss": 1.6873,
"step": 1131
},
{
"epoch": 0.5046812304948729,
"grad_norm": 0.13372153043746948,
"learning_rate": 6.118233708093982e-05,
"loss": 1.6855,
"step": 1132
},
{
"epoch": 0.5051270619705751,
"grad_norm": 0.113282710313797,
"learning_rate": 6.1103526385113e-05,
"loss": 1.7465,
"step": 1133
},
{
"epoch": 0.5055728934462773,
"grad_norm": 0.10861644893884659,
"learning_rate": 6.1024686661428974e-05,
"loss": 1.7032,
"step": 1134
},
{
"epoch": 0.5060187249219795,
"grad_norm": 0.14159952104091644,
"learning_rate": 6.094581811599773e-05,
"loss": 1.7682,
"step": 1135
},
{
"epoch": 0.5064645563976817,
"grad_norm": 0.10061583667993546,
"learning_rate": 6.086692095500468e-05,
"loss": 1.6376,
"step": 1136
},
{
"epoch": 0.5069103878733838,
"grad_norm": 0.12080123275518417,
"learning_rate": 6.078799538471002e-05,
"loss": 1.6937,
"step": 1137
},
{
"epoch": 0.507356219349086,
"grad_norm": 0.12634600698947906,
"learning_rate": 6.070904161144819e-05,
"loss": 1.7529,
"step": 1138
},
{
"epoch": 0.5078020508247882,
"grad_norm": 0.1051335409283638,
"learning_rate": 6.063005984162743e-05,
"loss": 1.7399,
"step": 1139
},
{
"epoch": 0.5082478823004905,
"grad_norm": 0.10309924930334091,
"learning_rate": 6.0551050281729095e-05,
"loss": 1.7029,
"step": 1140
},
{
"epoch": 0.5086937137761925,
"grad_norm": 0.12764118611812592,
"learning_rate": 6.0472013138307235e-05,
"loss": 1.7604,
"step": 1141
},
{
"epoch": 0.5091395452518948,
"grad_norm": 0.10762520134449005,
"learning_rate": 6.039294861798799e-05,
"loss": 1.7471,
"step": 1142
},
{
"epoch": 0.509585376727597,
"grad_norm": 0.1139635369181633,
"learning_rate": 6.031385692746909e-05,
"loss": 1.8011,
"step": 1143
},
{
"epoch": 0.5100312082032992,
"grad_norm": 0.10205898433923721,
"learning_rate": 6.02347382735193e-05,
"loss": 1.6282,
"step": 1144
},
{
"epoch": 0.5104770396790014,
"grad_norm": 0.10260274261236191,
"learning_rate": 6.0155592862977836e-05,
"loss": 1.7622,
"step": 1145
},
{
"epoch": 0.5109228711547035,
"grad_norm": 0.10429879277944565,
"learning_rate": 6.0076420902753927e-05,
"loss": 1.7492,
"step": 1146
},
{
"epoch": 0.5113687026304057,
"grad_norm": 0.1011742651462555,
"learning_rate": 5.999722259982614e-05,
"loss": 1.7412,
"step": 1147
},
{
"epoch": 0.5118145341061079,
"grad_norm": 0.10449127852916718,
"learning_rate": 5.9917998161241963e-05,
"loss": 1.6657,
"step": 1148
},
{
"epoch": 0.5122603655818101,
"grad_norm": 0.10454753786325455,
"learning_rate": 5.9838747794117175e-05,
"loss": 1.686,
"step": 1149
},
{
"epoch": 0.5127061970575123,
"grad_norm": 0.10285554081201553,
"learning_rate": 5.9759471705635376e-05,
"loss": 1.6631,
"step": 1150
},
{
"epoch": 0.5131520285332144,
"grad_norm": 0.10133292526006699,
"learning_rate": 5.9680170103047375e-05,
"loss": 1.714,
"step": 1151
},
{
"epoch": 0.5135978600089166,
"grad_norm": 0.10651468485593796,
"learning_rate": 5.96008431936707e-05,
"loss": 1.7947,
"step": 1152
},
{
"epoch": 0.5140436914846188,
"grad_norm": 0.1021052896976471,
"learning_rate": 5.9521491184889035e-05,
"loss": 1.6979,
"step": 1153
},
{
"epoch": 0.514489522960321,
"grad_norm": 0.10320725291967392,
"learning_rate": 5.944211428415167e-05,
"loss": 1.7853,
"step": 1154
},
{
"epoch": 0.5149353544360232,
"grad_norm": 0.10193000733852386,
"learning_rate": 5.9362712698973e-05,
"loss": 1.7532,
"step": 1155
},
{
"epoch": 0.5153811859117253,
"grad_norm": 0.10487652570009232,
"learning_rate": 5.9283286636931904e-05,
"loss": 1.7218,
"step": 1156
},
{
"epoch": 0.5158270173874275,
"grad_norm": 0.10608694702386856,
"learning_rate": 5.920383630567131e-05,
"loss": 1.7388,
"step": 1157
},
{
"epoch": 0.5162728488631297,
"grad_norm": 0.10088912397623062,
"learning_rate": 5.912436191289755e-05,
"loss": 1.7005,
"step": 1158
},
{
"epoch": 0.516718680338832,
"grad_norm": 0.10738028585910797,
"learning_rate": 5.904486366637988e-05,
"loss": 1.683,
"step": 1159
},
{
"epoch": 0.5171645118145342,
"grad_norm": 0.10869428515434265,
"learning_rate": 5.896534177394989e-05,
"loss": 1.7495,
"step": 1160
},
{
"epoch": 0.5176103432902363,
"grad_norm": 0.1092354878783226,
"learning_rate": 5.888579644350102e-05,
"loss": 1.7392,
"step": 1161
},
{
"epoch": 0.5180561747659385,
"grad_norm": 0.11755093932151794,
"learning_rate": 5.880622788298795e-05,
"loss": 1.7836,
"step": 1162
},
{
"epoch": 0.5185020062416407,
"grad_norm": 0.1067739948630333,
"learning_rate": 5.8726636300426154e-05,
"loss": 1.715,
"step": 1163
},
{
"epoch": 0.5189478377173429,
"grad_norm": 0.10619974136352539,
"learning_rate": 5.8647021903891206e-05,
"loss": 1.6579,
"step": 1164
},
{
"epoch": 0.5193936691930451,
"grad_norm": 0.10408498346805573,
"learning_rate": 5.856738490151838e-05,
"loss": 1.7113,
"step": 1165
},
{
"epoch": 0.5198395006687472,
"grad_norm": 0.10899797827005386,
"learning_rate": 5.848772550150203e-05,
"loss": 1.7024,
"step": 1166
},
{
"epoch": 0.5202853321444494,
"grad_norm": 0.1036175936460495,
"learning_rate": 5.840804391209507e-05,
"loss": 1.7452,
"step": 1167
},
{
"epoch": 0.5207311636201516,
"grad_norm": 0.11126765608787537,
"learning_rate": 5.8328340341608426e-05,
"loss": 1.6616,
"step": 1168
},
{
"epoch": 0.5211769950958538,
"grad_norm": 0.10354796051979065,
"learning_rate": 5.824861499841047e-05,
"loss": 1.6956,
"step": 1169
},
{
"epoch": 0.5216228265715559,
"grad_norm": 0.10516001284122467,
"learning_rate": 5.816886809092651e-05,
"loss": 1.667,
"step": 1170
},
{
"epoch": 0.5220686580472581,
"grad_norm": 0.10458080470561981,
"learning_rate": 5.808909982763825e-05,
"loss": 1.7103,
"step": 1171
},
{
"epoch": 0.5225144895229603,
"grad_norm": 0.10640576481819153,
"learning_rate": 5.8009310417083165e-05,
"loss": 1.7388,
"step": 1172
},
{
"epoch": 0.5229603209986625,
"grad_norm": 0.10430578142404556,
"learning_rate": 5.792950006785407e-05,
"loss": 1.7327,
"step": 1173
},
{
"epoch": 0.5234061524743647,
"grad_norm": 0.10134794563055038,
"learning_rate": 5.7849668988598514e-05,
"loss": 1.7289,
"step": 1174
},
{
"epoch": 0.5238519839500668,
"grad_norm": 0.1047339215874672,
"learning_rate": 5.77698173880182e-05,
"loss": 1.7616,
"step": 1175
},
{
"epoch": 0.524297815425769,
"grad_norm": 0.1061745285987854,
"learning_rate": 5.7689945474868525e-05,
"loss": 1.6447,
"step": 1176
},
{
"epoch": 0.5247436469014712,
"grad_norm": 0.1092158779501915,
"learning_rate": 5.761005345795797e-05,
"loss": 1.7735,
"step": 1177
},
{
"epoch": 0.5251894783771734,
"grad_norm": 0.1155422180891037,
"learning_rate": 5.7530141546147565e-05,
"loss": 1.6401,
"step": 1178
},
{
"epoch": 0.5256353098528757,
"grad_norm": 0.10517088323831558,
"learning_rate": 5.745020994835037e-05,
"loss": 1.7186,
"step": 1179
},
{
"epoch": 0.5260811413285778,
"grad_norm": 0.10002213716506958,
"learning_rate": 5.73702588735309e-05,
"loss": 1.6587,
"step": 1180
},
{
"epoch": 0.52652697280428,
"grad_norm": 0.10640916973352432,
"learning_rate": 5.729028853070459e-05,
"loss": 1.6614,
"step": 1181
},
{
"epoch": 0.5269728042799822,
"grad_norm": 0.12083696573972702,
"learning_rate": 5.721029912893724e-05,
"loss": 1.7733,
"step": 1182
},
{
"epoch": 0.5274186357556844,
"grad_norm": 0.09709788858890533,
"learning_rate": 5.713029087734447e-05,
"loss": 1.6124,
"step": 1183
},
{
"epoch": 0.5278644672313866,
"grad_norm": 0.10455354303121567,
"learning_rate": 5.7050263985091224e-05,
"loss": 1.7302,
"step": 1184
},
{
"epoch": 0.5283102987070887,
"grad_norm": 0.11093839257955551,
"learning_rate": 5.697021866139113e-05,
"loss": 1.7355,
"step": 1185
},
{
"epoch": 0.5287561301827909,
"grad_norm": 0.10643623769283295,
"learning_rate": 5.6890155115506e-05,
"loss": 1.7678,
"step": 1186
},
{
"epoch": 0.5292019616584931,
"grad_norm": 0.10465513914823532,
"learning_rate": 5.6810073556745316e-05,
"loss": 1.7651,
"step": 1187
},
{
"epoch": 0.5296477931341953,
"grad_norm": 0.11257901787757874,
"learning_rate": 5.6729974194465615e-05,
"loss": 1.8115,
"step": 1188
},
{
"epoch": 0.5300936246098975,
"grad_norm": 0.1023031547665596,
"learning_rate": 5.664985723807004e-05,
"loss": 1.8034,
"step": 1189
},
{
"epoch": 0.5305394560855996,
"grad_norm": 0.11121316999197006,
"learning_rate": 5.6569722897007635e-05,
"loss": 1.7847,
"step": 1190
},
{
"epoch": 0.5309852875613018,
"grad_norm": 0.10349234193563461,
"learning_rate": 5.6489571380773e-05,
"loss": 1.7454,
"step": 1191
},
{
"epoch": 0.531431119037004,
"grad_norm": 0.10839033871889114,
"learning_rate": 5.640940289890554e-05,
"loss": 1.7684,
"step": 1192
},
{
"epoch": 0.5318769505127062,
"grad_norm": 0.107262521982193,
"learning_rate": 5.632921766098906e-05,
"loss": 1.6535,
"step": 1193
},
{
"epoch": 0.5323227819884084,
"grad_norm": 0.11383821070194244,
"learning_rate": 5.624901587665118e-05,
"loss": 1.757,
"step": 1194
},
{
"epoch": 0.5327686134641105,
"grad_norm": 0.1030779555439949,
"learning_rate": 5.616879775556276e-05,
"loss": 1.7113,
"step": 1195
},
{
"epoch": 0.5332144449398127,
"grad_norm": 0.10793551057577133,
"learning_rate": 5.608856350743735e-05,
"loss": 1.7453,
"step": 1196
},
{
"epoch": 0.533660276415515,
"grad_norm": 0.12622252106666565,
"learning_rate": 5.6008313342030704e-05,
"loss": 1.7304,
"step": 1197
},
{
"epoch": 0.5341061078912172,
"grad_norm": 0.1026214212179184,
"learning_rate": 5.592804746914017e-05,
"loss": 1.8095,
"step": 1198
},
{
"epoch": 0.5345519393669194,
"grad_norm": 0.10837383568286896,
"learning_rate": 5.584776609860414e-05,
"loss": 1.6469,
"step": 1199
},
{
"epoch": 0.5349977708426215,
"grad_norm": 0.11983513832092285,
"learning_rate": 5.576746944030152e-05,
"loss": 1.7298,
"step": 1200
}
],
"logging_steps": 1,
"max_steps": 2243,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 300,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.051081472475136e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}