Files
Llama-3.1-8B-Instruct_SDFT_…/trainer_state.json
ModelHub XC 521b6fffe2 初始化项目,由ModelHub XC社区提供模型
Model: Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.09
Source: Original Platform
2026-04-23 18:15:00 +08:00

9263 lines
205 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1317,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002277904328018223,
"grad_norm": 3.7515621185302734,
"learning_rate": 0.0,
"loss": 0.1547,
"step": 1
},
{
"epoch": 0.004555808656036446,
"grad_norm": 3.7196226119995117,
"learning_rate": 3.787878787878788e-08,
"loss": 0.1577,
"step": 2
},
{
"epoch": 0.00683371298405467,
"grad_norm": 3.765834093093872,
"learning_rate": 7.575757575757576e-08,
"loss": 0.1601,
"step": 3
},
{
"epoch": 0.009111617312072893,
"grad_norm": 3.8851237297058105,
"learning_rate": 1.1363636363636364e-07,
"loss": 0.1575,
"step": 4
},
{
"epoch": 0.011389521640091117,
"grad_norm": 3.452960252761841,
"learning_rate": 1.5151515151515152e-07,
"loss": 0.1564,
"step": 5
},
{
"epoch": 0.01366742596810934,
"grad_norm": 3.7792060375213623,
"learning_rate": 1.893939393939394e-07,
"loss": 0.1606,
"step": 6
},
{
"epoch": 0.015945330296127564,
"grad_norm": 3.6438887119293213,
"learning_rate": 2.2727272727272729e-07,
"loss": 0.1575,
"step": 7
},
{
"epoch": 0.018223234624145785,
"grad_norm": 3.7777984142303467,
"learning_rate": 2.651515151515152e-07,
"loss": 0.1546,
"step": 8
},
{
"epoch": 0.02050113895216401,
"grad_norm": 3.470759868621826,
"learning_rate": 3.0303030303030305e-07,
"loss": 0.1534,
"step": 9
},
{
"epoch": 0.022779043280182234,
"grad_norm": 3.5244765281677246,
"learning_rate": 3.409090909090909e-07,
"loss": 0.1567,
"step": 10
},
{
"epoch": 0.025056947608200455,
"grad_norm": 3.4608511924743652,
"learning_rate": 3.787878787878788e-07,
"loss": 0.1528,
"step": 11
},
{
"epoch": 0.02733485193621868,
"grad_norm": 3.4218990802764893,
"learning_rate": 4.1666666666666667e-07,
"loss": 0.1503,
"step": 12
},
{
"epoch": 0.029612756264236904,
"grad_norm": 2.852553367614746,
"learning_rate": 4.5454545454545457e-07,
"loss": 0.1461,
"step": 13
},
{
"epoch": 0.03189066059225513,
"grad_norm": 2.992276191711426,
"learning_rate": 4.924242424242425e-07,
"loss": 0.1475,
"step": 14
},
{
"epoch": 0.03416856492027335,
"grad_norm": 2.432781457901001,
"learning_rate": 5.303030303030304e-07,
"loss": 0.1398,
"step": 15
},
{
"epoch": 0.03644646924829157,
"grad_norm": 2.0288331508636475,
"learning_rate": 5.681818181818182e-07,
"loss": 0.1386,
"step": 16
},
{
"epoch": 0.0387243735763098,
"grad_norm": 1.6633920669555664,
"learning_rate": 6.060606060606061e-07,
"loss": 0.1294,
"step": 17
},
{
"epoch": 0.04100227790432802,
"grad_norm": 1.4245625734329224,
"learning_rate": 6.43939393939394e-07,
"loss": 0.1309,
"step": 18
},
{
"epoch": 0.04328018223234624,
"grad_norm": 1.3093671798706055,
"learning_rate": 6.818181818181818e-07,
"loss": 0.1271,
"step": 19
},
{
"epoch": 0.04555808656036447,
"grad_norm": 1.2491767406463623,
"learning_rate": 7.196969696969698e-07,
"loss": 0.1257,
"step": 20
},
{
"epoch": 0.04783599088838269,
"grad_norm": 1.123982548713684,
"learning_rate": 7.575757575757576e-07,
"loss": 0.1213,
"step": 21
},
{
"epoch": 0.05011389521640091,
"grad_norm": 1.0984852313995361,
"learning_rate": 7.954545454545455e-07,
"loss": 0.1186,
"step": 22
},
{
"epoch": 0.05239179954441914,
"grad_norm": 1.37436842918396,
"learning_rate": 8.333333333333333e-07,
"loss": 0.1116,
"step": 23
},
{
"epoch": 0.05466970387243736,
"grad_norm": 1.382936954498291,
"learning_rate": 8.712121212121213e-07,
"loss": 0.109,
"step": 24
},
{
"epoch": 0.05694760820045558,
"grad_norm": 1.3406814336776733,
"learning_rate": 9.090909090909091e-07,
"loss": 0.1085,
"step": 25
},
{
"epoch": 0.05922551252847381,
"grad_norm": 1.279089331626892,
"learning_rate": 9.469696969696971e-07,
"loss": 0.1063,
"step": 26
},
{
"epoch": 0.06150341685649203,
"grad_norm": 0.9895230531692505,
"learning_rate": 9.84848484848485e-07,
"loss": 0.1056,
"step": 27
},
{
"epoch": 0.06378132118451026,
"grad_norm": 0.8956998586654663,
"learning_rate": 1.0227272727272729e-06,
"loss": 0.1091,
"step": 28
},
{
"epoch": 0.06605922551252848,
"grad_norm": 0.815238893032074,
"learning_rate": 1.0606060606060608e-06,
"loss": 0.105,
"step": 29
},
{
"epoch": 0.0683371298405467,
"grad_norm": 0.9920597076416016,
"learning_rate": 1.0984848484848485e-06,
"loss": 0.1084,
"step": 30
},
{
"epoch": 0.07061503416856492,
"grad_norm": 1.0040704011917114,
"learning_rate": 1.1363636363636364e-06,
"loss": 0.1062,
"step": 31
},
{
"epoch": 0.07289293849658314,
"grad_norm": 1.0493673086166382,
"learning_rate": 1.1742424242424245e-06,
"loss": 0.1086,
"step": 32
},
{
"epoch": 0.07517084282460136,
"grad_norm": 1.0451900959014893,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.1028,
"step": 33
},
{
"epoch": 0.0774487471526196,
"grad_norm": 0.7993922829627991,
"learning_rate": 1.25e-06,
"loss": 0.1013,
"step": 34
},
{
"epoch": 0.07972665148063782,
"grad_norm": 0.7440354824066162,
"learning_rate": 1.287878787878788e-06,
"loss": 0.1009,
"step": 35
},
{
"epoch": 0.08200455580865604,
"grad_norm": 0.710520327091217,
"learning_rate": 1.3257575757575757e-06,
"loss": 0.0962,
"step": 36
},
{
"epoch": 0.08428246013667426,
"grad_norm": 0.7249789834022522,
"learning_rate": 1.3636363636363636e-06,
"loss": 0.0948,
"step": 37
},
{
"epoch": 0.08656036446469248,
"grad_norm": 0.7503432631492615,
"learning_rate": 1.4015151515151515e-06,
"loss": 0.0933,
"step": 38
},
{
"epoch": 0.0888382687927107,
"grad_norm": 0.6732667684555054,
"learning_rate": 1.4393939393939396e-06,
"loss": 0.094,
"step": 39
},
{
"epoch": 0.09111617312072894,
"grad_norm": 0.5606656074523926,
"learning_rate": 1.4772727272727275e-06,
"loss": 0.0951,
"step": 40
},
{
"epoch": 0.09339407744874716,
"grad_norm": 0.5518288612365723,
"learning_rate": 1.5151515151515152e-06,
"loss": 0.0924,
"step": 41
},
{
"epoch": 0.09567198177676538,
"grad_norm": 0.5367372632026672,
"learning_rate": 1.5530303030303032e-06,
"loss": 0.0938,
"step": 42
},
{
"epoch": 0.0979498861047836,
"grad_norm": 0.5601660013198853,
"learning_rate": 1.590909090909091e-06,
"loss": 0.0926,
"step": 43
},
{
"epoch": 0.10022779043280182,
"grad_norm": 0.5742217302322388,
"learning_rate": 1.628787878787879e-06,
"loss": 0.0894,
"step": 44
},
{
"epoch": 0.10250569476082004,
"grad_norm": 0.4841398596763611,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.0908,
"step": 45
},
{
"epoch": 0.10478359908883828,
"grad_norm": 0.4976852238178253,
"learning_rate": 1.7045454545454546e-06,
"loss": 0.092,
"step": 46
},
{
"epoch": 0.1070615034168565,
"grad_norm": 0.49381938576698303,
"learning_rate": 1.7424242424242427e-06,
"loss": 0.0889,
"step": 47
},
{
"epoch": 0.10933940774487472,
"grad_norm": 0.5361044406890869,
"learning_rate": 1.7803030303030306e-06,
"loss": 0.0912,
"step": 48
},
{
"epoch": 0.11161731207289294,
"grad_norm": 0.44863954186439514,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.0878,
"step": 49
},
{
"epoch": 0.11389521640091116,
"grad_norm": 0.4702779948711395,
"learning_rate": 1.8560606060606062e-06,
"loss": 0.0895,
"step": 50
},
{
"epoch": 0.11617312072892938,
"grad_norm": 0.4760969877243042,
"learning_rate": 1.8939393939393941e-06,
"loss": 0.0869,
"step": 51
},
{
"epoch": 0.11845102505694761,
"grad_norm": 0.5038303136825562,
"learning_rate": 1.931818181818182e-06,
"loss": 0.0864,
"step": 52
},
{
"epoch": 0.12072892938496584,
"grad_norm": 0.39018872380256653,
"learning_rate": 1.96969696969697e-06,
"loss": 0.0832,
"step": 53
},
{
"epoch": 0.12300683371298406,
"grad_norm": 0.4925285577774048,
"learning_rate": 2.0075757575757576e-06,
"loss": 0.0825,
"step": 54
},
{
"epoch": 0.1252847380410023,
"grad_norm": 0.521104097366333,
"learning_rate": 2.0454545454545457e-06,
"loss": 0.0839,
"step": 55
},
{
"epoch": 0.1275626423690205,
"grad_norm": 0.46636050939559937,
"learning_rate": 2.0833333333333334e-06,
"loss": 0.0822,
"step": 56
},
{
"epoch": 0.12984054669703873,
"grad_norm": 0.4480585753917694,
"learning_rate": 2.1212121212121216e-06,
"loss": 0.0831,
"step": 57
},
{
"epoch": 0.13211845102505695,
"grad_norm": 0.4655265212059021,
"learning_rate": 2.1590909090909092e-06,
"loss": 0.0813,
"step": 58
},
{
"epoch": 0.13439635535307518,
"grad_norm": 0.6499490141868591,
"learning_rate": 2.196969696969697e-06,
"loss": 0.0806,
"step": 59
},
{
"epoch": 0.1366742596810934,
"grad_norm": 0.42999497056007385,
"learning_rate": 2.234848484848485e-06,
"loss": 0.082,
"step": 60
},
{
"epoch": 0.13895216400911162,
"grad_norm": 0.38357794284820557,
"learning_rate": 2.2727272727272728e-06,
"loss": 0.0794,
"step": 61
},
{
"epoch": 0.14123006833712984,
"grad_norm": 0.49868491291999817,
"learning_rate": 2.310606060606061e-06,
"loss": 0.0826,
"step": 62
},
{
"epoch": 0.14350797266514806,
"grad_norm": 0.43505406379699707,
"learning_rate": 2.348484848484849e-06,
"loss": 0.0809,
"step": 63
},
{
"epoch": 0.14578587699316628,
"grad_norm": 0.3699239492416382,
"learning_rate": 2.3863636363636367e-06,
"loss": 0.0794,
"step": 64
},
{
"epoch": 0.1480637813211845,
"grad_norm": 0.37682032585144043,
"learning_rate": 2.4242424242424244e-06,
"loss": 0.0805,
"step": 65
},
{
"epoch": 0.15034168564920272,
"grad_norm": 0.42901331186294556,
"learning_rate": 2.4621212121212125e-06,
"loss": 0.0804,
"step": 66
},
{
"epoch": 0.15261958997722094,
"grad_norm": 0.40458548069000244,
"learning_rate": 2.5e-06,
"loss": 0.0784,
"step": 67
},
{
"epoch": 0.1548974943052392,
"grad_norm": 0.4400278329849243,
"learning_rate": 2.537878787878788e-06,
"loss": 0.08,
"step": 68
},
{
"epoch": 0.1571753986332574,
"grad_norm": 0.4129616916179657,
"learning_rate": 2.575757575757576e-06,
"loss": 0.0773,
"step": 69
},
{
"epoch": 0.15945330296127563,
"grad_norm": 0.4329078793525696,
"learning_rate": 2.6136363636363637e-06,
"loss": 0.0771,
"step": 70
},
{
"epoch": 0.16173120728929385,
"grad_norm": 0.3519822657108307,
"learning_rate": 2.6515151515151514e-06,
"loss": 0.0754,
"step": 71
},
{
"epoch": 0.16400911161731208,
"grad_norm": 0.3959544897079468,
"learning_rate": 2.6893939393939395e-06,
"loss": 0.0769,
"step": 72
},
{
"epoch": 0.1662870159453303,
"grad_norm": 0.3731265366077423,
"learning_rate": 2.7272727272727272e-06,
"loss": 0.077,
"step": 73
},
{
"epoch": 0.16856492027334852,
"grad_norm": 0.43425431847572327,
"learning_rate": 2.7651515151515153e-06,
"loss": 0.0752,
"step": 74
},
{
"epoch": 0.17084282460136674,
"grad_norm": 0.3866608738899231,
"learning_rate": 2.803030303030303e-06,
"loss": 0.0768,
"step": 75
},
{
"epoch": 0.17312072892938496,
"grad_norm": 0.40310585498809814,
"learning_rate": 2.8409090909090916e-06,
"loss": 0.0741,
"step": 76
},
{
"epoch": 0.17539863325740318,
"grad_norm": 0.37993788719177246,
"learning_rate": 2.8787878787878793e-06,
"loss": 0.0761,
"step": 77
},
{
"epoch": 0.1776765375854214,
"grad_norm": 0.5747309327125549,
"learning_rate": 2.916666666666667e-06,
"loss": 0.0752,
"step": 78
},
{
"epoch": 0.17995444191343962,
"grad_norm": 0.3601266145706177,
"learning_rate": 2.954545454545455e-06,
"loss": 0.0732,
"step": 79
},
{
"epoch": 0.18223234624145787,
"grad_norm": 0.3578413128852844,
"learning_rate": 2.992424242424243e-06,
"loss": 0.0777,
"step": 80
},
{
"epoch": 0.1845102505694761,
"grad_norm": 0.3445342183113098,
"learning_rate": 3.0303030303030305e-06,
"loss": 0.077,
"step": 81
},
{
"epoch": 0.1867881548974943,
"grad_norm": 0.46273601055145264,
"learning_rate": 3.0681818181818186e-06,
"loss": 0.0743,
"step": 82
},
{
"epoch": 0.18906605922551253,
"grad_norm": 0.3583069443702698,
"learning_rate": 3.1060606060606063e-06,
"loss": 0.0735,
"step": 83
},
{
"epoch": 0.19134396355353075,
"grad_norm": 0.35333251953125,
"learning_rate": 3.143939393939394e-06,
"loss": 0.0705,
"step": 84
},
{
"epoch": 0.19362186788154898,
"grad_norm": 0.42324912548065186,
"learning_rate": 3.181818181818182e-06,
"loss": 0.0768,
"step": 85
},
{
"epoch": 0.1958997722095672,
"grad_norm": 0.38333430886268616,
"learning_rate": 3.21969696969697e-06,
"loss": 0.074,
"step": 86
},
{
"epoch": 0.19817767653758542,
"grad_norm": 0.382974773645401,
"learning_rate": 3.257575757575758e-06,
"loss": 0.0763,
"step": 87
},
{
"epoch": 0.20045558086560364,
"grad_norm": 0.3540959656238556,
"learning_rate": 3.2954545454545456e-06,
"loss": 0.0752,
"step": 88
},
{
"epoch": 0.20273348519362186,
"grad_norm": 0.44744303822517395,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.0774,
"step": 89
},
{
"epoch": 0.20501138952164008,
"grad_norm": 0.38871949911117554,
"learning_rate": 3.3712121212121214e-06,
"loss": 0.074,
"step": 90
},
{
"epoch": 0.2072892938496583,
"grad_norm": 0.3690223693847656,
"learning_rate": 3.409090909090909e-06,
"loss": 0.0716,
"step": 91
},
{
"epoch": 0.20956719817767655,
"grad_norm": 0.4073256552219391,
"learning_rate": 3.4469696969696977e-06,
"loss": 0.0724,
"step": 92
},
{
"epoch": 0.21184510250569477,
"grad_norm": 0.4237968623638153,
"learning_rate": 3.4848484848484854e-06,
"loss": 0.0753,
"step": 93
},
{
"epoch": 0.214123006833713,
"grad_norm": 0.4609670341014862,
"learning_rate": 3.522727272727273e-06,
"loss": 0.0762,
"step": 94
},
{
"epoch": 0.2164009111617312,
"grad_norm": 0.3941766023635864,
"learning_rate": 3.560606060606061e-06,
"loss": 0.0743,
"step": 95
},
{
"epoch": 0.21867881548974943,
"grad_norm": 0.4086122512817383,
"learning_rate": 3.598484848484849e-06,
"loss": 0.0731,
"step": 96
},
{
"epoch": 0.22095671981776766,
"grad_norm": 0.42508289217948914,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.0747,
"step": 97
},
{
"epoch": 0.22323462414578588,
"grad_norm": 0.3469661772251129,
"learning_rate": 3.6742424242424247e-06,
"loss": 0.0758,
"step": 98
},
{
"epoch": 0.2255125284738041,
"grad_norm": 2.2205488681793213,
"learning_rate": 3.7121212121212124e-06,
"loss": 0.0744,
"step": 99
},
{
"epoch": 0.22779043280182232,
"grad_norm": 0.5607733130455017,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0727,
"step": 100
},
{
"epoch": 0.23006833712984054,
"grad_norm": 0.3631141483783722,
"learning_rate": 3.7878787878787882e-06,
"loss": 0.0729,
"step": 101
},
{
"epoch": 0.23234624145785876,
"grad_norm": 0.41111883521080017,
"learning_rate": 3.825757575757576e-06,
"loss": 0.0707,
"step": 102
},
{
"epoch": 0.23462414578587698,
"grad_norm": 0.42842748761177063,
"learning_rate": 3.863636363636364e-06,
"loss": 0.0741,
"step": 103
},
{
"epoch": 0.23690205011389523,
"grad_norm": 0.5235817432403564,
"learning_rate": 3.901515151515151e-06,
"loss": 0.076,
"step": 104
},
{
"epoch": 0.23917995444191345,
"grad_norm": 0.47007620334625244,
"learning_rate": 3.93939393939394e-06,
"loss": 0.0738,
"step": 105
},
{
"epoch": 0.24145785876993167,
"grad_norm": 0.4875897765159607,
"learning_rate": 3.9772727272727275e-06,
"loss": 0.075,
"step": 106
},
{
"epoch": 0.2437357630979499,
"grad_norm": 0.482083797454834,
"learning_rate": 4.015151515151515e-06,
"loss": 0.073,
"step": 107
},
{
"epoch": 0.2460136674259681,
"grad_norm": 0.3963218033313751,
"learning_rate": 4.053030303030303e-06,
"loss": 0.0711,
"step": 108
},
{
"epoch": 0.24829157175398633,
"grad_norm": 0.45080500841140747,
"learning_rate": 4.0909090909090915e-06,
"loss": 0.0736,
"step": 109
},
{
"epoch": 0.2505694760820046,
"grad_norm": 0.4224866032600403,
"learning_rate": 4.128787878787879e-06,
"loss": 0.0729,
"step": 110
},
{
"epoch": 0.2528473804100228,
"grad_norm": 0.44626861810684204,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0739,
"step": 111
},
{
"epoch": 0.255125284738041,
"grad_norm": 0.4718227684497833,
"learning_rate": 4.204545454545455e-06,
"loss": 0.0734,
"step": 112
},
{
"epoch": 0.25740318906605925,
"grad_norm": 0.43946653604507446,
"learning_rate": 4.242424242424243e-06,
"loss": 0.0738,
"step": 113
},
{
"epoch": 0.25968109339407747,
"grad_norm": 0.4009428918361664,
"learning_rate": 4.280303030303031e-06,
"loss": 0.0735,
"step": 114
},
{
"epoch": 0.2619589977220957,
"grad_norm": 0.4430725574493408,
"learning_rate": 4.3181818181818185e-06,
"loss": 0.0713,
"step": 115
},
{
"epoch": 0.2642369020501139,
"grad_norm": 0.42131391167640686,
"learning_rate": 4.356060606060606e-06,
"loss": 0.0715,
"step": 116
},
{
"epoch": 0.26651480637813213,
"grad_norm": 0.4587585926055908,
"learning_rate": 4.393939393939394e-06,
"loss": 0.0739,
"step": 117
},
{
"epoch": 0.26879271070615035,
"grad_norm": 0.42365217208862305,
"learning_rate": 4.4318181818181824e-06,
"loss": 0.0766,
"step": 118
},
{
"epoch": 0.27107061503416857,
"grad_norm": 0.48815441131591797,
"learning_rate": 4.46969696969697e-06,
"loss": 0.072,
"step": 119
},
{
"epoch": 0.2733485193621868,
"grad_norm": 0.4345132112503052,
"learning_rate": 4.507575757575758e-06,
"loss": 0.0746,
"step": 120
},
{
"epoch": 0.275626423690205,
"grad_norm": 0.40394189953804016,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.0735,
"step": 121
},
{
"epoch": 0.27790432801822323,
"grad_norm": 0.40433070063591003,
"learning_rate": 4.583333333333333e-06,
"loss": 0.0715,
"step": 122
},
{
"epoch": 0.28018223234624146,
"grad_norm": 0.3981536626815796,
"learning_rate": 4.621212121212122e-06,
"loss": 0.0729,
"step": 123
},
{
"epoch": 0.2824601366742597,
"grad_norm": 0.42909497022628784,
"learning_rate": 4.6590909090909095e-06,
"loss": 0.0748,
"step": 124
},
{
"epoch": 0.2847380410022779,
"grad_norm": 0.3979114890098572,
"learning_rate": 4.696969696969698e-06,
"loss": 0.0706,
"step": 125
},
{
"epoch": 0.2870159453302961,
"grad_norm": 0.4175008237361908,
"learning_rate": 4.734848484848486e-06,
"loss": 0.0723,
"step": 126
},
{
"epoch": 0.28929384965831434,
"grad_norm": 0.4061114490032196,
"learning_rate": 4.772727272727273e-06,
"loss": 0.0741,
"step": 127
},
{
"epoch": 0.29157175398633256,
"grad_norm": 0.4005403518676758,
"learning_rate": 4.810606060606061e-06,
"loss": 0.074,
"step": 128
},
{
"epoch": 0.2938496583143508,
"grad_norm": 0.40054985880851746,
"learning_rate": 4.848484848484849e-06,
"loss": 0.0719,
"step": 129
},
{
"epoch": 0.296127562642369,
"grad_norm": 0.4266146421432495,
"learning_rate": 4.8863636363636365e-06,
"loss": 0.0736,
"step": 130
},
{
"epoch": 0.2984054669703872,
"grad_norm": 0.3816811442375183,
"learning_rate": 4.924242424242425e-06,
"loss": 0.0698,
"step": 131
},
{
"epoch": 0.30068337129840544,
"grad_norm": 0.3987654745578766,
"learning_rate": 4.962121212121213e-06,
"loss": 0.0703,
"step": 132
},
{
"epoch": 0.30296127562642367,
"grad_norm": 0.41395506262779236,
"learning_rate": 5e-06,
"loss": 0.0743,
"step": 133
},
{
"epoch": 0.3052391799544419,
"grad_norm": 0.41543126106262207,
"learning_rate": 5e-06,
"loss": 0.0734,
"step": 134
},
{
"epoch": 0.30751708428246016,
"grad_norm": 0.4777982532978058,
"learning_rate": 5e-06,
"loss": 0.0745,
"step": 135
},
{
"epoch": 0.3097949886104784,
"grad_norm": 0.47125476598739624,
"learning_rate": 5e-06,
"loss": 0.0732,
"step": 136
},
{
"epoch": 0.3120728929384966,
"grad_norm": 0.3936716616153717,
"learning_rate": 5e-06,
"loss": 0.0746,
"step": 137
},
{
"epoch": 0.3143507972665148,
"grad_norm": 0.4368305504322052,
"learning_rate": 5e-06,
"loss": 0.0731,
"step": 138
},
{
"epoch": 0.31662870159453305,
"grad_norm": 0.4058026671409607,
"learning_rate": 5e-06,
"loss": 0.0738,
"step": 139
},
{
"epoch": 0.31890660592255127,
"grad_norm": 0.4541865587234497,
"learning_rate": 5e-06,
"loss": 0.0735,
"step": 140
},
{
"epoch": 0.3211845102505695,
"grad_norm": 0.3929808437824249,
"learning_rate": 5e-06,
"loss": 0.0729,
"step": 141
},
{
"epoch": 0.3234624145785877,
"grad_norm": 0.4054822623729706,
"learning_rate": 5e-06,
"loss": 0.0746,
"step": 142
},
{
"epoch": 0.32574031890660593,
"grad_norm": 0.38358375430107117,
"learning_rate": 5e-06,
"loss": 0.0722,
"step": 143
},
{
"epoch": 0.32801822323462415,
"grad_norm": 0.41057437658309937,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 144
},
{
"epoch": 0.33029612756264237,
"grad_norm": 0.4309552013874054,
"learning_rate": 5e-06,
"loss": 0.0739,
"step": 145
},
{
"epoch": 0.3325740318906606,
"grad_norm": 0.38301971554756165,
"learning_rate": 5e-06,
"loss": 0.0713,
"step": 146
},
{
"epoch": 0.3348519362186788,
"grad_norm": 0.435709148645401,
"learning_rate": 5e-06,
"loss": 0.0705,
"step": 147
},
{
"epoch": 0.33712984054669703,
"grad_norm": 0.4956047832965851,
"learning_rate": 5e-06,
"loss": 0.0715,
"step": 148
},
{
"epoch": 0.33940774487471526,
"grad_norm": 0.4198216199874878,
"learning_rate": 5e-06,
"loss": 0.0724,
"step": 149
},
{
"epoch": 0.3416856492027335,
"grad_norm": 0.42688027024269104,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 150
},
{
"epoch": 0.3439635535307517,
"grad_norm": 0.4963231086730957,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 151
},
{
"epoch": 0.3462414578587699,
"grad_norm": 0.44305217266082764,
"learning_rate": 5e-06,
"loss": 0.0717,
"step": 152
},
{
"epoch": 0.34851936218678814,
"grad_norm": 0.5162036418914795,
"learning_rate": 5e-06,
"loss": 0.0735,
"step": 153
},
{
"epoch": 0.35079726651480636,
"grad_norm": 0.4345501959323883,
"learning_rate": 5e-06,
"loss": 0.0732,
"step": 154
},
{
"epoch": 0.3530751708428246,
"grad_norm": 0.3963910937309265,
"learning_rate": 5e-06,
"loss": 0.0722,
"step": 155
},
{
"epoch": 0.3553530751708428,
"grad_norm": 0.42344456911087036,
"learning_rate": 5e-06,
"loss": 0.0727,
"step": 156
},
{
"epoch": 0.357630979498861,
"grad_norm": 0.40760302543640137,
"learning_rate": 5e-06,
"loss": 0.0718,
"step": 157
},
{
"epoch": 0.35990888382687924,
"grad_norm": 0.5510509610176086,
"learning_rate": 5e-06,
"loss": 0.0731,
"step": 158
},
{
"epoch": 0.3621867881548975,
"grad_norm": 0.4162476062774658,
"learning_rate": 5e-06,
"loss": 0.0709,
"step": 159
},
{
"epoch": 0.36446469248291574,
"grad_norm": 0.5093443989753723,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 160
},
{
"epoch": 0.36674259681093396,
"grad_norm": 0.4493374228477478,
"learning_rate": 5e-06,
"loss": 0.071,
"step": 161
},
{
"epoch": 0.3690205011389522,
"grad_norm": 0.44762253761291504,
"learning_rate": 5e-06,
"loss": 0.072,
"step": 162
},
{
"epoch": 0.3712984054669704,
"grad_norm": 0.375567764043808,
"learning_rate": 5e-06,
"loss": 0.0745,
"step": 163
},
{
"epoch": 0.3735763097949886,
"grad_norm": 0.4188103973865509,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 164
},
{
"epoch": 0.37585421412300685,
"grad_norm": 0.37547120451927185,
"learning_rate": 5e-06,
"loss": 0.0721,
"step": 165
},
{
"epoch": 0.37813211845102507,
"grad_norm": 0.45365750789642334,
"learning_rate": 5e-06,
"loss": 0.0721,
"step": 166
},
{
"epoch": 0.3804100227790433,
"grad_norm": 0.4168195128440857,
"learning_rate": 5e-06,
"loss": 0.0717,
"step": 167
},
{
"epoch": 0.3826879271070615,
"grad_norm": 0.4386206269264221,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 168
},
{
"epoch": 0.38496583143507973,
"grad_norm": 0.46875110268592834,
"learning_rate": 5e-06,
"loss": 0.0712,
"step": 169
},
{
"epoch": 0.38724373576309795,
"grad_norm": 0.3938765823841095,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 170
},
{
"epoch": 0.3895216400911162,
"grad_norm": 0.4123467803001404,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 171
},
{
"epoch": 0.3917995444191344,
"grad_norm": 0.4382531940937042,
"learning_rate": 5e-06,
"loss": 0.0712,
"step": 172
},
{
"epoch": 0.3940774487471526,
"grad_norm": 0.4919157922267914,
"learning_rate": 5e-06,
"loss": 0.0729,
"step": 173
},
{
"epoch": 0.39635535307517084,
"grad_norm": 0.5063402056694031,
"learning_rate": 5e-06,
"loss": 0.0707,
"step": 174
},
{
"epoch": 0.39863325740318906,
"grad_norm": 0.6215523481369019,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 175
},
{
"epoch": 0.4009111617312073,
"grad_norm": 0.4623260200023651,
"learning_rate": 5e-06,
"loss": 0.0721,
"step": 176
},
{
"epoch": 0.4031890660592255,
"grad_norm": 0.5183009505271912,
"learning_rate": 5e-06,
"loss": 0.0731,
"step": 177
},
{
"epoch": 0.4054669703872437,
"grad_norm": 0.4948502480983734,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 178
},
{
"epoch": 0.40774487471526194,
"grad_norm": 0.4933330714702606,
"learning_rate": 5e-06,
"loss": 0.0711,
"step": 179
},
{
"epoch": 0.41002277904328016,
"grad_norm": 0.4790695607662201,
"learning_rate": 5e-06,
"loss": 0.0722,
"step": 180
},
{
"epoch": 0.4123006833712984,
"grad_norm": 0.4662487506866455,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 181
},
{
"epoch": 0.4145785876993166,
"grad_norm": 0.3859008252620697,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 182
},
{
"epoch": 0.4168564920273349,
"grad_norm": 0.6519958972930908,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 183
},
{
"epoch": 0.4191343963553531,
"grad_norm": 0.494468092918396,
"learning_rate": 5e-06,
"loss": 0.072,
"step": 184
},
{
"epoch": 0.4214123006833713,
"grad_norm": 0.5084004998207092,
"learning_rate": 5e-06,
"loss": 0.0713,
"step": 185
},
{
"epoch": 0.42369020501138954,
"grad_norm": 0.4281460642814636,
"learning_rate": 5e-06,
"loss": 0.0727,
"step": 186
},
{
"epoch": 0.42596810933940776,
"grad_norm": 0.4384775161743164,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 187
},
{
"epoch": 0.428246013667426,
"grad_norm": 0.4647282660007477,
"learning_rate": 5e-06,
"loss": 0.0714,
"step": 188
},
{
"epoch": 0.4305239179954442,
"grad_norm": 0.4845445156097412,
"learning_rate": 5e-06,
"loss": 0.071,
"step": 189
},
{
"epoch": 0.4328018223234624,
"grad_norm": 0.40431490540504456,
"learning_rate": 5e-06,
"loss": 0.0694,
"step": 190
},
{
"epoch": 0.43507972665148065,
"grad_norm": 0.4188959002494812,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 191
},
{
"epoch": 0.43735763097949887,
"grad_norm": 0.5054275989532471,
"learning_rate": 5e-06,
"loss": 0.0738,
"step": 192
},
{
"epoch": 0.4396355353075171,
"grad_norm": 0.438518226146698,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 193
},
{
"epoch": 0.4419134396355353,
"grad_norm": 0.5088305473327637,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 194
},
{
"epoch": 0.44419134396355353,
"grad_norm": 0.44068580865859985,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 195
},
{
"epoch": 0.44646924829157175,
"grad_norm": 0.4711444675922394,
"learning_rate": 5e-06,
"loss": 0.0749,
"step": 196
},
{
"epoch": 0.44874715261959,
"grad_norm": 0.42442336678504944,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 197
},
{
"epoch": 0.4510250569476082,
"grad_norm": 0.45719027519226074,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 198
},
{
"epoch": 0.4533029612756264,
"grad_norm": 0.4533730745315552,
"learning_rate": 5e-06,
"loss": 0.073,
"step": 199
},
{
"epoch": 0.45558086560364464,
"grad_norm": 0.3968890607357025,
"learning_rate": 5e-06,
"loss": 0.0729,
"step": 200
},
{
"epoch": 0.45785876993166286,
"grad_norm": 0.4367174804210663,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 201
},
{
"epoch": 0.4601366742596811,
"grad_norm": 0.37111589312553406,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 202
},
{
"epoch": 0.4624145785876993,
"grad_norm": 0.45682379603385925,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 203
},
{
"epoch": 0.4646924829157175,
"grad_norm": 0.36972588300704956,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 204
},
{
"epoch": 0.46697038724373574,
"grad_norm": 0.36360761523246765,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 205
},
{
"epoch": 0.46924829157175396,
"grad_norm": 0.3721333146095276,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 206
},
{
"epoch": 0.4715261958997722,
"grad_norm": 0.40355461835861206,
"learning_rate": 5e-06,
"loss": 0.0741,
"step": 207
},
{
"epoch": 0.47380410022779046,
"grad_norm": 0.4323730766773224,
"learning_rate": 5e-06,
"loss": 0.0746,
"step": 208
},
{
"epoch": 0.4760820045558087,
"grad_norm": 0.38074442744255066,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 209
},
{
"epoch": 0.4783599088838269,
"grad_norm": 0.43709224462509155,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 210
},
{
"epoch": 0.4806378132118451,
"grad_norm": 0.3957338333129883,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 211
},
{
"epoch": 0.48291571753986334,
"grad_norm": 0.5257817506790161,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 212
},
{
"epoch": 0.48519362186788156,
"grad_norm": 0.3774060904979706,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 213
},
{
"epoch": 0.4874715261958998,
"grad_norm": 0.5191784501075745,
"learning_rate": 5e-06,
"loss": 0.0732,
"step": 214
},
{
"epoch": 0.489749430523918,
"grad_norm": 0.40021416544914246,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 215
},
{
"epoch": 0.4920273348519362,
"grad_norm": 0.44555339217185974,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 216
},
{
"epoch": 0.49430523917995445,
"grad_norm": 0.5284780859947205,
"learning_rate": 5e-06,
"loss": 0.0726,
"step": 217
},
{
"epoch": 0.49658314350797267,
"grad_norm": 0.4448579251766205,
"learning_rate": 5e-06,
"loss": 0.0711,
"step": 218
},
{
"epoch": 0.4988610478359909,
"grad_norm": 0.4625869393348694,
"learning_rate": 5e-06,
"loss": 0.0711,
"step": 219
},
{
"epoch": 0.5011389521640092,
"grad_norm": 0.46510323882102966,
"learning_rate": 5e-06,
"loss": 0.0736,
"step": 220
},
{
"epoch": 0.5034168564920274,
"grad_norm": 0.480757474899292,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 221
},
{
"epoch": 0.5056947608200456,
"grad_norm": 0.4454173445701599,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 222
},
{
"epoch": 0.5079726651480638,
"grad_norm": 0.44396576285362244,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 223
},
{
"epoch": 0.510250569476082,
"grad_norm": 0.4392300844192505,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 224
},
{
"epoch": 0.5125284738041003,
"grad_norm": 0.4110094904899597,
"learning_rate": 5e-06,
"loss": 0.0717,
"step": 225
},
{
"epoch": 0.5148063781321185,
"grad_norm": 0.41785213351249695,
"learning_rate": 5e-06,
"loss": 0.0728,
"step": 226
},
{
"epoch": 0.5170842824601367,
"grad_norm": 0.4551200568675995,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 227
},
{
"epoch": 0.5193621867881549,
"grad_norm": 0.41336214542388916,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 228
},
{
"epoch": 0.5216400911161732,
"grad_norm": 0.420012503862381,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 229
},
{
"epoch": 0.5239179954441914,
"grad_norm": 0.3874534070491791,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 230
},
{
"epoch": 0.5261958997722096,
"grad_norm": 0.44382932782173157,
"learning_rate": 5e-06,
"loss": 0.0709,
"step": 231
},
{
"epoch": 0.5284738041002278,
"grad_norm": 0.4071871042251587,
"learning_rate": 5e-06,
"loss": 0.0705,
"step": 232
},
{
"epoch": 0.530751708428246,
"grad_norm": 0.4357655644416809,
"learning_rate": 5e-06,
"loss": 0.072,
"step": 233
},
{
"epoch": 0.5330296127562643,
"grad_norm": 0.4081815183162689,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 234
},
{
"epoch": 0.5353075170842825,
"grad_norm": 0.38522443175315857,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 235
},
{
"epoch": 0.5375854214123007,
"grad_norm": 0.4070127308368683,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 236
},
{
"epoch": 0.5398633257403189,
"grad_norm": 0.43571823835372925,
"learning_rate": 5e-06,
"loss": 0.0714,
"step": 237
},
{
"epoch": 0.5421412300683371,
"grad_norm": 0.43545764684677124,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 238
},
{
"epoch": 0.5444191343963554,
"grad_norm": 0.37378817796707153,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 239
},
{
"epoch": 0.5466970387243736,
"grad_norm": 0.40321189165115356,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 240
},
{
"epoch": 0.5489749430523918,
"grad_norm": 0.4021066725254059,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 241
},
{
"epoch": 0.55125284738041,
"grad_norm": 0.3792532682418823,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 242
},
{
"epoch": 0.5535307517084282,
"grad_norm": 0.351995050907135,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 243
},
{
"epoch": 0.5558086560364465,
"grad_norm": 0.4324621558189392,
"learning_rate": 5e-06,
"loss": 0.0719,
"step": 244
},
{
"epoch": 0.5580865603644647,
"grad_norm": 0.4158404767513275,
"learning_rate": 5e-06,
"loss": 0.0689,
"step": 245
},
{
"epoch": 0.5603644646924829,
"grad_norm": 0.39611494541168213,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 246
},
{
"epoch": 0.5626423690205011,
"grad_norm": 0.4095311462879181,
"learning_rate": 5e-06,
"loss": 0.0712,
"step": 247
},
{
"epoch": 0.5649202733485194,
"grad_norm": 0.425353467464447,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 248
},
{
"epoch": 0.5671981776765376,
"grad_norm": 0.4120287299156189,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 249
},
{
"epoch": 0.5694760820045558,
"grad_norm": 0.42984098196029663,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 250
},
{
"epoch": 0.571753986332574,
"grad_norm": 0.41558778285980225,
"learning_rate": 5e-06,
"loss": 0.07,
"step": 251
},
{
"epoch": 0.5740318906605922,
"grad_norm": 0.39627233147621155,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 252
},
{
"epoch": 0.5763097949886105,
"grad_norm": 0.4116947650909424,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 253
},
{
"epoch": 0.5785876993166287,
"grad_norm": 0.4483950436115265,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 254
},
{
"epoch": 0.5808656036446469,
"grad_norm": 0.40655770897865295,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 255
},
{
"epoch": 0.5831435079726651,
"grad_norm": 0.4380018413066864,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 256
},
{
"epoch": 0.5854214123006833,
"grad_norm": 0.37291720509529114,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 257
},
{
"epoch": 0.5876993166287016,
"grad_norm": 0.4471172094345093,
"learning_rate": 5e-06,
"loss": 0.0706,
"step": 258
},
{
"epoch": 0.5899772209567198,
"grad_norm": 0.33719295263290405,
"learning_rate": 5e-06,
"loss": 0.0704,
"step": 259
},
{
"epoch": 0.592255125284738,
"grad_norm": 0.4563951790332794,
"learning_rate": 5e-06,
"loss": 0.0704,
"step": 260
},
{
"epoch": 0.5945330296127562,
"grad_norm": 0.479675829410553,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 261
},
{
"epoch": 0.5968109339407744,
"grad_norm": 0.48119309544563293,
"learning_rate": 5e-06,
"loss": 0.0704,
"step": 262
},
{
"epoch": 0.5990888382687927,
"grad_norm": 0.4188333749771118,
"learning_rate": 5e-06,
"loss": 0.0689,
"step": 263
},
{
"epoch": 0.6013667425968109,
"grad_norm": 0.4289758801460266,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 264
},
{
"epoch": 0.6036446469248291,
"grad_norm": 0.4562152922153473,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 265
},
{
"epoch": 0.6059225512528473,
"grad_norm": 0.3772522807121277,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 266
},
{
"epoch": 0.6082004555808656,
"grad_norm": 0.4561619460582733,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 267
},
{
"epoch": 0.6104783599088838,
"grad_norm": 0.3349689245223999,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 268
},
{
"epoch": 0.6127562642369021,
"grad_norm": 0.37530314922332764,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 269
},
{
"epoch": 0.6150341685649203,
"grad_norm": 0.4140493869781494,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 270
},
{
"epoch": 0.6173120728929385,
"grad_norm": 0.3943673074245453,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 271
},
{
"epoch": 0.6195899772209568,
"grad_norm": 0.4929119348526001,
"learning_rate": 5e-06,
"loss": 0.0694,
"step": 272
},
{
"epoch": 0.621867881548975,
"grad_norm": 0.3644123375415802,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 273
},
{
"epoch": 0.6241457858769932,
"grad_norm": 0.3780081570148468,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 274
},
{
"epoch": 0.6264236902050114,
"grad_norm": 0.3895011246204376,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 275
},
{
"epoch": 0.6287015945330297,
"grad_norm": 0.39944520592689514,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 276
},
{
"epoch": 0.6309794988610479,
"grad_norm": 0.5009689927101135,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 277
},
{
"epoch": 0.6332574031890661,
"grad_norm": 0.3824428915977478,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 278
},
{
"epoch": 0.6355353075170843,
"grad_norm": 0.40774327516555786,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 279
},
{
"epoch": 0.6378132118451025,
"grad_norm": 0.4349845051765442,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 280
},
{
"epoch": 0.6400911161731208,
"grad_norm": 0.3697284758090973,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 281
},
{
"epoch": 0.642369020501139,
"grad_norm": 0.42937129735946655,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 282
},
{
"epoch": 0.6446469248291572,
"grad_norm": 0.3947838544845581,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 283
},
{
"epoch": 0.6469248291571754,
"grad_norm": 0.435682088136673,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 284
},
{
"epoch": 0.6492027334851936,
"grad_norm": 0.4589371979236603,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 285
},
{
"epoch": 0.6514806378132119,
"grad_norm": 0.43639275431632996,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 286
},
{
"epoch": 0.6537585421412301,
"grad_norm": 0.4098499119281769,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 287
},
{
"epoch": 0.6560364464692483,
"grad_norm": 0.35208365321159363,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 288
},
{
"epoch": 0.6583143507972665,
"grad_norm": 0.34454038739204407,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 289
},
{
"epoch": 0.6605922551252847,
"grad_norm": 0.41582560539245605,
"learning_rate": 5e-06,
"loss": 0.0707,
"step": 290
},
{
"epoch": 0.662870159453303,
"grad_norm": 0.4000478684902191,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 291
},
{
"epoch": 0.6651480637813212,
"grad_norm": 0.3716413676738739,
"learning_rate": 5e-06,
"loss": 0.0707,
"step": 292
},
{
"epoch": 0.6674259681093394,
"grad_norm": 0.4950391352176666,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 293
},
{
"epoch": 0.6697038724373576,
"grad_norm": 0.40866413712501526,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 294
},
{
"epoch": 0.6719817767653758,
"grad_norm": 0.35762685537338257,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 295
},
{
"epoch": 0.6742596810933941,
"grad_norm": 0.37755048274993896,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 296
},
{
"epoch": 0.6765375854214123,
"grad_norm": 0.4419291913509369,
"learning_rate": 5e-06,
"loss": 0.0746,
"step": 297
},
{
"epoch": 0.6788154897494305,
"grad_norm": 0.42603951692581177,
"learning_rate": 5e-06,
"loss": 0.0705,
"step": 298
},
{
"epoch": 0.6810933940774487,
"grad_norm": 0.4297736585140228,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 299
},
{
"epoch": 0.683371298405467,
"grad_norm": 0.4051309823989868,
"learning_rate": 5e-06,
"loss": 0.069,
"step": 300
},
{
"epoch": 0.6856492027334852,
"grad_norm": 0.43650469183921814,
"learning_rate": 5e-06,
"loss": 0.0705,
"step": 301
},
{
"epoch": 0.6879271070615034,
"grad_norm": 0.4065714180469513,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 302
},
{
"epoch": 0.6902050113895216,
"grad_norm": 0.3967154026031494,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 303
},
{
"epoch": 0.6924829157175398,
"grad_norm": 0.4712061882019043,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 304
},
{
"epoch": 0.6947608200455581,
"grad_norm": 0.42462876439094543,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 305
},
{
"epoch": 0.6970387243735763,
"grad_norm": 0.41642263531684875,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 306
},
{
"epoch": 0.6993166287015945,
"grad_norm": 0.4268721044063568,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 307
},
{
"epoch": 0.7015945330296127,
"grad_norm": 0.4870758652687073,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 308
},
{
"epoch": 0.7038724373576309,
"grad_norm": 0.38001054525375366,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 309
},
{
"epoch": 0.7061503416856492,
"grad_norm": 0.44683194160461426,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 310
},
{
"epoch": 0.7084282460136674,
"grad_norm": 0.3841770589351654,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 311
},
{
"epoch": 0.7107061503416856,
"grad_norm": 0.41161251068115234,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 312
},
{
"epoch": 0.7129840546697038,
"grad_norm": 0.38489028811454773,
"learning_rate": 5e-06,
"loss": 0.07,
"step": 313
},
{
"epoch": 0.715261958997722,
"grad_norm": 0.3507677912712097,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 314
},
{
"epoch": 0.7175398633257403,
"grad_norm": 0.38104042410850525,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 315
},
{
"epoch": 0.7198177676537585,
"grad_norm": 0.3669570982456207,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 316
},
{
"epoch": 0.7220956719817767,
"grad_norm": 0.42886313796043396,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 317
},
{
"epoch": 0.724373576309795,
"grad_norm": 0.3710843324661255,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 318
},
{
"epoch": 0.7266514806378133,
"grad_norm": 0.44205132126808167,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 319
},
{
"epoch": 0.7289293849658315,
"grad_norm": 0.41439348459243774,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 320
},
{
"epoch": 0.7312072892938497,
"grad_norm": 0.3940696716308594,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 321
},
{
"epoch": 0.7334851936218679,
"grad_norm": 0.41583356261253357,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 322
},
{
"epoch": 0.7357630979498861,
"grad_norm": 0.39446648955345154,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 323
},
{
"epoch": 0.7380410022779044,
"grad_norm": 0.4365374445915222,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 324
},
{
"epoch": 0.7403189066059226,
"grad_norm": 0.36670970916748047,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 325
},
{
"epoch": 0.7425968109339408,
"grad_norm": 0.43367478251457214,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 326
},
{
"epoch": 0.744874715261959,
"grad_norm": 0.3726787567138672,
"learning_rate": 5e-06,
"loss": 0.0701,
"step": 327
},
{
"epoch": 0.7471526195899773,
"grad_norm": 0.4093555808067322,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 328
},
{
"epoch": 0.7494305239179955,
"grad_norm": 0.49851593375205994,
"learning_rate": 5e-06,
"loss": 0.0717,
"step": 329
},
{
"epoch": 0.7517084282460137,
"grad_norm": 0.38292035460472107,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 330
},
{
"epoch": 0.7539863325740319,
"grad_norm": 0.41123974323272705,
"learning_rate": 5e-06,
"loss": 0.07,
"step": 331
},
{
"epoch": 0.7562642369020501,
"grad_norm": 0.3536129295825958,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 332
},
{
"epoch": 0.7585421412300684,
"grad_norm": 0.38178107142448425,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 333
},
{
"epoch": 0.7608200455580866,
"grad_norm": 0.36010780930519104,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 334
},
{
"epoch": 0.7630979498861048,
"grad_norm": 0.4523884356021881,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 335
},
{
"epoch": 0.765375854214123,
"grad_norm": 0.39606744050979614,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 336
},
{
"epoch": 0.7676537585421412,
"grad_norm": 0.41211503744125366,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 337
},
{
"epoch": 0.7699316628701595,
"grad_norm": 0.41744863986968994,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 338
},
{
"epoch": 0.7722095671981777,
"grad_norm": 0.3365219235420227,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 339
},
{
"epoch": 0.7744874715261959,
"grad_norm": 0.4278775453567505,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 340
},
{
"epoch": 0.7767653758542141,
"grad_norm": 0.3654761016368866,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 341
},
{
"epoch": 0.7790432801822323,
"grad_norm": 0.4179307520389557,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 342
},
{
"epoch": 0.7813211845102506,
"grad_norm": 0.3700203597545624,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 343
},
{
"epoch": 0.7835990888382688,
"grad_norm": 0.41979873180389404,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 344
},
{
"epoch": 0.785876993166287,
"grad_norm": 0.3833925127983093,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 345
},
{
"epoch": 0.7881548974943052,
"grad_norm": 0.38170167803764343,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 346
},
{
"epoch": 0.7904328018223234,
"grad_norm": 0.4435146749019623,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 347
},
{
"epoch": 0.7927107061503417,
"grad_norm": 0.3727116584777832,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 348
},
{
"epoch": 0.7949886104783599,
"grad_norm": 0.3438148498535156,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 349
},
{
"epoch": 0.7972665148063781,
"grad_norm": 1.1323906183242798,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 350
},
{
"epoch": 0.7995444191343963,
"grad_norm": 0.49652302265167236,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 351
},
{
"epoch": 0.8018223234624146,
"grad_norm": 0.3763923943042755,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 352
},
{
"epoch": 0.8041002277904328,
"grad_norm": 0.3898470997810364,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 353
},
{
"epoch": 0.806378132118451,
"grad_norm": 0.43604037165641785,
"learning_rate": 5e-06,
"loss": 0.0699,
"step": 354
},
{
"epoch": 0.8086560364464692,
"grad_norm": 0.40902185440063477,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 355
},
{
"epoch": 0.8109339407744874,
"grad_norm": 0.4095119535923004,
"learning_rate": 5e-06,
"loss": 0.0703,
"step": 356
},
{
"epoch": 0.8132118451025057,
"grad_norm": 0.38673949241638184,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 357
},
{
"epoch": 0.8154897494305239,
"grad_norm": 0.3702470362186432,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 358
},
{
"epoch": 0.8177676537585421,
"grad_norm": 0.38289743661880493,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 359
},
{
"epoch": 0.8200455580865603,
"grad_norm": 0.398942232131958,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 360
},
{
"epoch": 0.8223234624145785,
"grad_norm": 0.4990338683128357,
"learning_rate": 5e-06,
"loss": 0.0689,
"step": 361
},
{
"epoch": 0.8246013667425968,
"grad_norm": 0.4140332341194153,
"learning_rate": 5e-06,
"loss": 0.0702,
"step": 362
},
{
"epoch": 0.826879271070615,
"grad_norm": 0.38353094458580017,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 363
},
{
"epoch": 0.8291571753986332,
"grad_norm": 0.40966200828552246,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 364
},
{
"epoch": 0.8314350797266514,
"grad_norm": 0.40145012736320496,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 365
},
{
"epoch": 0.8337129840546698,
"grad_norm": 0.3553916811943054,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 366
},
{
"epoch": 0.835990888382688,
"grad_norm": 0.36585506796836853,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 367
},
{
"epoch": 0.8382687927107062,
"grad_norm": 0.40545061230659485,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 368
},
{
"epoch": 0.8405466970387244,
"grad_norm": 0.43122202157974243,
"learning_rate": 5e-06,
"loss": 0.07,
"step": 369
},
{
"epoch": 0.8428246013667426,
"grad_norm": 0.38822853565216064,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 370
},
{
"epoch": 0.8451025056947609,
"grad_norm": 0.36941057443618774,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 371
},
{
"epoch": 0.8473804100227791,
"grad_norm": 0.3812001049518585,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 372
},
{
"epoch": 0.8496583143507973,
"grad_norm": 0.37349483370780945,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 373
},
{
"epoch": 0.8519362186788155,
"grad_norm": 0.36606496572494507,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 374
},
{
"epoch": 0.8542141230068337,
"grad_norm": 0.4783948063850403,
"learning_rate": 5e-06,
"loss": 0.0697,
"step": 375
},
{
"epoch": 0.856492027334852,
"grad_norm": 0.42428654432296753,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 376
},
{
"epoch": 0.8587699316628702,
"grad_norm": 0.43024080991744995,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 377
},
{
"epoch": 0.8610478359908884,
"grad_norm": 0.45276060700416565,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 378
},
{
"epoch": 0.8633257403189066,
"grad_norm": 0.5208924412727356,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 379
},
{
"epoch": 0.8656036446469249,
"grad_norm": 0.44442853331565857,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 380
},
{
"epoch": 0.8678815489749431,
"grad_norm": 0.4459463059902191,
"learning_rate": 5e-06,
"loss": 0.0708,
"step": 381
},
{
"epoch": 0.8701594533029613,
"grad_norm": 0.4089488387107849,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 382
},
{
"epoch": 0.8724373576309795,
"grad_norm": 0.4216194450855255,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 383
},
{
"epoch": 0.8747152619589977,
"grad_norm": 0.4460054337978363,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 384
},
{
"epoch": 0.876993166287016,
"grad_norm": 0.3685241937637329,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 385
},
{
"epoch": 0.8792710706150342,
"grad_norm": 0.5342898964881897,
"learning_rate": 5e-06,
"loss": 0.0619,
"step": 386
},
{
"epoch": 0.8815489749430524,
"grad_norm": 0.41996005177497864,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 387
},
{
"epoch": 0.8838268792710706,
"grad_norm": 0.5424495339393616,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 388
},
{
"epoch": 0.8861047835990888,
"grad_norm": 0.5055522918701172,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 389
},
{
"epoch": 0.8883826879271071,
"grad_norm": 0.48916786909103394,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 390
},
{
"epoch": 0.8906605922551253,
"grad_norm": 0.4740985333919525,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 391
},
{
"epoch": 0.8929384965831435,
"grad_norm": 0.5370116829872131,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 392
},
{
"epoch": 0.8952164009111617,
"grad_norm": 0.45419377088546753,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 393
},
{
"epoch": 0.89749430523918,
"grad_norm": 0.4498198330402374,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 394
},
{
"epoch": 0.8997722095671982,
"grad_norm": 0.47344449162483215,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 395
},
{
"epoch": 0.9020501138952164,
"grad_norm": 0.49295154213905334,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 396
},
{
"epoch": 0.9043280182232346,
"grad_norm": 0.49694356322288513,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 397
},
{
"epoch": 0.9066059225512528,
"grad_norm": 0.4109736680984497,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 398
},
{
"epoch": 0.908883826879271,
"grad_norm": 0.386333703994751,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 399
},
{
"epoch": 0.9111617312072893,
"grad_norm": 0.4430575966835022,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 400
},
{
"epoch": 0.9134396355353075,
"grad_norm": 0.34944966435432434,
"learning_rate": 5e-06,
"loss": 0.0706,
"step": 401
},
{
"epoch": 0.9157175398633257,
"grad_norm": 0.4361039400100708,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 402
},
{
"epoch": 0.9179954441913439,
"grad_norm": 0.41876447200775146,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 403
},
{
"epoch": 0.9202733485193622,
"grad_norm": 0.46392524242401123,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 404
},
{
"epoch": 0.9225512528473804,
"grad_norm": 0.36828112602233887,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 405
},
{
"epoch": 0.9248291571753986,
"grad_norm": 0.445583313703537,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 406
},
{
"epoch": 0.9271070615034168,
"grad_norm": 0.4569609463214874,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 407
},
{
"epoch": 0.929384965831435,
"grad_norm": 0.4351450800895691,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 408
},
{
"epoch": 0.9316628701594533,
"grad_norm": 0.4705968499183655,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 409
},
{
"epoch": 0.9339407744874715,
"grad_norm": 0.3710295855998993,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 410
},
{
"epoch": 0.9362186788154897,
"grad_norm": 0.46435174345970154,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 411
},
{
"epoch": 0.9384965831435079,
"grad_norm": 0.35733482241630554,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 412
},
{
"epoch": 0.9407744874715261,
"grad_norm": 0.4195706844329834,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 413
},
{
"epoch": 0.9430523917995444,
"grad_norm": 0.3877922594547272,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 414
},
{
"epoch": 0.9453302961275627,
"grad_norm": 0.3729753792285919,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 415
},
{
"epoch": 0.9476082004555809,
"grad_norm": 0.38233113288879395,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 416
},
{
"epoch": 0.9498861047835991,
"grad_norm": 0.34748148918151855,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 417
},
{
"epoch": 0.9521640091116174,
"grad_norm": 0.38823238015174866,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 418
},
{
"epoch": 0.9544419134396356,
"grad_norm": 0.38967302441596985,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 419
},
{
"epoch": 0.9567198177676538,
"grad_norm": 0.3796670734882355,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 420
},
{
"epoch": 0.958997722095672,
"grad_norm": 0.375175803899765,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 421
},
{
"epoch": 0.9612756264236902,
"grad_norm": 0.39777424931526184,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 422
},
{
"epoch": 0.9635535307517085,
"grad_norm": 0.3519769310951233,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 423
},
{
"epoch": 0.9658314350797267,
"grad_norm": 0.39732250571250916,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 424
},
{
"epoch": 0.9681093394077449,
"grad_norm": 0.3979857861995697,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 425
},
{
"epoch": 0.9703872437357631,
"grad_norm": 0.4009624421596527,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 426
},
{
"epoch": 0.9726651480637813,
"grad_norm": 0.37647587060928345,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 427
},
{
"epoch": 0.9749430523917996,
"grad_norm": 0.4034980833530426,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 428
},
{
"epoch": 0.9772209567198178,
"grad_norm": 0.3745870292186737,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 429
},
{
"epoch": 0.979498861047836,
"grad_norm": 0.3924770653247833,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 430
},
{
"epoch": 0.9817767653758542,
"grad_norm": 0.3894212543964386,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 431
},
{
"epoch": 0.9840546697038725,
"grad_norm": 0.4379626214504242,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 432
},
{
"epoch": 0.9863325740318907,
"grad_norm": 0.41487187147140503,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 433
},
{
"epoch": 0.9886104783599089,
"grad_norm": 0.3902760446071625,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 434
},
{
"epoch": 0.9908883826879271,
"grad_norm": 0.4039607644081116,
"learning_rate": 5e-06,
"loss": 0.0704,
"step": 435
},
{
"epoch": 0.9931662870159453,
"grad_norm": 0.46864795684814453,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 436
},
{
"epoch": 0.9954441913439636,
"grad_norm": 0.4453410804271698,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 437
},
{
"epoch": 0.9977220956719818,
"grad_norm": 0.41671499609947205,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 438
},
{
"epoch": 1.0,
"grad_norm": 0.43622660636901855,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 439
},
{
"epoch": 1.0022779043280183,
"grad_norm": 0.4500711262226105,
"learning_rate": 5e-06,
"loss": 0.0694,
"step": 440
},
{
"epoch": 1.0045558086560364,
"grad_norm": 0.4106467664241791,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 441
},
{
"epoch": 1.0068337129840548,
"grad_norm": 0.3629504144191742,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 442
},
{
"epoch": 1.0091116173120729,
"grad_norm": 0.3577280640602112,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 443
},
{
"epoch": 1.0113895216400912,
"grad_norm": 0.4010712206363678,
"learning_rate": 5e-06,
"loss": 0.0698,
"step": 444
},
{
"epoch": 1.0136674259681093,
"grad_norm": 0.4344230890274048,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 445
},
{
"epoch": 1.0159453302961277,
"grad_norm": 0.36966174840927124,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 446
},
{
"epoch": 1.0182232346241458,
"grad_norm": 0.40414756536483765,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 447
},
{
"epoch": 1.020501138952164,
"grad_norm": 0.4263600707054138,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 448
},
{
"epoch": 1.0227790432801822,
"grad_norm": 0.3861621618270874,
"learning_rate": 5e-06,
"loss": 0.0689,
"step": 449
},
{
"epoch": 1.0250569476082005,
"grad_norm": 0.4103226363658905,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 450
},
{
"epoch": 1.0273348519362187,
"grad_norm": 0.5162451863288879,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 451
},
{
"epoch": 1.029612756264237,
"grad_norm": 0.3653396964073181,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 452
},
{
"epoch": 1.031890660592255,
"grad_norm": 0.40646302700042725,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 453
},
{
"epoch": 1.0341685649202734,
"grad_norm": 0.351541668176651,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 454
},
{
"epoch": 1.0364464692482915,
"grad_norm": 0.45820608735084534,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 455
},
{
"epoch": 1.0387243735763099,
"grad_norm": 0.36796748638153076,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 456
},
{
"epoch": 1.041002277904328,
"grad_norm": 0.41809725761413574,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 457
},
{
"epoch": 1.0432801822323463,
"grad_norm": 0.4381527006626129,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 458
},
{
"epoch": 1.0455580865603644,
"grad_norm": 0.34027010202407837,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 459
},
{
"epoch": 1.0478359908883828,
"grad_norm": 0.3854738175868988,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 460
},
{
"epoch": 1.0501138952164009,
"grad_norm": 0.33832982182502747,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 461
},
{
"epoch": 1.0523917995444192,
"grad_norm": 0.3581103980541229,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 462
},
{
"epoch": 1.0546697038724373,
"grad_norm": 0.3820573687553406,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 463
},
{
"epoch": 1.0569476082004556,
"grad_norm": 0.38710519671440125,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 464
},
{
"epoch": 1.0592255125284737,
"grad_norm": 0.45680227875709534,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 465
},
{
"epoch": 1.061503416856492,
"grad_norm": 0.4713359773159027,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 466
},
{
"epoch": 1.0637813211845102,
"grad_norm": 0.4612472355365753,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 467
},
{
"epoch": 1.0660592255125285,
"grad_norm": 0.3581363558769226,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 468
},
{
"epoch": 1.0683371298405466,
"grad_norm": 0.6403517723083496,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 469
},
{
"epoch": 1.070615034168565,
"grad_norm": 0.6075398921966553,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 470
},
{
"epoch": 1.072892938496583,
"grad_norm": 0.37106701731681824,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 471
},
{
"epoch": 1.0751708428246014,
"grad_norm": 0.4145383834838867,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 472
},
{
"epoch": 1.0774487471526195,
"grad_norm": 0.4051216244697571,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 473
},
{
"epoch": 1.0797266514806378,
"grad_norm": 0.4450092017650604,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 474
},
{
"epoch": 1.082004555808656,
"grad_norm": 0.6834749579429626,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 475
},
{
"epoch": 1.0842824601366743,
"grad_norm": 0.4596191346645355,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 476
},
{
"epoch": 1.0865603644646924,
"grad_norm": 0.35578453540802,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 477
},
{
"epoch": 1.0888382687927107,
"grad_norm": 0.38176682591438293,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 478
},
{
"epoch": 1.0911161731207288,
"grad_norm": 0.4199659526348114,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 479
},
{
"epoch": 1.0933940774487472,
"grad_norm": 0.39762362837791443,
"learning_rate": 5e-06,
"loss": 0.0707,
"step": 480
},
{
"epoch": 1.0956719817767653,
"grad_norm": 0.3889635503292084,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 481
},
{
"epoch": 1.0979498861047836,
"grad_norm": 0.3593704402446747,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 482
},
{
"epoch": 1.1002277904328017,
"grad_norm": 0.36741095781326294,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 483
},
{
"epoch": 1.10250569476082,
"grad_norm": 0.3881998062133789,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 484
},
{
"epoch": 1.1047835990888384,
"grad_norm": 0.4464372992515564,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 485
},
{
"epoch": 1.1070615034168565,
"grad_norm": 0.431099534034729,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 486
},
{
"epoch": 1.1093394077448746,
"grad_norm": 0.3904043436050415,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 487
},
{
"epoch": 1.111617312072893,
"grad_norm": 0.3737926781177521,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 488
},
{
"epoch": 1.1138952164009113,
"grad_norm": 0.3733069896697998,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 489
},
{
"epoch": 1.1161731207289294,
"grad_norm": 0.4064606726169586,
"learning_rate": 5e-06,
"loss": 0.0689,
"step": 490
},
{
"epoch": 1.1184510250569477,
"grad_norm": 0.3892678916454315,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 491
},
{
"epoch": 1.1207289293849658,
"grad_norm": 0.40777847170829773,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 492
},
{
"epoch": 1.1230068337129842,
"grad_norm": 0.3872988522052765,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 493
},
{
"epoch": 1.1252847380410023,
"grad_norm": 0.42812952399253845,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 494
},
{
"epoch": 1.1275626423690206,
"grad_norm": 0.33735978603363037,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 495
},
{
"epoch": 1.1298405466970387,
"grad_norm": 0.40792304277420044,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 496
},
{
"epoch": 1.132118451025057,
"grad_norm": 0.3538738191127777,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 497
},
{
"epoch": 1.1343963553530751,
"grad_norm": 0.40359169244766235,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 498
},
{
"epoch": 1.1366742596810935,
"grad_norm": 0.4550337791442871,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 499
},
{
"epoch": 1.1389521640091116,
"grad_norm": 0.37589704990386963,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 500
},
{
"epoch": 1.14123006833713,
"grad_norm": 0.5502781867980957,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 501
},
{
"epoch": 1.143507972665148,
"grad_norm": 0.3509303629398346,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 502
},
{
"epoch": 1.1457858769931664,
"grad_norm": 0.36012589931488037,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 503
},
{
"epoch": 1.1480637813211845,
"grad_norm": 0.40766096115112305,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 504
},
{
"epoch": 1.1503416856492028,
"grad_norm": 0.35230013728141785,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 505
},
{
"epoch": 1.152619589977221,
"grad_norm": 0.3493717610836029,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 506
},
{
"epoch": 1.1548974943052392,
"grad_norm": 0.34316879510879517,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 507
},
{
"epoch": 1.1571753986332574,
"grad_norm": 0.37918758392333984,
"learning_rate": 5e-06,
"loss": 0.07,
"step": 508
},
{
"epoch": 1.1594533029612757,
"grad_norm": 0.3596925437450409,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 509
},
{
"epoch": 1.1617312072892938,
"grad_norm": 0.36058440804481506,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 510
},
{
"epoch": 1.1640091116173121,
"grad_norm": 0.37516024708747864,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 511
},
{
"epoch": 1.1662870159453302,
"grad_norm": 0.39049404859542847,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 512
},
{
"epoch": 1.1685649202733486,
"grad_norm": 0.3826717734336853,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 513
},
{
"epoch": 1.1708428246013667,
"grad_norm": 0.3979628384113312,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 514
},
{
"epoch": 1.173120728929385,
"grad_norm": 0.36135396361351013,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 515
},
{
"epoch": 1.1753986332574031,
"grad_norm": 0.3812471032142639,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 516
},
{
"epoch": 1.1776765375854215,
"grad_norm": 0.381881982088089,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 517
},
{
"epoch": 1.1799544419134396,
"grad_norm": 0.40275490283966064,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 518
},
{
"epoch": 1.182232346241458,
"grad_norm": 0.35566964745521545,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 519
},
{
"epoch": 1.184510250569476,
"grad_norm": 0.4010874927043915,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 520
},
{
"epoch": 1.1867881548974943,
"grad_norm": 0.35122379660606384,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 521
},
{
"epoch": 1.1890660592255125,
"grad_norm": 0.38552436232566833,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 522
},
{
"epoch": 1.1913439635535308,
"grad_norm": 0.36752209067344666,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 523
},
{
"epoch": 1.193621867881549,
"grad_norm": 0.3583572208881378,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 524
},
{
"epoch": 1.1958997722095672,
"grad_norm": 0.34054288268089294,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 525
},
{
"epoch": 1.1981776765375853,
"grad_norm": 0.4100807309150696,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 526
},
{
"epoch": 1.2004555808656037,
"grad_norm": 0.3639017641544342,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 527
},
{
"epoch": 1.2027334851936218,
"grad_norm": 0.47511011362075806,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 528
},
{
"epoch": 1.20501138952164,
"grad_norm": 0.4454311728477478,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 529
},
{
"epoch": 1.2072892938496582,
"grad_norm": 0.38880598545074463,
"learning_rate": 5e-06,
"loss": 0.069,
"step": 530
},
{
"epoch": 1.2095671981776766,
"grad_norm": 0.3639177978038788,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 531
},
{
"epoch": 1.2118451025056949,
"grad_norm": 0.36371222138404846,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 532
},
{
"epoch": 1.214123006833713,
"grad_norm": 0.3781519830226898,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 533
},
{
"epoch": 1.216400911161731,
"grad_norm": 0.4092641770839691,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 534
},
{
"epoch": 1.2186788154897494,
"grad_norm": 0.4048423171043396,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 535
},
{
"epoch": 1.2209567198177678,
"grad_norm": 0.40468040108680725,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 536
},
{
"epoch": 1.2232346241457859,
"grad_norm": 0.38839131593704224,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 537
},
{
"epoch": 1.225512528473804,
"grad_norm": 0.35276639461517334,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 538
},
{
"epoch": 1.2277904328018223,
"grad_norm": 0.43698349595069885,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 539
},
{
"epoch": 1.2300683371298406,
"grad_norm": 0.4079034626483917,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 540
},
{
"epoch": 1.2323462414578588,
"grad_norm": 0.40131327509880066,
"learning_rate": 5e-06,
"loss": 0.0691,
"step": 541
},
{
"epoch": 1.2346241457858769,
"grad_norm": 0.3789280652999878,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 542
},
{
"epoch": 1.2369020501138952,
"grad_norm": 0.31505241990089417,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 543
},
{
"epoch": 1.2391799544419135,
"grad_norm": 0.40908434987068176,
"learning_rate": 5e-06,
"loss": 0.0705,
"step": 544
},
{
"epoch": 1.2414578587699316,
"grad_norm": 0.39963164925575256,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 545
},
{
"epoch": 1.24373576309795,
"grad_norm": 0.41629716753959656,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 546
},
{
"epoch": 1.246013667425968,
"grad_norm": 0.384478896856308,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 547
},
{
"epoch": 1.2482915717539864,
"grad_norm": 0.3786999583244324,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 548
},
{
"epoch": 1.2505694760820045,
"grad_norm": 0.40297600626945496,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 549
},
{
"epoch": 1.2528473804100229,
"grad_norm": 0.40436241030693054,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 550
},
{
"epoch": 1.255125284738041,
"grad_norm": 0.42469269037246704,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 551
},
{
"epoch": 1.2574031890660593,
"grad_norm": 0.3578304052352905,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 552
},
{
"epoch": 1.2596810933940774,
"grad_norm": 0.45142272114753723,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 553
},
{
"epoch": 1.2619589977220957,
"grad_norm": 0.36942797899246216,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 554
},
{
"epoch": 1.2642369020501139,
"grad_norm": 0.4410291314125061,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 555
},
{
"epoch": 1.2665148063781322,
"grad_norm": 0.376847505569458,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 556
},
{
"epoch": 1.2687927107061503,
"grad_norm": 0.4184603989124298,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 557
},
{
"epoch": 1.2710706150341686,
"grad_norm": 0.35660773515701294,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 558
},
{
"epoch": 1.2733485193621867,
"grad_norm": 0.41945064067840576,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 559
},
{
"epoch": 1.275626423690205,
"grad_norm": 0.3595651686191559,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 560
},
{
"epoch": 1.2779043280182232,
"grad_norm": 0.43288135528564453,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 561
},
{
"epoch": 1.2801822323462415,
"grad_norm": 0.38666829466819763,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 562
},
{
"epoch": 1.2824601366742596,
"grad_norm": 0.40617242455482483,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 563
},
{
"epoch": 1.284738041002278,
"grad_norm": 0.46813103556632996,
"learning_rate": 5e-06,
"loss": 0.0693,
"step": 564
},
{
"epoch": 1.287015945330296,
"grad_norm": 0.36550068855285645,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 565
},
{
"epoch": 1.2892938496583144,
"grad_norm": 0.4070315659046173,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 566
},
{
"epoch": 1.2915717539863325,
"grad_norm": 0.35947465896606445,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 567
},
{
"epoch": 1.2938496583143508,
"grad_norm": 0.36455580592155457,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 568
},
{
"epoch": 1.296127562642369,
"grad_norm": 0.38757917284965515,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 569
},
{
"epoch": 1.2984054669703873,
"grad_norm": 0.3300890326499939,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 570
},
{
"epoch": 1.3006833712984054,
"grad_norm": 0.3766978085041046,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 571
},
{
"epoch": 1.3029612756264237,
"grad_norm": 0.37804752588272095,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 572
},
{
"epoch": 1.3052391799544418,
"grad_norm": 0.3786337077617645,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 573
},
{
"epoch": 1.3075170842824602,
"grad_norm": 0.3882148265838623,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 574
},
{
"epoch": 1.3097949886104785,
"grad_norm": 3.220677137374878,
"learning_rate": 5e-06,
"loss": 0.0848,
"step": 575
},
{
"epoch": 1.3120728929384966,
"grad_norm": 0.5298126339912415,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 576
},
{
"epoch": 1.3143507972665147,
"grad_norm": 0.3402281701564789,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 577
},
{
"epoch": 1.316628701594533,
"grad_norm": 0.5069661140441895,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 578
},
{
"epoch": 1.3189066059225514,
"grad_norm": 0.3968346416950226,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 579
},
{
"epoch": 1.3211845102505695,
"grad_norm": 0.5330082774162292,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 580
},
{
"epoch": 1.3234624145785876,
"grad_norm": 0.4296810030937195,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 581
},
{
"epoch": 1.325740318906606,
"grad_norm": 0.39723390340805054,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 582
},
{
"epoch": 1.3280182232346243,
"grad_norm": 0.432210773229599,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 583
},
{
"epoch": 1.3302961275626424,
"grad_norm": 0.4127228558063507,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 584
},
{
"epoch": 1.3325740318906605,
"grad_norm": 0.43230441212654114,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 585
},
{
"epoch": 1.3348519362186788,
"grad_norm": 0.4305982291698456,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 586
},
{
"epoch": 1.3371298405466971,
"grad_norm": 0.3959517180919647,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 587
},
{
"epoch": 1.3394077448747153,
"grad_norm": 0.3866342306137085,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 588
},
{
"epoch": 1.3416856492027334,
"grad_norm": 0.43050622940063477,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 589
},
{
"epoch": 1.3439635535307517,
"grad_norm": 0.35574769973754883,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 590
},
{
"epoch": 1.34624145785877,
"grad_norm": 0.4432176351547241,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 591
},
{
"epoch": 1.3485193621867881,
"grad_norm": 0.3702254593372345,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 592
},
{
"epoch": 1.3507972665148062,
"grad_norm": 0.39732804894447327,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 593
},
{
"epoch": 1.3530751708428246,
"grad_norm": 0.39644646644592285,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 594
},
{
"epoch": 1.355353075170843,
"grad_norm": 0.3526952564716339,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 595
},
{
"epoch": 1.357630979498861,
"grad_norm": 0.4213428199291229,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 596
},
{
"epoch": 1.3599088838268791,
"grad_norm": 0.37950488924980164,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 597
},
{
"epoch": 1.3621867881548975,
"grad_norm": 0.42429694533348083,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 598
},
{
"epoch": 1.3644646924829158,
"grad_norm": 0.36994752287864685,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 599
},
{
"epoch": 1.366742596810934,
"grad_norm": 0.43309274315834045,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 600
},
{
"epoch": 1.3690205011389522,
"grad_norm": 0.39048635959625244,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 601
},
{
"epoch": 1.3712984054669703,
"grad_norm": 0.42135119438171387,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 602
},
{
"epoch": 1.3735763097949887,
"grad_norm": 0.36672961711883545,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 603
},
{
"epoch": 1.3758542141230068,
"grad_norm": 0.3776116371154785,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 604
},
{
"epoch": 1.3781321184510251,
"grad_norm": 0.34916606545448303,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 605
},
{
"epoch": 1.3804100227790432,
"grad_norm": 0.36569520831108093,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 606
},
{
"epoch": 1.3826879271070616,
"grad_norm": 0.3608874976634979,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 607
},
{
"epoch": 1.3849658314350797,
"grad_norm": 0.350178062915802,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 608
},
{
"epoch": 1.387243735763098,
"grad_norm": 0.37865710258483887,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 609
},
{
"epoch": 1.3895216400911161,
"grad_norm": 0.34312868118286133,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 610
},
{
"epoch": 1.3917995444191344,
"grad_norm": 0.35455793142318726,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 611
},
{
"epoch": 1.3940774487471526,
"grad_norm": 0.39417535066604614,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 612
},
{
"epoch": 1.396355353075171,
"grad_norm": 0.3636500835418701,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 613
},
{
"epoch": 1.398633257403189,
"grad_norm": 0.34348249435424805,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 614
},
{
"epoch": 1.4009111617312073,
"grad_norm": 0.3714514672756195,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 615
},
{
"epoch": 1.4031890660592254,
"grad_norm": 0.3414510488510132,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 616
},
{
"epoch": 1.4054669703872438,
"grad_norm": 0.38482949137687683,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 617
},
{
"epoch": 1.4077448747152619,
"grad_norm": 0.36240047216415405,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 618
},
{
"epoch": 1.4100227790432802,
"grad_norm": 0.39666205644607544,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 619
},
{
"epoch": 1.4123006833712983,
"grad_norm": 0.40982839465141296,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 620
},
{
"epoch": 1.4145785876993167,
"grad_norm": 0.38487517833709717,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 621
},
{
"epoch": 1.416856492027335,
"grad_norm": 0.35109570622444153,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 622
},
{
"epoch": 1.419134396355353,
"grad_norm": 0.4212898015975952,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 623
},
{
"epoch": 1.4214123006833712,
"grad_norm": 0.3583887815475464,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 624
},
{
"epoch": 1.4236902050113895,
"grad_norm": 0.4153973162174225,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 625
},
{
"epoch": 1.4259681093394079,
"grad_norm": 0.3374607264995575,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 626
},
{
"epoch": 1.428246013667426,
"grad_norm": 0.4959464371204376,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 627
},
{
"epoch": 1.430523917995444,
"grad_norm": 0.36800554394721985,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 628
},
{
"epoch": 1.4328018223234624,
"grad_norm": 0.3965972065925598,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 629
},
{
"epoch": 1.4350797266514808,
"grad_norm": 0.39917150139808655,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 630
},
{
"epoch": 1.4373576309794989,
"grad_norm": 0.41251757740974426,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 631
},
{
"epoch": 1.439635535307517,
"grad_norm": 0.43166816234588623,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 632
},
{
"epoch": 1.4419134396355353,
"grad_norm": 0.368181437253952,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 633
},
{
"epoch": 1.4441913439635536,
"grad_norm": 0.37732475996017456,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 634
},
{
"epoch": 1.4464692482915718,
"grad_norm": 0.3955388069152832,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 635
},
{
"epoch": 1.4487471526195899,
"grad_norm": 0.37553057074546814,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 636
},
{
"epoch": 1.4510250569476082,
"grad_norm": 0.43095558881759644,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 637
},
{
"epoch": 1.4533029612756265,
"grad_norm": 0.38773244619369507,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 638
},
{
"epoch": 1.4555808656036446,
"grad_norm": 0.39239251613616943,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 639
},
{
"epoch": 1.4578587699316627,
"grad_norm": 0.3327813148498535,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 640
},
{
"epoch": 1.460136674259681,
"grad_norm": 0.40319737792015076,
"learning_rate": 5e-06,
"loss": 0.069,
"step": 641
},
{
"epoch": 1.4624145785876994,
"grad_norm": 0.34045639634132385,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 642
},
{
"epoch": 1.4646924829157175,
"grad_norm": 0.3521750867366791,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 643
},
{
"epoch": 1.4669703872437356,
"grad_norm": 0.45059895515441895,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 644
},
{
"epoch": 1.469248291571754,
"grad_norm": 0.3266962468624115,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 645
},
{
"epoch": 1.4715261958997723,
"grad_norm": 0.3925187885761261,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 646
},
{
"epoch": 1.4738041002277904,
"grad_norm": 0.36219561100006104,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 647
},
{
"epoch": 1.4760820045558087,
"grad_norm": 0.4496672749519348,
"learning_rate": 5e-06,
"loss": 0.0696,
"step": 648
},
{
"epoch": 1.4783599088838268,
"grad_norm": 0.37146294116973877,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 649
},
{
"epoch": 1.4806378132118452,
"grad_norm": 0.3783736824989319,
"learning_rate": 5e-06,
"loss": 0.0695,
"step": 650
},
{
"epoch": 1.4829157175398633,
"grad_norm": 0.3593132495880127,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 651
},
{
"epoch": 1.4851936218678816,
"grad_norm": 0.3631625771522522,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 652
},
{
"epoch": 1.4874715261958997,
"grad_norm": 0.37941277027130127,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 653
},
{
"epoch": 1.489749430523918,
"grad_norm": 0.37117141485214233,
"learning_rate": 5e-06,
"loss": 0.0687,
"step": 654
},
{
"epoch": 1.4920273348519362,
"grad_norm": 0.3478919267654419,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 655
},
{
"epoch": 1.4943052391799545,
"grad_norm": 0.341808557510376,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 656
},
{
"epoch": 1.4965831435079726,
"grad_norm": 0.3450130224227905,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 657
},
{
"epoch": 1.498861047835991,
"grad_norm": 0.3433770537376404,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 658
},
{
"epoch": 1.501138952164009,
"grad_norm": 0.33789244294166565,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 659
},
{
"epoch": 1.5034168564920274,
"grad_norm": 0.36195793747901917,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 660
},
{
"epoch": 1.5056947608200457,
"grad_norm": 0.33813396096229553,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 661
},
{
"epoch": 1.5079726651480638,
"grad_norm": 0.343996524810791,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 662
},
{
"epoch": 1.510250569476082,
"grad_norm": 0.360070139169693,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 663
},
{
"epoch": 1.5125284738041003,
"grad_norm": 0.3460543751716614,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 664
},
{
"epoch": 1.5148063781321186,
"grad_norm": 0.34158506989479065,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 665
},
{
"epoch": 1.5170842824601367,
"grad_norm": 0.35960525274276733,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 666
},
{
"epoch": 1.5193621867881548,
"grad_norm": 0.4116029143333435,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 667
},
{
"epoch": 1.5216400911161732,
"grad_norm": 0.33416780829429626,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 668
},
{
"epoch": 1.5239179954441915,
"grad_norm": 0.37547293305397034,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 669
},
{
"epoch": 1.5261958997722096,
"grad_norm": 0.3883625268936157,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 670
},
{
"epoch": 1.5284738041002277,
"grad_norm": 0.394598126411438,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 671
},
{
"epoch": 1.530751708428246,
"grad_norm": 0.388380229473114,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 672
},
{
"epoch": 1.5330296127562644,
"grad_norm": 0.4153890609741211,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 673
},
{
"epoch": 1.5353075170842825,
"grad_norm": 0.33149614930152893,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 674
},
{
"epoch": 1.5375854214123006,
"grad_norm": 0.35577189922332764,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 675
},
{
"epoch": 1.539863325740319,
"grad_norm": 0.3430947959423065,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 676
},
{
"epoch": 1.5421412300683373,
"grad_norm": 0.3969891667366028,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 677
},
{
"epoch": 1.5444191343963554,
"grad_norm": 0.34465450048446655,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 678
},
{
"epoch": 1.5466970387243735,
"grad_norm": 0.4321921169757843,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 679
},
{
"epoch": 1.5489749430523918,
"grad_norm": 0.4178912937641144,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 680
},
{
"epoch": 1.5512528473804101,
"grad_norm": 0.4607953727245331,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 681
},
{
"epoch": 1.5535307517084282,
"grad_norm": 0.36263149976730347,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 682
},
{
"epoch": 1.5558086560364464,
"grad_norm": 0.4377477765083313,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 683
},
{
"epoch": 1.5580865603644647,
"grad_norm": 0.40092626214027405,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 684
},
{
"epoch": 1.560364464692483,
"grad_norm": 0.4000115990638733,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 685
},
{
"epoch": 1.5626423690205011,
"grad_norm": 0.3874872326850891,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 686
},
{
"epoch": 1.5649202733485192,
"grad_norm": 0.40038931369781494,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 687
},
{
"epoch": 1.5671981776765376,
"grad_norm": 0.39067986607551575,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 688
},
{
"epoch": 1.569476082004556,
"grad_norm": 0.4196305572986603,
"learning_rate": 5e-06,
"loss": 0.0688,
"step": 689
},
{
"epoch": 1.571753986332574,
"grad_norm": 0.36991575360298157,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 690
},
{
"epoch": 1.5740318906605921,
"grad_norm": 0.3553236424922943,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 691
},
{
"epoch": 1.5763097949886105,
"grad_norm": 0.354350209236145,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 692
},
{
"epoch": 1.5785876993166288,
"grad_norm": 0.420137494802475,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 693
},
{
"epoch": 1.580865603644647,
"grad_norm": 0.32134318351745605,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 694
},
{
"epoch": 1.583143507972665,
"grad_norm": 0.367403507232666,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 695
},
{
"epoch": 1.5854214123006833,
"grad_norm": 0.3804835081100464,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 696
},
{
"epoch": 1.5876993166287017,
"grad_norm": 0.38060566782951355,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 697
},
{
"epoch": 1.5899772209567198,
"grad_norm": 0.40258821845054626,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 698
},
{
"epoch": 1.592255125284738,
"grad_norm": 0.3835340738296509,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 699
},
{
"epoch": 1.5945330296127562,
"grad_norm": 0.3699604272842407,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 700
},
{
"epoch": 1.5968109339407746,
"grad_norm": 0.4031272828578949,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 701
},
{
"epoch": 1.5990888382687927,
"grad_norm": 0.3443854749202728,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 702
},
{
"epoch": 1.6013667425968108,
"grad_norm": 0.41966134309768677,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 703
},
{
"epoch": 1.603644646924829,
"grad_norm": 0.3769599199295044,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 704
},
{
"epoch": 1.6059225512528474,
"grad_norm": 0.40910017490386963,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 705
},
{
"epoch": 1.6082004555808656,
"grad_norm": 0.370617151260376,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 706
},
{
"epoch": 1.6104783599088837,
"grad_norm": 0.3756926655769348,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 707
},
{
"epoch": 1.6127562642369022,
"grad_norm": 0.3458310067653656,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 708
},
{
"epoch": 1.6150341685649203,
"grad_norm": 0.4030172824859619,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 709
},
{
"epoch": 1.6173120728929384,
"grad_norm": 0.32781001925468445,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 710
},
{
"epoch": 1.6195899772209568,
"grad_norm": 0.3912848234176636,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 711
},
{
"epoch": 1.621867881548975,
"grad_norm": 0.326858788728714,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 712
},
{
"epoch": 1.6241457858769932,
"grad_norm": 0.40474191308021545,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 713
},
{
"epoch": 1.6264236902050113,
"grad_norm": 0.3906795084476471,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 714
},
{
"epoch": 1.6287015945330297,
"grad_norm": 0.3630123734474182,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 715
},
{
"epoch": 1.630979498861048,
"grad_norm": 0.3990236222743988,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 716
},
{
"epoch": 1.633257403189066,
"grad_norm": 0.35970017313957214,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 717
},
{
"epoch": 1.6355353075170842,
"grad_norm": 0.4213522672653198,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 718
},
{
"epoch": 1.6378132118451025,
"grad_norm": 0.3456747829914093,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 719
},
{
"epoch": 1.6400911161731209,
"grad_norm": 0.4727102816104889,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 720
},
{
"epoch": 1.642369020501139,
"grad_norm": 0.3923806846141815,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 721
},
{
"epoch": 1.644646924829157,
"grad_norm": 0.3525092303752899,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 722
},
{
"epoch": 1.6469248291571754,
"grad_norm": 0.3721219301223755,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 723
},
{
"epoch": 1.6492027334851938,
"grad_norm": 0.3733888268470764,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 724
},
{
"epoch": 1.6514806378132119,
"grad_norm": 0.39531344175338745,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 725
},
{
"epoch": 1.65375854214123,
"grad_norm": 0.4157196879386902,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 726
},
{
"epoch": 1.6560364464692483,
"grad_norm": 0.3935493230819702,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 727
},
{
"epoch": 1.6583143507972666,
"grad_norm": 0.43975120782852173,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 728
},
{
"epoch": 1.6605922551252847,
"grad_norm": 0.40202975273132324,
"learning_rate": 5e-06,
"loss": 0.0614,
"step": 729
},
{
"epoch": 1.6628701594533029,
"grad_norm": 0.3833255171775818,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 730
},
{
"epoch": 1.6651480637813212,
"grad_norm": 0.4237973690032959,
"learning_rate": 5e-06,
"loss": 0.0694,
"step": 731
},
{
"epoch": 1.6674259681093395,
"grad_norm": 0.41160348057746887,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 732
},
{
"epoch": 1.6697038724373576,
"grad_norm": 0.4225656986236572,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 733
},
{
"epoch": 1.6719817767653757,
"grad_norm": 0.40820473432540894,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 734
},
{
"epoch": 1.674259681093394,
"grad_norm": 0.4059019982814789,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 735
},
{
"epoch": 1.6765375854214124,
"grad_norm": 0.3632740378379822,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 736
},
{
"epoch": 1.6788154897494305,
"grad_norm": 0.3080376982688904,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 737
},
{
"epoch": 1.6810933940774486,
"grad_norm": 0.36947083473205566,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 738
},
{
"epoch": 1.683371298405467,
"grad_norm": 0.3585936725139618,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 739
},
{
"epoch": 1.6856492027334853,
"grad_norm": 0.4264557957649231,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 740
},
{
"epoch": 1.6879271070615034,
"grad_norm": 0.3662192225456238,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 741
},
{
"epoch": 1.6902050113895215,
"grad_norm": 0.34586918354034424,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 742
},
{
"epoch": 1.6924829157175398,
"grad_norm": 0.3758877217769623,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 743
},
{
"epoch": 1.6947608200455582,
"grad_norm": 0.37783950567245483,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 744
},
{
"epoch": 1.6970387243735763,
"grad_norm": 0.48236802220344543,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 745
},
{
"epoch": 1.6993166287015944,
"grad_norm": 0.3640000522136688,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 746
},
{
"epoch": 1.7015945330296127,
"grad_norm": 0.3304060995578766,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 747
},
{
"epoch": 1.703872437357631,
"grad_norm": 0.42156603932380676,
"learning_rate": 5e-06,
"loss": 0.069,
"step": 748
},
{
"epoch": 1.7061503416856492,
"grad_norm": 0.4093463122844696,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 749
},
{
"epoch": 1.7084282460136673,
"grad_norm": 0.3772518038749695,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 750
},
{
"epoch": 1.7107061503416856,
"grad_norm": 0.3777291476726532,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 751
},
{
"epoch": 1.712984054669704,
"grad_norm": 0.32958298921585083,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 752
},
{
"epoch": 1.715261958997722,
"grad_norm": 0.3931344151496887,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 753
},
{
"epoch": 1.7175398633257402,
"grad_norm": 0.38946473598480225,
"learning_rate": 5e-06,
"loss": 0.0683,
"step": 754
},
{
"epoch": 1.7198177676537585,
"grad_norm": 0.38754236698150635,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 755
},
{
"epoch": 1.7220956719817768,
"grad_norm": 0.358132541179657,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 756
},
{
"epoch": 1.724373576309795,
"grad_norm": 0.3571512997150421,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 757
},
{
"epoch": 1.7266514806378133,
"grad_norm": 0.41262051463127136,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 758
},
{
"epoch": 1.7289293849658316,
"grad_norm": 0.3680334687232971,
"learning_rate": 5e-06,
"loss": 0.0686,
"step": 759
},
{
"epoch": 1.7312072892938497,
"grad_norm": 0.38827383518218994,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 760
},
{
"epoch": 1.7334851936218678,
"grad_norm": 0.36443886160850525,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 761
},
{
"epoch": 1.7357630979498861,
"grad_norm": 0.44589725136756897,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 762
},
{
"epoch": 1.7380410022779045,
"grad_norm": 0.36552733182907104,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 763
},
{
"epoch": 1.7403189066059226,
"grad_norm": 0.3776485025882721,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 764
},
{
"epoch": 1.7425968109339407,
"grad_norm": 0.4614730477333069,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 765
},
{
"epoch": 1.744874715261959,
"grad_norm": 0.3474021553993225,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 766
},
{
"epoch": 1.7471526195899774,
"grad_norm": 0.4213907718658447,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 767
},
{
"epoch": 1.7494305239179955,
"grad_norm": 0.32314637303352356,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 768
},
{
"epoch": 1.7517084282460136,
"grad_norm": 0.3781552016735077,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 769
},
{
"epoch": 1.753986332574032,
"grad_norm": 0.40325456857681274,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 770
},
{
"epoch": 1.7562642369020502,
"grad_norm": 0.394195556640625,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 771
},
{
"epoch": 1.7585421412300684,
"grad_norm": 0.35617461800575256,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 772
},
{
"epoch": 1.7608200455580865,
"grad_norm": 0.31758973002433777,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 773
},
{
"epoch": 1.7630979498861048,
"grad_norm": 0.35947299003601074,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 774
},
{
"epoch": 1.7653758542141231,
"grad_norm": 0.3657311797142029,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 775
},
{
"epoch": 1.7676537585421412,
"grad_norm": 0.471209853887558,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 776
},
{
"epoch": 1.7699316628701594,
"grad_norm": 0.40624454617500305,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 777
},
{
"epoch": 1.7722095671981777,
"grad_norm": 0.37600862979888916,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 778
},
{
"epoch": 1.774487471526196,
"grad_norm": 0.37594738602638245,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 779
},
{
"epoch": 1.7767653758542141,
"grad_norm": 0.3494108319282532,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 780
},
{
"epoch": 1.7790432801822322,
"grad_norm": 0.3323187232017517,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 781
},
{
"epoch": 1.7813211845102506,
"grad_norm": 0.3645932376384735,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 782
},
{
"epoch": 1.783599088838269,
"grad_norm": 0.4065336287021637,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 783
},
{
"epoch": 1.785876993166287,
"grad_norm": 0.38880616426467896,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 784
},
{
"epoch": 1.7881548974943051,
"grad_norm": 0.375024676322937,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 785
},
{
"epoch": 1.7904328018223234,
"grad_norm": 0.37921419739723206,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 786
},
{
"epoch": 1.7927107061503418,
"grad_norm": 0.3726096749305725,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 787
},
{
"epoch": 1.79498861047836,
"grad_norm": 0.3758138120174408,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 788
},
{
"epoch": 1.797266514806378,
"grad_norm": 0.42794129252433777,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 789
},
{
"epoch": 1.7995444191343963,
"grad_norm": 0.38579314947128296,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 790
},
{
"epoch": 1.8018223234624147,
"grad_norm": 0.3638302683830261,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 791
},
{
"epoch": 1.8041002277904328,
"grad_norm": 0.4297358989715576,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 792
},
{
"epoch": 1.8063781321184509,
"grad_norm": 0.4153372645378113,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 793
},
{
"epoch": 1.8086560364464692,
"grad_norm": 0.3808562755584717,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 794
},
{
"epoch": 1.8109339407744875,
"grad_norm": 0.4327223002910614,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 795
},
{
"epoch": 1.8132118451025057,
"grad_norm": 0.44192948937416077,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 796
},
{
"epoch": 1.8154897494305238,
"grad_norm": 0.34678900241851807,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 797
},
{
"epoch": 1.817767653758542,
"grad_norm": 0.34950852394104004,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 798
},
{
"epoch": 1.8200455580865604,
"grad_norm": 0.36530327796936035,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 799
},
{
"epoch": 1.8223234624145785,
"grad_norm": 0.3592337667942047,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 800
},
{
"epoch": 1.8246013667425967,
"grad_norm": 0.3423630893230438,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 801
},
{
"epoch": 1.826879271070615,
"grad_norm": 0.35642048716545105,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 802
},
{
"epoch": 1.8291571753986333,
"grad_norm": 0.36607348918914795,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 803
},
{
"epoch": 1.8314350797266514,
"grad_norm": 0.43585270643234253,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 804
},
{
"epoch": 1.8337129840546698,
"grad_norm": 0.3595200777053833,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 805
},
{
"epoch": 1.835990888382688,
"grad_norm": 0.39456018805503845,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 806
},
{
"epoch": 1.8382687927107062,
"grad_norm": 0.37392258644104004,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 807
},
{
"epoch": 1.8405466970387243,
"grad_norm": 0.4371819496154785,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 808
},
{
"epoch": 1.8428246013667426,
"grad_norm": 0.4336298108100891,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 809
},
{
"epoch": 1.845102505694761,
"grad_norm": 0.3856502175331116,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 810
},
{
"epoch": 1.847380410022779,
"grad_norm": 0.4522041082382202,
"learning_rate": 5e-06,
"loss": 0.0692,
"step": 811
},
{
"epoch": 1.8496583143507972,
"grad_norm": 0.3512691259384155,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 812
},
{
"epoch": 1.8519362186788155,
"grad_norm": 0.43539708852767944,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 813
},
{
"epoch": 1.8542141230068339,
"grad_norm": 0.36477357149124146,
"learning_rate": 5e-06,
"loss": 0.0681,
"step": 814
},
{
"epoch": 1.856492027334852,
"grad_norm": 0.3925856649875641,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 815
},
{
"epoch": 1.85876993166287,
"grad_norm": 0.3788635730743408,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 816
},
{
"epoch": 1.8610478359908884,
"grad_norm": 0.4003060460090637,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 817
},
{
"epoch": 1.8633257403189067,
"grad_norm": 0.35700076818466187,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 818
},
{
"epoch": 1.8656036446469249,
"grad_norm": 0.3399184048175812,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 819
},
{
"epoch": 1.867881548974943,
"grad_norm": 0.3661590814590454,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 820
},
{
"epoch": 1.8701594533029613,
"grad_norm": 0.33902713656425476,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 821
},
{
"epoch": 1.8724373576309796,
"grad_norm": 0.447002112865448,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 822
},
{
"epoch": 1.8747152619589977,
"grad_norm": 0.38841983675956726,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 823
},
{
"epoch": 1.8769931662870158,
"grad_norm": 0.46865421533584595,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 824
},
{
"epoch": 1.8792710706150342,
"grad_norm": 0.3745507597923279,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 825
},
{
"epoch": 1.8815489749430525,
"grad_norm": 0.34042197465896606,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 826
},
{
"epoch": 1.8838268792710706,
"grad_norm": 0.36797165870666504,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 827
},
{
"epoch": 1.8861047835990887,
"grad_norm": 0.39723649621009827,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 828
},
{
"epoch": 1.888382687927107,
"grad_norm": 0.3646100163459778,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 829
},
{
"epoch": 1.8906605922551254,
"grad_norm": 0.35160142183303833,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 830
},
{
"epoch": 1.8929384965831435,
"grad_norm": 0.3282979130744934,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 831
},
{
"epoch": 1.8952164009111616,
"grad_norm": 0.33924567699432373,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 832
},
{
"epoch": 1.89749430523918,
"grad_norm": 0.34475693106651306,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 833
},
{
"epoch": 1.8997722095671983,
"grad_norm": 0.38452866673469543,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 834
},
{
"epoch": 1.9020501138952164,
"grad_norm": 0.36789998412132263,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 835
},
{
"epoch": 1.9043280182232345,
"grad_norm": 0.34242087602615356,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 836
},
{
"epoch": 1.9066059225512528,
"grad_norm": 0.33219853043556213,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 837
},
{
"epoch": 1.9088838268792712,
"grad_norm": 0.3524526059627533,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 838
},
{
"epoch": 1.9111617312072893,
"grad_norm": 0.3499576449394226,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 839
},
{
"epoch": 1.9134396355353074,
"grad_norm": 0.41930925846099854,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 840
},
{
"epoch": 1.9157175398633257,
"grad_norm": 0.36949628591537476,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 841
},
{
"epoch": 1.917995444191344,
"grad_norm": 0.354651540517807,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 842
},
{
"epoch": 1.9202733485193622,
"grad_norm": 0.37935441732406616,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 843
},
{
"epoch": 1.9225512528473803,
"grad_norm": 0.43017083406448364,
"learning_rate": 5e-06,
"loss": 0.0678,
"step": 844
},
{
"epoch": 1.9248291571753986,
"grad_norm": 0.37563037872314453,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 845
},
{
"epoch": 1.927107061503417,
"grad_norm": 0.3513509929180145,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 846
},
{
"epoch": 1.929384965831435,
"grad_norm": 0.3746267855167389,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 847
},
{
"epoch": 1.9316628701594531,
"grad_norm": 0.4095878303050995,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 848
},
{
"epoch": 1.9339407744874715,
"grad_norm": 0.4189017713069916,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 849
},
{
"epoch": 1.9362186788154898,
"grad_norm": 0.37285467982292175,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 850
},
{
"epoch": 1.938496583143508,
"grad_norm": 0.4462735950946808,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 851
},
{
"epoch": 1.940774487471526,
"grad_norm": 0.41118356585502625,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 852
},
{
"epoch": 1.9430523917995444,
"grad_norm": 0.3878600597381592,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 853
},
{
"epoch": 1.9453302961275627,
"grad_norm": 0.40632522106170654,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 854
},
{
"epoch": 1.9476082004555808,
"grad_norm": 0.35835206508636475,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 855
},
{
"epoch": 1.9498861047835991,
"grad_norm": 0.3729773163795471,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 856
},
{
"epoch": 1.9521640091116175,
"grad_norm": 0.32670673727989197,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 857
},
{
"epoch": 1.9544419134396356,
"grad_norm": 0.32948240637779236,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 858
},
{
"epoch": 1.9567198177676537,
"grad_norm": 0.30624064803123474,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 859
},
{
"epoch": 1.958997722095672,
"grad_norm": 0.32112807035446167,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 860
},
{
"epoch": 1.9612756264236904,
"grad_norm": 0.3518359959125519,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 861
},
{
"epoch": 1.9635535307517085,
"grad_norm": 0.3307065963745117,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 862
},
{
"epoch": 1.9658314350797266,
"grad_norm": 0.42508912086486816,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 863
},
{
"epoch": 1.968109339407745,
"grad_norm": 0.32008594274520874,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 864
},
{
"epoch": 1.9703872437357632,
"grad_norm": 0.36606013774871826,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 865
},
{
"epoch": 1.9726651480637813,
"grad_norm": 0.347261905670166,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 866
},
{
"epoch": 1.9749430523917995,
"grad_norm": 0.32424452900886536,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 867
},
{
"epoch": 1.9772209567198178,
"grad_norm": 0.3837982714176178,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 868
},
{
"epoch": 1.9794988610478361,
"grad_norm": 0.38964781165122986,
"learning_rate": 5e-06,
"loss": 0.061,
"step": 869
},
{
"epoch": 1.9817767653758542,
"grad_norm": 0.3276178538799286,
"learning_rate": 5e-06,
"loss": 0.0673,
"step": 870
},
{
"epoch": 1.9840546697038723,
"grad_norm": 0.35975369811058044,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 871
},
{
"epoch": 1.9863325740318907,
"grad_norm": 0.3330411911010742,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 872
},
{
"epoch": 1.988610478359909,
"grad_norm": 0.33740854263305664,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 873
},
{
"epoch": 1.9908883826879271,
"grad_norm": 0.3705332577228546,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 874
},
{
"epoch": 1.9931662870159452,
"grad_norm": 0.3322344720363617,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 875
},
{
"epoch": 1.9954441913439636,
"grad_norm": 0.37892571091651917,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 876
},
{
"epoch": 1.997722095671982,
"grad_norm": 0.4094819724559784,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 877
},
{
"epoch": 2.0,
"grad_norm": 0.3718055188655853,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 878
},
{
"epoch": 2.002277904328018,
"grad_norm": 0.4386118948459625,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 879
},
{
"epoch": 2.0045558086560367,
"grad_norm": 0.3467435836791992,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 880
},
{
"epoch": 2.0068337129840548,
"grad_norm": 0.3573801517486572,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 881
},
{
"epoch": 2.009111617312073,
"grad_norm": 0.36609163880348206,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 882
},
{
"epoch": 2.011389521640091,
"grad_norm": 0.36750468611717224,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 883
},
{
"epoch": 2.0136674259681095,
"grad_norm": 0.3811657726764679,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 884
},
{
"epoch": 2.0159453302961277,
"grad_norm": 0.38328248262405396,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 885
},
{
"epoch": 2.0182232346241458,
"grad_norm": 0.35302114486694336,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 886
},
{
"epoch": 2.020501138952164,
"grad_norm": 0.35229402780532837,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 887
},
{
"epoch": 2.0227790432801824,
"grad_norm": 0.4118206202983856,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 888
},
{
"epoch": 2.0250569476082005,
"grad_norm": 0.35905227065086365,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 889
},
{
"epoch": 2.0273348519362187,
"grad_norm": 0.3849807381629944,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 890
},
{
"epoch": 2.0296127562642368,
"grad_norm": 0.38305532932281494,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 891
},
{
"epoch": 2.0318906605922553,
"grad_norm": 0.3660757839679718,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 892
},
{
"epoch": 2.0341685649202734,
"grad_norm": 0.37978801131248474,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 893
},
{
"epoch": 2.0364464692482915,
"grad_norm": 0.3686749041080475,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 894
},
{
"epoch": 2.0387243735763096,
"grad_norm": 0.3721759617328644,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 895
},
{
"epoch": 2.041002277904328,
"grad_norm": 0.4217437207698822,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 896
},
{
"epoch": 2.0432801822323463,
"grad_norm": 0.37084710597991943,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 897
},
{
"epoch": 2.0455580865603644,
"grad_norm": 0.3468475341796875,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 898
},
{
"epoch": 2.0478359908883825,
"grad_norm": 0.3841940462589264,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 899
},
{
"epoch": 2.050113895216401,
"grad_norm": 0.4270191192626953,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 900
},
{
"epoch": 2.052391799544419,
"grad_norm": 0.3628332316875458,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 901
},
{
"epoch": 2.0546697038724373,
"grad_norm": 0.4229717254638672,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 902
},
{
"epoch": 2.0569476082004554,
"grad_norm": 0.37091630697250366,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 903
},
{
"epoch": 2.059225512528474,
"grad_norm": 0.3613353669643402,
"learning_rate": 5e-06,
"loss": 0.0682,
"step": 904
},
{
"epoch": 2.061503416856492,
"grad_norm": 0.4177112281322479,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 905
},
{
"epoch": 2.06378132118451,
"grad_norm": 0.3757723271846771,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 906
},
{
"epoch": 2.0660592255125283,
"grad_norm": 0.4058937430381775,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 907
},
{
"epoch": 2.068337129840547,
"grad_norm": 0.3449467420578003,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 908
},
{
"epoch": 2.070615034168565,
"grad_norm": 0.39998921751976013,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 909
},
{
"epoch": 2.072892938496583,
"grad_norm": 0.3876377046108246,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 910
},
{
"epoch": 2.075170842824601,
"grad_norm": 0.38587743043899536,
"learning_rate": 5e-06,
"loss": 0.0614,
"step": 911
},
{
"epoch": 2.0774487471526197,
"grad_norm": 0.38243022561073303,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 912
},
{
"epoch": 2.079726651480638,
"grad_norm": 0.37763819098472595,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 913
},
{
"epoch": 2.082004555808656,
"grad_norm": 0.39426735043525696,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 914
},
{
"epoch": 2.084282460136674,
"grad_norm": 0.4097016453742981,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 915
},
{
"epoch": 2.0865603644646926,
"grad_norm": 0.31911271810531616,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 916
},
{
"epoch": 2.0888382687927107,
"grad_norm": 0.37096673250198364,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 917
},
{
"epoch": 2.091116173120729,
"grad_norm": 0.37522169947624207,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 918
},
{
"epoch": 2.093394077448747,
"grad_norm": 0.35180211067199707,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 919
},
{
"epoch": 2.0956719817767655,
"grad_norm": 0.3494492173194885,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 920
},
{
"epoch": 2.0979498861047836,
"grad_norm": 0.38248974084854126,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 921
},
{
"epoch": 2.1002277904328017,
"grad_norm": 0.3548568785190582,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 922
},
{
"epoch": 2.10250569476082,
"grad_norm": 0.34141600131988525,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 923
},
{
"epoch": 2.1047835990888384,
"grad_norm": 0.43948766589164734,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 924
},
{
"epoch": 2.1070615034168565,
"grad_norm": 0.370527446269989,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 925
},
{
"epoch": 2.1093394077448746,
"grad_norm": 0.44553908705711365,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 926
},
{
"epoch": 2.1116173120728927,
"grad_norm": 0.4327397346496582,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 927
},
{
"epoch": 2.1138952164009113,
"grad_norm": 0.42272982001304626,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 928
},
{
"epoch": 2.1161731207289294,
"grad_norm": 0.4232465326786041,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 929
},
{
"epoch": 2.1184510250569475,
"grad_norm": 0.40464767813682556,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 930
},
{
"epoch": 2.120728929384966,
"grad_norm": 0.39294788241386414,
"learning_rate": 5e-06,
"loss": 0.062,
"step": 931
},
{
"epoch": 2.123006833712984,
"grad_norm": 0.3918789029121399,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 932
},
{
"epoch": 2.1252847380410023,
"grad_norm": 0.47361522912979126,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 933
},
{
"epoch": 2.1275626423690204,
"grad_norm": 0.3954993784427643,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 934
},
{
"epoch": 2.129840546697039,
"grad_norm": 0.4152219295501709,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 935
},
{
"epoch": 2.132118451025057,
"grad_norm": 0.42703163623809814,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 936
},
{
"epoch": 2.134396355353075,
"grad_norm": 0.3991785943508148,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 937
},
{
"epoch": 2.1366742596810933,
"grad_norm": 0.4113765060901642,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 938
},
{
"epoch": 2.138952164009112,
"grad_norm": 0.348736047744751,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 939
},
{
"epoch": 2.14123006833713,
"grad_norm": 0.34686192870140076,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 940
},
{
"epoch": 2.143507972665148,
"grad_norm": 0.4006514251232147,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 941
},
{
"epoch": 2.145785876993166,
"grad_norm": 0.360848605632782,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 942
},
{
"epoch": 2.1480637813211847,
"grad_norm": 0.39627739787101746,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 943
},
{
"epoch": 2.150341685649203,
"grad_norm": 0.3971979320049286,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 944
},
{
"epoch": 2.152619589977221,
"grad_norm": 0.3891604542732239,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 945
},
{
"epoch": 2.154897494305239,
"grad_norm": 0.42411237955093384,
"learning_rate": 5e-06,
"loss": 0.0609,
"step": 946
},
{
"epoch": 2.1571753986332576,
"grad_norm": 0.32573559880256653,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 947
},
{
"epoch": 2.1594533029612757,
"grad_norm": 0.46468672156333923,
"learning_rate": 5e-06,
"loss": 0.0616,
"step": 948
},
{
"epoch": 2.161731207289294,
"grad_norm": 0.3554407060146332,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 949
},
{
"epoch": 2.164009111617312,
"grad_norm": 0.4320879280567169,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 950
},
{
"epoch": 2.1662870159453305,
"grad_norm": 0.347248911857605,
"learning_rate": 5e-06,
"loss": 0.0614,
"step": 951
},
{
"epoch": 2.1685649202733486,
"grad_norm": 0.36107945442199707,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 952
},
{
"epoch": 2.1708428246013667,
"grad_norm": 0.33618679642677307,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 953
},
{
"epoch": 2.173120728929385,
"grad_norm": 0.359061598777771,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 954
},
{
"epoch": 2.1753986332574033,
"grad_norm": 0.3282698094844818,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 955
},
{
"epoch": 2.1776765375854215,
"grad_norm": 0.3779278099536896,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 956
},
{
"epoch": 2.1799544419134396,
"grad_norm": 0.35100382566452026,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 957
},
{
"epoch": 2.1822323462414577,
"grad_norm": 0.41122227907180786,
"learning_rate": 5e-06,
"loss": 0.0612,
"step": 958
},
{
"epoch": 2.1845102505694762,
"grad_norm": 0.31362035870552063,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 959
},
{
"epoch": 2.1867881548974943,
"grad_norm": 0.32592323422431946,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 960
},
{
"epoch": 2.1890660592255125,
"grad_norm": 0.3565470278263092,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 961
},
{
"epoch": 2.1913439635535306,
"grad_norm": 0.33629193902015686,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 962
},
{
"epoch": 2.193621867881549,
"grad_norm": 0.32078197598457336,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 963
},
{
"epoch": 2.1958997722095672,
"grad_norm": 0.3121110200881958,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 964
},
{
"epoch": 2.1981776765375853,
"grad_norm": 0.35310298204421997,
"learning_rate": 5e-06,
"loss": 0.061,
"step": 965
},
{
"epoch": 2.2004555808656034,
"grad_norm": 0.3640041649341583,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 966
},
{
"epoch": 2.202733485193622,
"grad_norm": 0.3210286498069763,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 967
},
{
"epoch": 2.20501138952164,
"grad_norm": 0.4181840419769287,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 968
},
{
"epoch": 2.207289293849658,
"grad_norm": 0.3561514616012573,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 969
},
{
"epoch": 2.2095671981776768,
"grad_norm": 0.3986862599849701,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 970
},
{
"epoch": 2.211845102505695,
"grad_norm": 0.349417507648468,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 971
},
{
"epoch": 2.214123006833713,
"grad_norm": 0.37399938702583313,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 972
},
{
"epoch": 2.216400911161731,
"grad_norm": 0.3361985385417938,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 973
},
{
"epoch": 2.218678815489749,
"grad_norm": 0.359173059463501,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 974
},
{
"epoch": 2.2209567198177678,
"grad_norm": 0.3447031080722809,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 975
},
{
"epoch": 2.223234624145786,
"grad_norm": 0.3254874050617218,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 976
},
{
"epoch": 2.225512528473804,
"grad_norm": 0.3558181822299957,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 977
},
{
"epoch": 2.2277904328018225,
"grad_norm": 0.37203213572502136,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 978
},
{
"epoch": 2.2300683371298406,
"grad_norm": 0.4200899600982666,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 979
},
{
"epoch": 2.2323462414578588,
"grad_norm": 0.3482038080692291,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 980
},
{
"epoch": 2.234624145785877,
"grad_norm": 0.38406234979629517,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 981
},
{
"epoch": 2.2369020501138954,
"grad_norm": 0.3911779820919037,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 982
},
{
"epoch": 2.2391799544419135,
"grad_norm": 0.3870941698551178,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 983
},
{
"epoch": 2.2414578587699316,
"grad_norm": 0.426997572183609,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 984
},
{
"epoch": 2.2437357630979498,
"grad_norm": 0.3327006697654724,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 985
},
{
"epoch": 2.2460136674259683,
"grad_norm": 0.40405985713005066,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 986
},
{
"epoch": 2.2482915717539864,
"grad_norm": 0.3728192448616028,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 987
},
{
"epoch": 2.2505694760820045,
"grad_norm": 0.447054922580719,
"learning_rate": 5e-06,
"loss": 0.0679,
"step": 988
},
{
"epoch": 2.2528473804100226,
"grad_norm": 0.4169905483722687,
"learning_rate": 5e-06,
"loss": 0.0675,
"step": 989
},
{
"epoch": 2.255125284738041,
"grad_norm": 0.4643232524394989,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 990
},
{
"epoch": 2.2574031890660593,
"grad_norm": 0.370007187128067,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 991
},
{
"epoch": 2.2596810933940774,
"grad_norm": 0.5323000550270081,
"learning_rate": 5e-06,
"loss": 0.068,
"step": 992
},
{
"epoch": 2.2619589977220955,
"grad_norm": 0.41063234210014343,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 993
},
{
"epoch": 2.264236902050114,
"grad_norm": 0.4756401777267456,
"learning_rate": 5e-06,
"loss": 0.0615,
"step": 994
},
{
"epoch": 2.266514806378132,
"grad_norm": 0.47712597250938416,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 995
},
{
"epoch": 2.2687927107061503,
"grad_norm": 0.43546780943870544,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 996
},
{
"epoch": 2.2710706150341684,
"grad_norm": 0.4730824828147888,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 997
},
{
"epoch": 2.273348519362187,
"grad_norm": 0.3857640027999878,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 998
},
{
"epoch": 2.275626423690205,
"grad_norm": 0.48187997937202454,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 999
},
{
"epoch": 2.277904328018223,
"grad_norm": 0.41435930132865906,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1000
},
{
"epoch": 2.2801822323462413,
"grad_norm": 0.4311675727367401,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1001
},
{
"epoch": 2.28246013667426,
"grad_norm": 0.3588732182979584,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1002
},
{
"epoch": 2.284738041002278,
"grad_norm": 0.39682042598724365,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1003
},
{
"epoch": 2.287015945330296,
"grad_norm": 0.32970863580703735,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1004
},
{
"epoch": 2.289293849658314,
"grad_norm": 0.41080474853515625,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 1005
},
{
"epoch": 2.2915717539863327,
"grad_norm": 0.3642153739929199,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1006
},
{
"epoch": 2.293849658314351,
"grad_norm": 0.3400186002254486,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 1007
},
{
"epoch": 2.296127562642369,
"grad_norm": 0.36358851194381714,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1008
},
{
"epoch": 2.298405466970387,
"grad_norm": 0.3627476990222931,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1009
},
{
"epoch": 2.3006833712984056,
"grad_norm": 0.33303695917129517,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 1010
},
{
"epoch": 2.3029612756264237,
"grad_norm": 0.3159809112548828,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1011
},
{
"epoch": 2.305239179954442,
"grad_norm": 0.3029627203941345,
"learning_rate": 5e-06,
"loss": 0.0615,
"step": 1012
},
{
"epoch": 2.30751708428246,
"grad_norm": 0.33818596601486206,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1013
},
{
"epoch": 2.3097949886104785,
"grad_norm": 0.3519606292247772,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1014
},
{
"epoch": 2.3120728929384966,
"grad_norm": 0.3234321177005768,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1015
},
{
"epoch": 2.3143507972665147,
"grad_norm": 0.3304242193698883,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1016
},
{
"epoch": 2.3166287015945333,
"grad_norm": 0.3527721166610718,
"learning_rate": 5e-06,
"loss": 0.0617,
"step": 1017
},
{
"epoch": 2.3189066059225514,
"grad_norm": 0.32102298736572266,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1018
},
{
"epoch": 2.3211845102505695,
"grad_norm": 0.3999481797218323,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 1019
},
{
"epoch": 2.3234624145785876,
"grad_norm": 0.3413870632648468,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 1020
},
{
"epoch": 2.3257403189066057,
"grad_norm": 0.3446578085422516,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1021
},
{
"epoch": 2.3280182232346243,
"grad_norm": 0.3409595489501953,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1022
},
{
"epoch": 2.3302961275626424,
"grad_norm": 0.38335004448890686,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1023
},
{
"epoch": 2.3325740318906605,
"grad_norm": 0.34537696838378906,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 1024
},
{
"epoch": 2.334851936218679,
"grad_norm": 0.35324957966804504,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 1025
},
{
"epoch": 2.337129840546697,
"grad_norm": 0.3460294306278229,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1026
},
{
"epoch": 2.3394077448747153,
"grad_norm": 0.3597829341888428,
"learning_rate": 5e-06,
"loss": 0.0613,
"step": 1027
},
{
"epoch": 2.3416856492027334,
"grad_norm": 0.34790682792663574,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1028
},
{
"epoch": 2.3439635535307515,
"grad_norm": 0.372488796710968,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1029
},
{
"epoch": 2.34624145785877,
"grad_norm": 0.3652331233024597,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 1030
},
{
"epoch": 2.348519362186788,
"grad_norm": 0.35086071491241455,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 1031
},
{
"epoch": 2.3507972665148062,
"grad_norm": 0.3590526282787323,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1032
},
{
"epoch": 2.353075170842825,
"grad_norm": 0.3077162504196167,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1033
},
{
"epoch": 2.355353075170843,
"grad_norm": 0.36362966895103455,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1034
},
{
"epoch": 2.357630979498861,
"grad_norm": 0.35024797916412354,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1035
},
{
"epoch": 2.359908883826879,
"grad_norm": 0.35729578137397766,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1036
},
{
"epoch": 2.3621867881548977,
"grad_norm": 0.3868909776210785,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1037
},
{
"epoch": 2.364464692482916,
"grad_norm": 0.3617287874221802,
"learning_rate": 5e-06,
"loss": 0.0685,
"step": 1038
},
{
"epoch": 2.366742596810934,
"grad_norm": 0.40562912821769714,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1039
},
{
"epoch": 2.369020501138952,
"grad_norm": 0.3510848581790924,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 1040
},
{
"epoch": 2.3712984054669706,
"grad_norm": 0.42867493629455566,
"learning_rate": 5e-06,
"loss": 0.0604,
"step": 1041
},
{
"epoch": 2.3735763097949887,
"grad_norm": 0.35482341051101685,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 1042
},
{
"epoch": 2.375854214123007,
"grad_norm": 0.42982247471809387,
"learning_rate": 5e-06,
"loss": 0.0633,
"step": 1043
},
{
"epoch": 2.378132118451025,
"grad_norm": 0.41004472970962524,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1044
},
{
"epoch": 2.3804100227790435,
"grad_norm": 0.37374380230903625,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 1045
},
{
"epoch": 2.3826879271070616,
"grad_norm": 0.40902790427207947,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1046
},
{
"epoch": 2.3849658314350797,
"grad_norm": 0.3632076680660248,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 1047
},
{
"epoch": 2.387243735763098,
"grad_norm": 0.34351205825805664,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 1048
},
{
"epoch": 2.3895216400911163,
"grad_norm": 0.38355907797813416,
"learning_rate": 5e-06,
"loss": 0.0611,
"step": 1049
},
{
"epoch": 2.3917995444191344,
"grad_norm": 0.33864936232566833,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 1050
},
{
"epoch": 2.3940774487471526,
"grad_norm": 0.42707204818725586,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1051
},
{
"epoch": 2.3963553530751707,
"grad_norm": 0.35341501235961914,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1052
},
{
"epoch": 2.3986332574031892,
"grad_norm": 0.4059014618396759,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1053
},
{
"epoch": 2.4009111617312073,
"grad_norm": 0.3321845233440399,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1054
},
{
"epoch": 2.4031890660592254,
"grad_norm": 0.4802558422088623,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 1055
},
{
"epoch": 2.4054669703872436,
"grad_norm": 0.37992075085639954,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1056
},
{
"epoch": 2.407744874715262,
"grad_norm": 0.4289088249206543,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1057
},
{
"epoch": 2.41002277904328,
"grad_norm": 0.3717344403266907,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1058
},
{
"epoch": 2.4123006833712983,
"grad_norm": 0.3617473840713501,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 1059
},
{
"epoch": 2.4145785876993164,
"grad_norm": 0.3671506643295288,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1060
},
{
"epoch": 2.416856492027335,
"grad_norm": 0.3733121156692505,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1061
},
{
"epoch": 2.419134396355353,
"grad_norm": 0.3563171625137329,
"learning_rate": 5e-06,
"loss": 0.0667,
"step": 1062
},
{
"epoch": 2.421412300683371,
"grad_norm": 0.41789793968200684,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1063
},
{
"epoch": 2.4236902050113898,
"grad_norm": 0.3826461732387543,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1064
},
{
"epoch": 2.425968109339408,
"grad_norm": 0.38771623373031616,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1065
},
{
"epoch": 2.428246013667426,
"grad_norm": 0.34157484769821167,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1066
},
{
"epoch": 2.430523917995444,
"grad_norm": 0.3616361916065216,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 1067
},
{
"epoch": 2.432801822323462,
"grad_norm": 0.3935610353946686,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1068
},
{
"epoch": 2.4350797266514808,
"grad_norm": 0.38885191082954407,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 1069
},
{
"epoch": 2.437357630979499,
"grad_norm": 0.36633971333503723,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1070
},
{
"epoch": 2.439635535307517,
"grad_norm": 0.39490458369255066,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1071
},
{
"epoch": 2.4419134396355355,
"grad_norm": 0.3240135908126831,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1072
},
{
"epoch": 2.4441913439635536,
"grad_norm": 0.3697579503059387,
"learning_rate": 5e-06,
"loss": 0.0604,
"step": 1073
},
{
"epoch": 2.4464692482915718,
"grad_norm": 0.4132577180862427,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 1074
},
{
"epoch": 2.44874715261959,
"grad_norm": 0.39057809114456177,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1075
},
{
"epoch": 2.451025056947608,
"grad_norm": 0.3658410310745239,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1076
},
{
"epoch": 2.4533029612756265,
"grad_norm": 0.4368787109851837,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1077
},
{
"epoch": 2.4555808656036446,
"grad_norm": 0.3769480586051941,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1078
},
{
"epoch": 2.4578587699316627,
"grad_norm": 0.3672235906124115,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 1079
},
{
"epoch": 2.4601366742596813,
"grad_norm": 0.39357760548591614,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1080
},
{
"epoch": 2.4624145785876994,
"grad_norm": 0.37806954979896545,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 1081
},
{
"epoch": 2.4646924829157175,
"grad_norm": 0.35902294516563416,
"learning_rate": 5e-06,
"loss": 0.0668,
"step": 1082
},
{
"epoch": 2.4669703872437356,
"grad_norm": 0.3983694314956665,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1083
},
{
"epoch": 2.4692482915717537,
"grad_norm": 0.3836486041545868,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 1084
},
{
"epoch": 2.4715261958997723,
"grad_norm": 0.3957916796207428,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 1085
},
{
"epoch": 2.4738041002277904,
"grad_norm": 0.39857879281044006,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1086
},
{
"epoch": 2.4760820045558085,
"grad_norm": 0.4524567425251007,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1087
},
{
"epoch": 2.478359908883827,
"grad_norm": 0.35638338327407837,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1088
},
{
"epoch": 2.480637813211845,
"grad_norm": 0.4003960192203522,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1089
},
{
"epoch": 2.4829157175398633,
"grad_norm": 0.3599901497364044,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1090
},
{
"epoch": 2.4851936218678814,
"grad_norm": 0.3281540870666504,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 1091
},
{
"epoch": 2.4874715261959,
"grad_norm": 0.3587161600589752,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1092
},
{
"epoch": 2.489749430523918,
"grad_norm": 0.32150331139564514,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1093
},
{
"epoch": 2.492027334851936,
"grad_norm": 0.38395655155181885,
"learning_rate": 5e-06,
"loss": 0.0671,
"step": 1094
},
{
"epoch": 2.4943052391799543,
"grad_norm": 0.3485938608646393,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 1095
},
{
"epoch": 2.496583143507973,
"grad_norm": 0.34448081254959106,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1096
},
{
"epoch": 2.498861047835991,
"grad_norm": 0.3400004804134369,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1097
},
{
"epoch": 2.501138952164009,
"grad_norm": 0.3427201211452484,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1098
},
{
"epoch": 2.503416856492027,
"grad_norm": 0.3488285541534424,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1099
},
{
"epoch": 2.5056947608200457,
"grad_norm": 0.3434089422225952,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1100
},
{
"epoch": 2.507972665148064,
"grad_norm": 0.33915603160858154,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1101
},
{
"epoch": 2.510250569476082,
"grad_norm": 0.33430543541908264,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1102
},
{
"epoch": 2.5125284738041005,
"grad_norm": 0.4376661777496338,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1103
},
{
"epoch": 2.5148063781321186,
"grad_norm": 0.3509063422679901,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1104
},
{
"epoch": 2.5170842824601367,
"grad_norm": 0.4079601466655731,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1105
},
{
"epoch": 2.519362186788155,
"grad_norm": 0.36879250407218933,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 1106
},
{
"epoch": 2.521640091116173,
"grad_norm": 0.4270707964897156,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1107
},
{
"epoch": 2.5239179954441915,
"grad_norm": 0.3785046637058258,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1108
},
{
"epoch": 2.5261958997722096,
"grad_norm": 0.37609314918518066,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 1109
},
{
"epoch": 2.5284738041002277,
"grad_norm": 0.40449628233909607,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1110
},
{
"epoch": 2.5307517084282463,
"grad_norm": 0.33656638860702515,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 1111
},
{
"epoch": 2.5330296127562644,
"grad_norm": 0.34896692633628845,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1112
},
{
"epoch": 2.5353075170842825,
"grad_norm": 0.3910132050514221,
"learning_rate": 5e-06,
"loss": 0.0676,
"step": 1113
},
{
"epoch": 2.5375854214123006,
"grad_norm": 0.4085399806499481,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1114
},
{
"epoch": 2.5398633257403187,
"grad_norm": 0.40095609426498413,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1115
},
{
"epoch": 2.5421412300683373,
"grad_norm": 0.388229101896286,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1116
},
{
"epoch": 2.5444191343963554,
"grad_norm": 0.33334848284721375,
"learning_rate": 5e-06,
"loss": 0.0619,
"step": 1117
},
{
"epoch": 2.5466970387243735,
"grad_norm": 0.3782349228858948,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1118
},
{
"epoch": 2.548974943052392,
"grad_norm": 0.34723809361457825,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 1119
},
{
"epoch": 2.55125284738041,
"grad_norm": 0.3522922992706299,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 1120
},
{
"epoch": 2.5535307517084282,
"grad_norm": 0.3559888005256653,
"learning_rate": 5e-06,
"loss": 0.0674,
"step": 1121
},
{
"epoch": 2.5558086560364464,
"grad_norm": 0.3526102602481842,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 1122
},
{
"epoch": 2.5580865603644645,
"grad_norm": 0.3434252142906189,
"learning_rate": 5e-06,
"loss": 0.0662,
"step": 1123
},
{
"epoch": 2.560364464692483,
"grad_norm": 0.3523869216442108,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1124
},
{
"epoch": 2.562642369020501,
"grad_norm": 0.3304862380027771,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1125
},
{
"epoch": 2.5649202733485192,
"grad_norm": 0.3856379985809326,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1126
},
{
"epoch": 2.567198177676538,
"grad_norm": 0.35280197858810425,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1127
},
{
"epoch": 2.569476082004556,
"grad_norm": 0.3772255480289459,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1128
},
{
"epoch": 2.571753986332574,
"grad_norm": 0.3618199825286865,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 1129
},
{
"epoch": 2.574031890660592,
"grad_norm": 0.40705057978630066,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 1130
},
{
"epoch": 2.5763097949886102,
"grad_norm": 0.3558051288127899,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1131
},
{
"epoch": 2.578587699316629,
"grad_norm": 0.34395596385002136,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 1132
},
{
"epoch": 2.580865603644647,
"grad_norm": 0.36210745573043823,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1133
},
{
"epoch": 2.583143507972665,
"grad_norm": 0.3228192627429962,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 1134
},
{
"epoch": 2.5854214123006836,
"grad_norm": 0.42203786969184875,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1135
},
{
"epoch": 2.5876993166287017,
"grad_norm": 0.3415069878101349,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1136
},
{
"epoch": 2.58997722095672,
"grad_norm": 0.42018458247184753,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1137
},
{
"epoch": 2.592255125284738,
"grad_norm": 0.3087046444416046,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1138
},
{
"epoch": 2.594533029612756,
"grad_norm": 0.44265905022621155,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1139
},
{
"epoch": 2.5968109339407746,
"grad_norm": 0.40397506952285767,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1140
},
{
"epoch": 2.5990888382687927,
"grad_norm": 0.37356775999069214,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1141
},
{
"epoch": 2.6013667425968108,
"grad_norm": 0.36775606870651245,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 1142
},
{
"epoch": 2.6036446469248293,
"grad_norm": 0.369292289018631,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 1143
},
{
"epoch": 2.6059225512528474,
"grad_norm": 0.36045145988464355,
"learning_rate": 5e-06,
"loss": 0.0669,
"step": 1144
},
{
"epoch": 2.6082004555808656,
"grad_norm": 0.328274667263031,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 1145
},
{
"epoch": 2.6104783599088837,
"grad_norm": 0.38536250591278076,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1146
},
{
"epoch": 2.612756264236902,
"grad_norm": 0.36271294951438904,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 1147
},
{
"epoch": 2.6150341685649203,
"grad_norm": 0.3569026589393616,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1148
},
{
"epoch": 2.6173120728929384,
"grad_norm": 0.36661359667778015,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 1149
},
{
"epoch": 2.619589977220957,
"grad_norm": 0.357048362493515,
"learning_rate": 5e-06,
"loss": 0.0617,
"step": 1150
},
{
"epoch": 2.621867881548975,
"grad_norm": 0.3479042649269104,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 1151
},
{
"epoch": 2.624145785876993,
"grad_norm": 0.37682074308395386,
"learning_rate": 5e-06,
"loss": 0.0672,
"step": 1152
},
{
"epoch": 2.6264236902050113,
"grad_norm": 0.3442467749118805,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 1153
},
{
"epoch": 2.6287015945330294,
"grad_norm": 0.350748747587204,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1154
},
{
"epoch": 2.630979498861048,
"grad_norm": 0.3581165671348572,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1155
},
{
"epoch": 2.633257403189066,
"grad_norm": 0.35141557455062866,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1156
},
{
"epoch": 2.635535307517084,
"grad_norm": 0.3422101140022278,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1157
},
{
"epoch": 2.6378132118451028,
"grad_norm": 0.32578712701797485,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1158
},
{
"epoch": 2.640091116173121,
"grad_norm": 0.3447733223438263,
"learning_rate": 5e-06,
"loss": 0.0647,
"step": 1159
},
{
"epoch": 2.642369020501139,
"grad_norm": 0.31952229142189026,
"learning_rate": 5e-06,
"loss": 0.0608,
"step": 1160
},
{
"epoch": 2.644646924829157,
"grad_norm": 0.3545774519443512,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1161
},
{
"epoch": 2.646924829157175,
"grad_norm": 0.306447833776474,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1162
},
{
"epoch": 2.6492027334851938,
"grad_norm": 0.3436081111431122,
"learning_rate": 5e-06,
"loss": 0.0631,
"step": 1163
},
{
"epoch": 2.651480637813212,
"grad_norm": 0.3364735543727875,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1164
},
{
"epoch": 2.65375854214123,
"grad_norm": 0.36356112360954285,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1165
},
{
"epoch": 2.6560364464692485,
"grad_norm": 0.318620890378952,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1166
},
{
"epoch": 2.6583143507972666,
"grad_norm": 0.3614048957824707,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1167
},
{
"epoch": 2.6605922551252847,
"grad_norm": 0.3666227459907532,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1168
},
{
"epoch": 2.662870159453303,
"grad_norm": 0.35970601439476013,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1169
},
{
"epoch": 2.665148063781321,
"grad_norm": 0.3734301030635834,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1170
},
{
"epoch": 2.6674259681093395,
"grad_norm": 0.361607164144516,
"learning_rate": 5e-06,
"loss": 0.066,
"step": 1171
},
{
"epoch": 2.6697038724373576,
"grad_norm": 0.36409586668014526,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1172
},
{
"epoch": 2.6719817767653757,
"grad_norm": 0.3264155983924866,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1173
},
{
"epoch": 2.6742596810933943,
"grad_norm": 0.3416155278682709,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1174
},
{
"epoch": 2.6765375854214124,
"grad_norm": 0.33026736974716187,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1175
},
{
"epoch": 2.6788154897494305,
"grad_norm": 0.30708789825439453,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 1176
},
{
"epoch": 2.6810933940774486,
"grad_norm": 0.34217360615730286,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1177
},
{
"epoch": 2.6833712984054667,
"grad_norm": 0.3175274729728699,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1178
},
{
"epoch": 2.6856492027334853,
"grad_norm": 0.3422200083732605,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1179
},
{
"epoch": 2.6879271070615034,
"grad_norm": 0.3193976879119873,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1180
},
{
"epoch": 2.6902050113895215,
"grad_norm": 0.3266102075576782,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1181
},
{
"epoch": 2.69248291571754,
"grad_norm": 0.37876564264297485,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1182
},
{
"epoch": 2.694760820045558,
"grad_norm": 0.35405901074409485,
"learning_rate": 5e-06,
"loss": 0.0656,
"step": 1183
},
{
"epoch": 2.6970387243735763,
"grad_norm": 0.35572513937950134,
"learning_rate": 5e-06,
"loss": 0.0663,
"step": 1184
},
{
"epoch": 2.6993166287015944,
"grad_norm": 0.3613019287586212,
"learning_rate": 5e-06,
"loss": 0.0609,
"step": 1185
},
{
"epoch": 2.7015945330296125,
"grad_norm": 0.37498390674591064,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1186
},
{
"epoch": 2.703872437357631,
"grad_norm": 0.31806430220603943,
"learning_rate": 5e-06,
"loss": 0.0666,
"step": 1187
},
{
"epoch": 2.706150341685649,
"grad_norm": 0.4339022934436798,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 1188
},
{
"epoch": 2.7084282460136673,
"grad_norm": 0.32378706336021423,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 1189
},
{
"epoch": 2.710706150341686,
"grad_norm": 0.34744852781295776,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1190
},
{
"epoch": 2.712984054669704,
"grad_norm": 0.32550448179244995,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1191
},
{
"epoch": 2.715261958997722,
"grad_norm": 0.33748725056648254,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1192
},
{
"epoch": 2.71753986332574,
"grad_norm": 0.396217405796051,
"learning_rate": 5e-06,
"loss": 0.0624,
"step": 1193
},
{
"epoch": 2.7198177676537583,
"grad_norm": 0.33462515473365784,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1194
},
{
"epoch": 2.722095671981777,
"grad_norm": 0.3674948811531067,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1195
},
{
"epoch": 2.724373576309795,
"grad_norm": 0.37018531560897827,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1196
},
{
"epoch": 2.7266514806378135,
"grad_norm": 0.33755621314048767,
"learning_rate": 5e-06,
"loss": 0.067,
"step": 1197
},
{
"epoch": 2.7289293849658316,
"grad_norm": 0.41091012954711914,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1198
},
{
"epoch": 2.7312072892938497,
"grad_norm": 0.41686341166496277,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1199
},
{
"epoch": 2.733485193621868,
"grad_norm": 0.4030642807483673,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1200
},
{
"epoch": 2.735763097949886,
"grad_norm": 0.3342956602573395,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1201
},
{
"epoch": 2.7380410022779045,
"grad_norm": 0.3751448094844818,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 1202
},
{
"epoch": 2.7403189066059226,
"grad_norm": 0.34822869300842285,
"learning_rate": 5e-06,
"loss": 0.0645,
"step": 1203
},
{
"epoch": 2.7425968109339407,
"grad_norm": 0.342708945274353,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 1204
},
{
"epoch": 2.7448747152619593,
"grad_norm": 0.34886717796325684,
"learning_rate": 5e-06,
"loss": 0.0677,
"step": 1205
},
{
"epoch": 2.7471526195899774,
"grad_norm": 0.36077600717544556,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1206
},
{
"epoch": 2.7494305239179955,
"grad_norm": 0.38435259461402893,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1207
},
{
"epoch": 2.7517084282460136,
"grad_norm": 0.3360936641693115,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1208
},
{
"epoch": 2.7539863325740317,
"grad_norm": 0.32045936584472656,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1209
},
{
"epoch": 2.7562642369020502,
"grad_norm": 0.3480812907218933,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 1210
},
{
"epoch": 2.7585421412300684,
"grad_norm": 0.38358426094055176,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 1211
},
{
"epoch": 2.7608200455580865,
"grad_norm": 0.33160167932510376,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1212
},
{
"epoch": 2.763097949886105,
"grad_norm": 0.3674454689025879,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1213
},
{
"epoch": 2.765375854214123,
"grad_norm": 0.3301061689853668,
"learning_rate": 5e-06,
"loss": 0.0593,
"step": 1214
},
{
"epoch": 2.7676537585421412,
"grad_norm": 0.3309481739997864,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1215
},
{
"epoch": 2.7699316628701594,
"grad_norm": 0.347108393907547,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1216
},
{
"epoch": 2.7722095671981775,
"grad_norm": 0.3608108162879944,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1217
},
{
"epoch": 2.774487471526196,
"grad_norm": 0.3953985273838043,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 1218
},
{
"epoch": 2.776765375854214,
"grad_norm": 0.3932558298110962,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1219
},
{
"epoch": 2.7790432801822322,
"grad_norm": 0.3517478108406067,
"learning_rate": 5e-06,
"loss": 0.0661,
"step": 1220
},
{
"epoch": 2.781321184510251,
"grad_norm": 0.3522094488143921,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1221
},
{
"epoch": 2.783599088838269,
"grad_norm": 0.3189462125301361,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1222
},
{
"epoch": 2.785876993166287,
"grad_norm": 0.3788624703884125,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 1223
},
{
"epoch": 2.788154897494305,
"grad_norm": 0.3391224145889282,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1224
},
{
"epoch": 2.7904328018223232,
"grad_norm": 0.36144745349884033,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1225
},
{
"epoch": 2.792710706150342,
"grad_norm": 0.3475210964679718,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1226
},
{
"epoch": 2.79498861047836,
"grad_norm": 0.3617037534713745,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1227
},
{
"epoch": 2.797266514806378,
"grad_norm": 0.39694684743881226,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 1228
},
{
"epoch": 2.7995444191343966,
"grad_norm": 0.3512531816959381,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1229
},
{
"epoch": 2.8018223234624147,
"grad_norm": 0.40816575288772583,
"learning_rate": 5e-06,
"loss": 0.065,
"step": 1230
},
{
"epoch": 2.8041002277904328,
"grad_norm": 0.3422633111476898,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1231
},
{
"epoch": 2.806378132118451,
"grad_norm": 0.36634865403175354,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1232
},
{
"epoch": 2.808656036446469,
"grad_norm": 0.3451927602291107,
"learning_rate": 5e-06,
"loss": 0.0609,
"step": 1233
},
{
"epoch": 2.8109339407744875,
"grad_norm": 0.36408817768096924,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1234
},
{
"epoch": 2.8132118451025057,
"grad_norm": 0.35038718581199646,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1235
},
{
"epoch": 2.8154897494305238,
"grad_norm": 0.33411678671836853,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1236
},
{
"epoch": 2.8177676537585423,
"grad_norm": 0.3636171221733093,
"learning_rate": 5e-06,
"loss": 0.0652,
"step": 1237
},
{
"epoch": 2.8200455580865604,
"grad_norm": 0.3390803933143616,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1238
},
{
"epoch": 2.8223234624145785,
"grad_norm": 0.3592444062232971,
"learning_rate": 5e-06,
"loss": 0.0641,
"step": 1239
},
{
"epoch": 2.8246013667425967,
"grad_norm": 0.3812445104122162,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1240
},
{
"epoch": 2.8268792710706148,
"grad_norm": 0.39333441853523254,
"learning_rate": 5e-06,
"loss": 0.0658,
"step": 1241
},
{
"epoch": 2.8291571753986333,
"grad_norm": 0.31484416127204895,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1242
},
{
"epoch": 2.8314350797266514,
"grad_norm": 0.37235206365585327,
"learning_rate": 5e-06,
"loss": 0.063,
"step": 1243
},
{
"epoch": 2.83371298405467,
"grad_norm": 0.31487953662872314,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1244
},
{
"epoch": 2.835990888382688,
"grad_norm": 0.3140309154987335,
"learning_rate": 5e-06,
"loss": 0.0607,
"step": 1245
},
{
"epoch": 2.838268792710706,
"grad_norm": 0.3087141215801239,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1246
},
{
"epoch": 2.8405466970387243,
"grad_norm": 0.3366031050682068,
"learning_rate": 5e-06,
"loss": 0.0617,
"step": 1247
},
{
"epoch": 2.8428246013667424,
"grad_norm": 0.33195042610168457,
"learning_rate": 5e-06,
"loss": 0.0617,
"step": 1248
},
{
"epoch": 2.845102505694761,
"grad_norm": 0.34049350023269653,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1249
},
{
"epoch": 2.847380410022779,
"grad_norm": 0.308563232421875,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1250
},
{
"epoch": 2.849658314350797,
"grad_norm": 0.363180547952652,
"learning_rate": 5e-06,
"loss": 0.0617,
"step": 1251
},
{
"epoch": 2.8519362186788157,
"grad_norm": 0.3409302830696106,
"learning_rate": 5e-06,
"loss": 0.0615,
"step": 1252
},
{
"epoch": 2.854214123006834,
"grad_norm": 0.33143019676208496,
"learning_rate": 5e-06,
"loss": 0.0655,
"step": 1253
},
{
"epoch": 2.856492027334852,
"grad_norm": 0.37796229124069214,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1254
},
{
"epoch": 2.85876993166287,
"grad_norm": 0.32886597514152527,
"learning_rate": 5e-06,
"loss": 0.0603,
"step": 1255
},
{
"epoch": 2.861047835990888,
"grad_norm": 0.4048435688018799,
"learning_rate": 5e-06,
"loss": 0.0664,
"step": 1256
},
{
"epoch": 2.8633257403189067,
"grad_norm": 0.36198365688323975,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1257
},
{
"epoch": 2.865603644646925,
"grad_norm": 0.5110198855400085,
"learning_rate": 5e-06,
"loss": 0.0665,
"step": 1258
},
{
"epoch": 2.867881548974943,
"grad_norm": 0.37884554266929626,
"learning_rate": 5e-06,
"loss": 0.0614,
"step": 1259
},
{
"epoch": 2.8701594533029615,
"grad_norm": 0.4248731732368469,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 1260
},
{
"epoch": 2.8724373576309796,
"grad_norm": 0.3942655324935913,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 1261
},
{
"epoch": 2.8747152619589977,
"grad_norm": 0.40612831711769104,
"learning_rate": 5e-06,
"loss": 0.0615,
"step": 1262
},
{
"epoch": 2.876993166287016,
"grad_norm": 0.41458389163017273,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1263
},
{
"epoch": 2.879271070615034,
"grad_norm": 0.40696799755096436,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1264
},
{
"epoch": 2.8815489749430525,
"grad_norm": 0.3632875978946686,
"learning_rate": 5e-06,
"loss": 0.0635,
"step": 1265
},
{
"epoch": 2.8838268792710706,
"grad_norm": 0.3959384858608246,
"learning_rate": 5e-06,
"loss": 0.0605,
"step": 1266
},
{
"epoch": 2.8861047835990887,
"grad_norm": 0.36218011379241943,
"learning_rate": 5e-06,
"loss": 0.0628,
"step": 1267
},
{
"epoch": 2.8883826879271073,
"grad_norm": 0.37656182050704956,
"learning_rate": 5e-06,
"loss": 0.0607,
"step": 1268
},
{
"epoch": 2.8906605922551254,
"grad_norm": 0.36499765515327454,
"learning_rate": 5e-06,
"loss": 0.0638,
"step": 1269
},
{
"epoch": 2.8929384965831435,
"grad_norm": 0.3435059189796448,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 1270
},
{
"epoch": 2.8952164009111616,
"grad_norm": 0.36923810839653015,
"learning_rate": 5e-06,
"loss": 0.0607,
"step": 1271
},
{
"epoch": 2.8974943052391797,
"grad_norm": 0.37164321541786194,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 1272
},
{
"epoch": 2.8997722095671983,
"grad_norm": 0.42563021183013916,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 1273
},
{
"epoch": 2.9020501138952164,
"grad_norm": 0.3721482753753662,
"learning_rate": 5e-06,
"loss": 0.0632,
"step": 1274
},
{
"epoch": 2.9043280182232345,
"grad_norm": 0.36868250370025635,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1275
},
{
"epoch": 2.906605922551253,
"grad_norm": 0.3597923517227173,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1276
},
{
"epoch": 2.908883826879271,
"grad_norm": 0.3550402522087097,
"learning_rate": 5e-06,
"loss": 0.0648,
"step": 1277
},
{
"epoch": 2.9111617312072893,
"grad_norm": 0.3539983928203583,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1278
},
{
"epoch": 2.9134396355353074,
"grad_norm": 0.32854676246643066,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1279
},
{
"epoch": 2.9157175398633255,
"grad_norm": 0.33244210481643677,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1280
},
{
"epoch": 2.917995444191344,
"grad_norm": 0.3468360900878906,
"learning_rate": 5e-06,
"loss": 0.0634,
"step": 1281
},
{
"epoch": 2.920273348519362,
"grad_norm": 0.35334527492523193,
"learning_rate": 5e-06,
"loss": 0.0627,
"step": 1282
},
{
"epoch": 2.9225512528473803,
"grad_norm": 0.35016804933547974,
"learning_rate": 5e-06,
"loss": 0.0636,
"step": 1283
},
{
"epoch": 2.924829157175399,
"grad_norm": 0.4512026906013489,
"learning_rate": 5e-06,
"loss": 0.064,
"step": 1284
},
{
"epoch": 2.927107061503417,
"grad_norm": 0.359772264957428,
"learning_rate": 5e-06,
"loss": 0.0643,
"step": 1285
},
{
"epoch": 2.929384965831435,
"grad_norm": 0.3655630350112915,
"learning_rate": 5e-06,
"loss": 0.0629,
"step": 1286
},
{
"epoch": 2.931662870159453,
"grad_norm": 0.33043938875198364,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1287
},
{
"epoch": 2.9339407744874713,
"grad_norm": 0.3892334997653961,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1288
},
{
"epoch": 2.93621867881549,
"grad_norm": 0.3802751898765564,
"learning_rate": 5e-06,
"loss": 0.0612,
"step": 1289
},
{
"epoch": 2.938496583143508,
"grad_norm": 0.35937488079071045,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1290
},
{
"epoch": 2.940774487471526,
"grad_norm": 0.36067768931388855,
"learning_rate": 5e-06,
"loss": 0.0625,
"step": 1291
},
{
"epoch": 2.9430523917995446,
"grad_norm": 0.33447036147117615,
"learning_rate": 5e-06,
"loss": 0.0639,
"step": 1292
},
{
"epoch": 2.9453302961275627,
"grad_norm": 0.36563393473625183,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 1293
},
{
"epoch": 2.947608200455581,
"grad_norm": 0.35415124893188477,
"learning_rate": 5e-06,
"loss": 0.0613,
"step": 1294
},
{
"epoch": 2.949886104783599,
"grad_norm": 0.32227981090545654,
"learning_rate": 5e-06,
"loss": 0.0596,
"step": 1295
},
{
"epoch": 2.9521640091116175,
"grad_norm": 0.36177361011505127,
"learning_rate": 5e-06,
"loss": 0.0609,
"step": 1296
},
{
"epoch": 2.9544419134396356,
"grad_norm": 0.3240223228931427,
"learning_rate": 5e-06,
"loss": 0.0626,
"step": 1297
},
{
"epoch": 2.9567198177676537,
"grad_norm": 0.4267748296260834,
"learning_rate": 5e-06,
"loss": 0.0618,
"step": 1298
},
{
"epoch": 2.9589977220956722,
"grad_norm": 0.3413817584514618,
"learning_rate": 5e-06,
"loss": 0.0649,
"step": 1299
},
{
"epoch": 2.9612756264236904,
"grad_norm": 0.3571028709411621,
"learning_rate": 5e-06,
"loss": 0.0613,
"step": 1300
},
{
"epoch": 2.9635535307517085,
"grad_norm": 0.3737579584121704,
"learning_rate": 5e-06,
"loss": 0.0637,
"step": 1301
},
{
"epoch": 2.9658314350797266,
"grad_norm": 0.34754571318626404,
"learning_rate": 5e-06,
"loss": 0.0659,
"step": 1302
},
{
"epoch": 2.9681093394077447,
"grad_norm": 0.3502677381038666,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 1303
},
{
"epoch": 2.9703872437357632,
"grad_norm": 0.3277047872543335,
"learning_rate": 5e-06,
"loss": 0.0651,
"step": 1304
},
{
"epoch": 2.9726651480637813,
"grad_norm": 0.3437495231628418,
"learning_rate": 5e-06,
"loss": 0.0644,
"step": 1305
},
{
"epoch": 2.9749430523917995,
"grad_norm": 0.33111703395843506,
"learning_rate": 5e-06,
"loss": 0.0646,
"step": 1306
},
{
"epoch": 2.977220956719818,
"grad_norm": 0.35934245586395264,
"learning_rate": 5e-06,
"loss": 0.0654,
"step": 1307
},
{
"epoch": 2.979498861047836,
"grad_norm": 0.331857293844223,
"learning_rate": 5e-06,
"loss": 0.0653,
"step": 1308
},
{
"epoch": 2.9817767653758542,
"grad_norm": 0.3608936667442322,
"learning_rate": 5e-06,
"loss": 0.0642,
"step": 1309
},
{
"epoch": 2.9840546697038723,
"grad_norm": 0.3277752697467804,
"learning_rate": 5e-06,
"loss": 0.0623,
"step": 1310
},
{
"epoch": 2.9863325740318905,
"grad_norm": 0.37028080224990845,
"learning_rate": 5e-06,
"loss": 0.0657,
"step": 1311
},
{
"epoch": 2.988610478359909,
"grad_norm": 0.3204702138900757,
"learning_rate": 5e-06,
"loss": 0.0616,
"step": 1312
},
{
"epoch": 2.990888382687927,
"grad_norm": 0.3566315770149231,
"learning_rate": 5e-06,
"loss": 0.062,
"step": 1313
},
{
"epoch": 2.9931662870159452,
"grad_norm": 0.32704809308052063,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1314
},
{
"epoch": 2.995444191343964,
"grad_norm": 0.3317294716835022,
"learning_rate": 5e-06,
"loss": 0.0622,
"step": 1315
},
{
"epoch": 2.997722095671982,
"grad_norm": 0.3896945118904114,
"learning_rate": 5e-06,
"loss": 0.0684,
"step": 1316
},
{
"epoch": 3.0,
"grad_norm": 0.3358425796031952,
"learning_rate": 5e-06,
"loss": 0.0621,
"step": 1317
},
{
"epoch": 3.0,
"step": 1317,
"total_flos": 0.0,
"train_loss": 0.06867336523107444,
"train_runtime": 41172.7067,
"train_samples_per_second": 16.404,
"train_steps_per_second": 0.032
}
],
"logging_steps": 1,
"max_steps": 1317,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 132,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}