Files
10k_globalbatchsize128_lr4e…/trainer_state.json
ModelHub XC b34caac47e 初始化项目,由ModelHub XC社区提供模型
Model: mlfoundations-dev/10k_globalbatchsize128_lr4e5_epochs7
Source: Original Platform
2026-06-29 17:21:12 +08:00

3865 lines
87 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.9888,
"eval_steps": 500,
"global_step": 546,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0128,
"grad_norm": 5.766647666212616,
"learning_rate": 7.272727272727273e-07,
"loss": 0.8581,
"step": 1
},
{
"epoch": 0.0256,
"grad_norm": 6.070563091767254,
"learning_rate": 1.4545454545454546e-06,
"loss": 0.8903,
"step": 2
},
{
"epoch": 0.0384,
"grad_norm": 5.849190565123478,
"learning_rate": 2.181818181818182e-06,
"loss": 0.8612,
"step": 3
},
{
"epoch": 0.0512,
"grad_norm": 5.366961420323551,
"learning_rate": 2.9090909090909093e-06,
"loss": 0.8373,
"step": 4
},
{
"epoch": 0.064,
"grad_norm": 4.319707192417716,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.8142,
"step": 5
},
{
"epoch": 0.0768,
"grad_norm": 3.983191448432348,
"learning_rate": 4.363636363636364e-06,
"loss": 0.7828,
"step": 6
},
{
"epoch": 0.0896,
"grad_norm": 2.2385536982978125,
"learning_rate": 5.090909090909091e-06,
"loss": 0.7785,
"step": 7
},
{
"epoch": 0.1024,
"grad_norm": 1.8524407061261374,
"learning_rate": 5.8181818181818185e-06,
"loss": 0.7922,
"step": 8
},
{
"epoch": 0.1152,
"grad_norm": 4.1424544972227535,
"learning_rate": 6.545454545454546e-06,
"loss": 0.7785,
"step": 9
},
{
"epoch": 0.128,
"grad_norm": 4.241603681338813,
"learning_rate": 7.272727272727273e-06,
"loss": 0.7593,
"step": 10
},
{
"epoch": 0.1408,
"grad_norm": 4.126008550691871,
"learning_rate": 8.000000000000001e-06,
"loss": 0.7382,
"step": 11
},
{
"epoch": 0.1536,
"grad_norm": 4.308634912593385,
"learning_rate": 8.727272727272728e-06,
"loss": 0.7525,
"step": 12
},
{
"epoch": 0.1664,
"grad_norm": 3.589409317711825,
"learning_rate": 9.454545454545456e-06,
"loss": 0.742,
"step": 13
},
{
"epoch": 0.1792,
"grad_norm": 2.237262469277396,
"learning_rate": 1.0181818181818182e-05,
"loss": 0.6832,
"step": 14
},
{
"epoch": 0.192,
"grad_norm": 1.6758797429922476,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.6703,
"step": 15
},
{
"epoch": 0.2048,
"grad_norm": 2.1923512665296605,
"learning_rate": 1.1636363636363637e-05,
"loss": 0.6537,
"step": 16
},
{
"epoch": 0.2176,
"grad_norm": 1.922487155991213,
"learning_rate": 1.2363636363636364e-05,
"loss": 0.641,
"step": 17
},
{
"epoch": 0.2304,
"grad_norm": 1.2973346514268629,
"learning_rate": 1.3090909090909092e-05,
"loss": 0.6528,
"step": 18
},
{
"epoch": 0.2432,
"grad_norm": 1.2961046946095225,
"learning_rate": 1.381818181818182e-05,
"loss": 0.6134,
"step": 19
},
{
"epoch": 0.256,
"grad_norm": 1.3306249684434817,
"learning_rate": 1.4545454545454546e-05,
"loss": 0.5982,
"step": 20
},
{
"epoch": 0.2688,
"grad_norm": 0.989519669968098,
"learning_rate": 1.5272727272727276e-05,
"loss": 0.5845,
"step": 21
},
{
"epoch": 0.2816,
"grad_norm": 1.011623939977001,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.6178,
"step": 22
},
{
"epoch": 0.2944,
"grad_norm": 1.098222401076638,
"learning_rate": 1.672727272727273e-05,
"loss": 0.588,
"step": 23
},
{
"epoch": 0.3072,
"grad_norm": 0.9865060069928192,
"learning_rate": 1.7454545454545456e-05,
"loss": 0.6123,
"step": 24
},
{
"epoch": 0.32,
"grad_norm": 0.8484006270435027,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.5905,
"step": 25
},
{
"epoch": 0.3328,
"grad_norm": 0.9148839630470734,
"learning_rate": 1.8909090909090912e-05,
"loss": 0.5878,
"step": 26
},
{
"epoch": 0.3456,
"grad_norm": 0.7336597756013822,
"learning_rate": 1.963636363636364e-05,
"loss": 0.5888,
"step": 27
},
{
"epoch": 0.3584,
"grad_norm": 0.8092409634479293,
"learning_rate": 2.0363636363636365e-05,
"loss": 0.5837,
"step": 28
},
{
"epoch": 0.3712,
"grad_norm": 0.7637535128865753,
"learning_rate": 2.109090909090909e-05,
"loss": 0.5814,
"step": 29
},
{
"epoch": 0.384,
"grad_norm": 0.7555077187353209,
"learning_rate": 2.1818181818181818e-05,
"loss": 0.5553,
"step": 30
},
{
"epoch": 0.3968,
"grad_norm": 0.8186392586199401,
"learning_rate": 2.2545454545454544e-05,
"loss": 0.5773,
"step": 31
},
{
"epoch": 0.4096,
"grad_norm": 0.8210622569331878,
"learning_rate": 2.3272727272727274e-05,
"loss": 0.5848,
"step": 32
},
{
"epoch": 0.4224,
"grad_norm": 0.8313195292833121,
"learning_rate": 2.4e-05,
"loss": 0.5727,
"step": 33
},
{
"epoch": 0.4352,
"grad_norm": 0.6630479354750299,
"learning_rate": 2.4727272727272727e-05,
"loss": 0.5675,
"step": 34
},
{
"epoch": 0.448,
"grad_norm": 0.9805477228857835,
"learning_rate": 2.5454545454545457e-05,
"loss": 0.5832,
"step": 35
},
{
"epoch": 0.4608,
"grad_norm": 0.7371360352051671,
"learning_rate": 2.6181818181818183e-05,
"loss": 0.5824,
"step": 36
},
{
"epoch": 0.4736,
"grad_norm": 0.8556866980617879,
"learning_rate": 2.690909090909091e-05,
"loss": 0.5738,
"step": 37
},
{
"epoch": 0.4864,
"grad_norm": 0.766882649198606,
"learning_rate": 2.763636363636364e-05,
"loss": 0.5614,
"step": 38
},
{
"epoch": 0.4992,
"grad_norm": 1.1955571273221928,
"learning_rate": 2.8363636363636366e-05,
"loss": 0.554,
"step": 39
},
{
"epoch": 0.512,
"grad_norm": 0.6114564427093548,
"learning_rate": 2.9090909090909093e-05,
"loss": 0.517,
"step": 40
},
{
"epoch": 0.5248,
"grad_norm": 1.0261669102259894,
"learning_rate": 2.9818181818181823e-05,
"loss": 0.5714,
"step": 41
},
{
"epoch": 0.5376,
"grad_norm": 0.8655996084109017,
"learning_rate": 3.054545454545455e-05,
"loss": 0.5287,
"step": 42
},
{
"epoch": 0.5504,
"grad_norm": 0.6771821140740898,
"learning_rate": 3.127272727272728e-05,
"loss": 0.5573,
"step": 43
},
{
"epoch": 0.5632,
"grad_norm": 0.7880081437519127,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.546,
"step": 44
},
{
"epoch": 0.576,
"grad_norm": 1.1131641762341702,
"learning_rate": 3.272727272727273e-05,
"loss": 0.5406,
"step": 45
},
{
"epoch": 0.5888,
"grad_norm": 0.8489996563987092,
"learning_rate": 3.345454545454546e-05,
"loss": 0.5271,
"step": 46
},
{
"epoch": 0.6016,
"grad_norm": 0.6805613862148753,
"learning_rate": 3.4181818181818185e-05,
"loss": 0.5142,
"step": 47
},
{
"epoch": 0.6144,
"grad_norm": 0.9178327140587307,
"learning_rate": 3.490909090909091e-05,
"loss": 0.509,
"step": 48
},
{
"epoch": 0.6272,
"grad_norm": 0.8562187238764861,
"learning_rate": 3.563636363636364e-05,
"loss": 0.5489,
"step": 49
},
{
"epoch": 0.64,
"grad_norm": 0.9567967213511702,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.5198,
"step": 50
},
{
"epoch": 0.6528,
"grad_norm": 1.0431846360290824,
"learning_rate": 3.709090909090909e-05,
"loss": 0.5356,
"step": 51
},
{
"epoch": 0.6656,
"grad_norm": 1.083823508582481,
"learning_rate": 3.7818181818181824e-05,
"loss": 0.5235,
"step": 52
},
{
"epoch": 0.6784,
"grad_norm": 1.134077161018365,
"learning_rate": 3.854545454545455e-05,
"loss": 0.5372,
"step": 53
},
{
"epoch": 0.6912,
"grad_norm": 0.9918330614306756,
"learning_rate": 3.927272727272728e-05,
"loss": 0.5349,
"step": 54
},
{
"epoch": 0.704,
"grad_norm": 0.895430718728658,
"learning_rate": 4e-05,
"loss": 0.5568,
"step": 55
},
{
"epoch": 0.7168,
"grad_norm": 1.1849253245115767,
"learning_rate": 3.9999590611838754e-05,
"loss": 0.5309,
"step": 56
},
{
"epoch": 0.7296,
"grad_norm": 1.6206581340504822,
"learning_rate": 3.9998362464114874e-05,
"loss": 0.5401,
"step": 57
},
{
"epoch": 0.7424,
"grad_norm": 0.8852091548398006,
"learning_rate": 3.9996315607107277e-05,
"loss": 0.5466,
"step": 58
},
{
"epoch": 0.7552,
"grad_norm": 2.4037295401703993,
"learning_rate": 3.999345012461187e-05,
"loss": 0.5228,
"step": 59
},
{
"epoch": 0.768,
"grad_norm": 1.18290113292988,
"learning_rate": 3.998976613393811e-05,
"loss": 0.5294,
"step": 60
},
{
"epoch": 0.7808,
"grad_norm": 2.3909872920791635,
"learning_rate": 3.9985263785904216e-05,
"loss": 0.5517,
"step": 61
},
{
"epoch": 0.7936,
"grad_norm": 1.8995488455984622,
"learning_rate": 3.997994326483098e-05,
"loss": 0.5545,
"step": 62
},
{
"epoch": 0.8064,
"grad_norm": 1.9806874172141407,
"learning_rate": 3.9973804788534234e-05,
"loss": 0.5232,
"step": 63
},
{
"epoch": 0.8192,
"grad_norm": 1.826849125317064,
"learning_rate": 3.996684860831595e-05,
"loss": 0.5196,
"step": 64
},
{
"epoch": 0.832,
"grad_norm": 2.1118198350321653,
"learning_rate": 3.995907500895389e-05,
"loss": 0.5351,
"step": 65
},
{
"epoch": 0.8448,
"grad_norm": 1.853943343385325,
"learning_rate": 3.995048430869002e-05,
"loss": 0.5463,
"step": 66
},
{
"epoch": 0.8576,
"grad_norm": 1.2859090452433557,
"learning_rate": 3.994107685921743e-05,
"loss": 0.513,
"step": 67
},
{
"epoch": 0.8704,
"grad_norm": 1.3324559576524067,
"learning_rate": 3.993085304566597e-05,
"loss": 0.5388,
"step": 68
},
{
"epoch": 0.8832,
"grad_norm": 1.4066383610468145,
"learning_rate": 3.991981328658646e-05,
"loss": 0.5266,
"step": 69
},
{
"epoch": 0.896,
"grad_norm": 1.074544255481515,
"learning_rate": 3.990795803393358e-05,
"loss": 0.5289,
"step": 70
},
{
"epoch": 0.9088,
"grad_norm": 1.233767803602614,
"learning_rate": 3.989528777304732e-05,
"loss": 0.5176,
"step": 71
},
{
"epoch": 0.9216,
"grad_norm": 1.1902967515411367,
"learning_rate": 3.988180302263317e-05,
"loss": 0.5142,
"step": 72
},
{
"epoch": 0.9344,
"grad_norm": 0.7468929103292316,
"learning_rate": 3.986750433474084e-05,
"loss": 0.508,
"step": 73
},
{
"epoch": 0.9472,
"grad_norm": 1.1721587861444878,
"learning_rate": 3.98523922947417e-05,
"loss": 0.5395,
"step": 74
},
{
"epoch": 0.96,
"grad_norm": 0.7706038364138307,
"learning_rate": 3.983646752130476e-05,
"loss": 0.5125,
"step": 75
},
{
"epoch": 0.9728,
"grad_norm": 1.0726481772450163,
"learning_rate": 3.981973066637141e-05,
"loss": 0.5029,
"step": 76
},
{
"epoch": 0.9856,
"grad_norm": 0.8400687765959799,
"learning_rate": 3.980218241512865e-05,
"loss": 0.5123,
"step": 77
},
{
"epoch": 0.9984,
"grad_norm": 0.8535214667511101,
"learning_rate": 3.9783823485981135e-05,
"loss": 0.5277,
"step": 78
},
{
"epoch": 1.0112,
"grad_norm": 1.7257143717748409,
"learning_rate": 3.976465463052168e-05,
"loss": 0.9868,
"step": 79
},
{
"epoch": 1.024,
"grad_norm": 0.9187320514880281,
"learning_rate": 3.974467663350053e-05,
"loss": 0.409,
"step": 80
},
{
"epoch": 1.0368,
"grad_norm": 0.9262130658449447,
"learning_rate": 3.972389031279324e-05,
"loss": 0.47,
"step": 81
},
{
"epoch": 1.0496,
"grad_norm": 0.8616469129748918,
"learning_rate": 3.970229651936717e-05,
"loss": 0.4449,
"step": 82
},
{
"epoch": 1.0624,
"grad_norm": 1.0518474663616275,
"learning_rate": 3.967989613724666e-05,
"loss": 0.5014,
"step": 83
},
{
"epoch": 1.0752,
"grad_norm": 0.8217604631371047,
"learning_rate": 3.965669008347683e-05,
"loss": 0.3972,
"step": 84
},
{
"epoch": 1.088,
"grad_norm": 0.9124931535305526,
"learning_rate": 3.963267930808604e-05,
"loss": 0.476,
"step": 85
},
{
"epoch": 1.1008,
"grad_norm": 0.7296858629742461,
"learning_rate": 3.9607864794047024e-05,
"loss": 0.4889,
"step": 86
},
{
"epoch": 1.1136,
"grad_norm": 0.8289576491901255,
"learning_rate": 3.958224755723661e-05,
"loss": 0.422,
"step": 87
},
{
"epoch": 1.1264,
"grad_norm": 0.6516116746500413,
"learning_rate": 3.955582864639413e-05,
"loss": 0.4481,
"step": 88
},
{
"epoch": 1.1392,
"grad_norm": 0.6970366182418265,
"learning_rate": 3.952860914307853e-05,
"loss": 0.4095,
"step": 89
},
{
"epoch": 1.152,
"grad_norm": 0.7629374723423523,
"learning_rate": 3.950059016162405e-05,
"loss": 0.4876,
"step": 90
},
{
"epoch": 1.1648,
"grad_norm": 0.7272520952740609,
"learning_rate": 3.947177284909461e-05,
"loss": 0.467,
"step": 91
},
{
"epoch": 1.1776,
"grad_norm": 0.7018243837639311,
"learning_rate": 3.944215838523688e-05,
"loss": 0.4342,
"step": 92
},
{
"epoch": 1.1904,
"grad_norm": 0.7721912911057486,
"learning_rate": 3.9411747982431946e-05,
"loss": 0.456,
"step": 93
},
{
"epoch": 1.2032,
"grad_norm": 0.8429070071857203,
"learning_rate": 3.93805428856457e-05,
"loss": 0.4618,
"step": 94
},
{
"epoch": 1.216,
"grad_norm": 0.8297785735343746,
"learning_rate": 3.934854437237786e-05,
"loss": 0.4565,
"step": 95
},
{
"epoch": 1.2288000000000001,
"grad_norm": 0.8148441099919421,
"learning_rate": 3.931575375260967e-05,
"loss": 0.4681,
"step": 96
},
{
"epoch": 1.2416,
"grad_norm": 0.74868212519342,
"learning_rate": 3.9282172368750296e-05,
"loss": 0.4657,
"step": 97
},
{
"epoch": 1.2544,
"grad_norm": 0.7608065655422503,
"learning_rate": 3.924780159558183e-05,
"loss": 0.4728,
"step": 98
},
{
"epoch": 1.2671999999999999,
"grad_norm": 0.5832130148164872,
"learning_rate": 3.921264284020303e-05,
"loss": 0.4464,
"step": 99
},
{
"epoch": 1.28,
"grad_norm": 0.7583796982679346,
"learning_rate": 3.917669754197172e-05,
"loss": 0.4781,
"step": 100
},
{
"epoch": 1.2928,
"grad_norm": 0.6983145819761016,
"learning_rate": 3.913996717244586e-05,
"loss": 0.4802,
"step": 101
},
{
"epoch": 1.3056,
"grad_norm": 0.633883220383747,
"learning_rate": 3.91024532353233e-05,
"loss": 0.4515,
"step": 102
},
{
"epoch": 1.3184,
"grad_norm": 0.7293043661363177,
"learning_rate": 3.906415726638019e-05,
"loss": 0.4618,
"step": 103
},
{
"epoch": 1.3312,
"grad_norm": 0.71457656680089,
"learning_rate": 3.902508083340819e-05,
"loss": 0.4485,
"step": 104
},
{
"epoch": 1.3439999999999999,
"grad_norm": 0.6694072080044774,
"learning_rate": 3.898522553615019e-05,
"loss": 0.4592,
"step": 105
},
{
"epoch": 1.3568,
"grad_norm": 0.765617737172502,
"learning_rate": 3.8944593006234875e-05,
"loss": 0.485,
"step": 106
},
{
"epoch": 1.3696,
"grad_norm": 0.7145515487305579,
"learning_rate": 3.890318490710991e-05,
"loss": 0.4613,
"step": 107
},
{
"epoch": 1.3824,
"grad_norm": 0.6061420766857758,
"learning_rate": 3.8861002933973864e-05,
"loss": 0.4298,
"step": 108
},
{
"epoch": 1.3952,
"grad_norm": 0.7012511500544174,
"learning_rate": 3.881804881370678e-05,
"loss": 0.4503,
"step": 109
},
{
"epoch": 1.408,
"grad_norm": 0.7186537669109706,
"learning_rate": 3.877432430479948e-05,
"loss": 0.446,
"step": 110
},
{
"epoch": 1.4208,
"grad_norm": 0.9561446414998498,
"learning_rate": 3.872983119728159e-05,
"loss": 0.4561,
"step": 111
},
{
"epoch": 1.4336,
"grad_norm": 0.8358387016313162,
"learning_rate": 3.868457131264827e-05,
"loss": 0.4322,
"step": 112
},
{
"epoch": 1.4464000000000001,
"grad_norm": 0.6628561595064786,
"learning_rate": 3.863854650378561e-05,
"loss": 0.4494,
"step": 113
},
{
"epoch": 1.4592,
"grad_norm": 0.8071170431319441,
"learning_rate": 3.85917586548948e-05,
"loss": 0.4782,
"step": 114
},
{
"epoch": 1.472,
"grad_norm": 0.8909575463285895,
"learning_rate": 3.8544209681414974e-05,
"loss": 0.4328,
"step": 115
},
{
"epoch": 1.4848,
"grad_norm": 0.7776045622327772,
"learning_rate": 3.849590152994482e-05,
"loss": 0.4615,
"step": 116
},
{
"epoch": 1.4976,
"grad_norm": 0.5050519210854457,
"learning_rate": 3.844683617816288e-05,
"loss": 0.4351,
"step": 117
},
{
"epoch": 1.5104,
"grad_norm": 0.7445309644133907,
"learning_rate": 3.839701563474655e-05,
"loss": 0.4355,
"step": 118
},
{
"epoch": 1.5232,
"grad_norm": 0.858712298478702,
"learning_rate": 3.8346441939289894e-05,
"loss": 0.4321,
"step": 119
},
{
"epoch": 1.536,
"grad_norm": 0.6986275684709435,
"learning_rate": 3.829511716222016e-05,
"loss": 0.4418,
"step": 120
},
{
"epoch": 1.5488,
"grad_norm": 0.4531036376400173,
"learning_rate": 3.824304340471292e-05,
"loss": 0.4563,
"step": 121
},
{
"epoch": 1.5615999999999999,
"grad_norm": 0.6997377767041477,
"learning_rate": 3.819022279860618e-05,
"loss": 0.4384,
"step": 122
},
{
"epoch": 1.5744,
"grad_norm": 0.8132599800044655,
"learning_rate": 3.813665750631303e-05,
"loss": 0.4326,
"step": 123
},
{
"epoch": 1.5872000000000002,
"grad_norm": 0.6506063752645281,
"learning_rate": 3.80823497207331e-05,
"loss": 0.4396,
"step": 124
},
{
"epoch": 1.6,
"grad_norm": 0.6030548407595232,
"learning_rate": 3.802730166516285e-05,
"loss": 0.4708,
"step": 125
},
{
"epoch": 1.6128,
"grad_norm": 0.7076521473676728,
"learning_rate": 3.79715155932045e-05,
"loss": 0.4474,
"step": 126
},
{
"epoch": 1.6256,
"grad_norm": 0.7765139604545522,
"learning_rate": 3.79149937886738e-05,
"loss": 0.4642,
"step": 127
},
{
"epoch": 1.6383999999999999,
"grad_norm": 0.5397240679719468,
"learning_rate": 3.78577385655065e-05,
"loss": 0.4276,
"step": 128
},
{
"epoch": 1.6512,
"grad_norm": 0.6826274999940021,
"learning_rate": 3.779975226766367e-05,
"loss": 0.4495,
"step": 129
},
{
"epoch": 1.6640000000000001,
"grad_norm": 0.7226813373442722,
"learning_rate": 3.774103726903569e-05,
"loss": 0.4378,
"step": 130
},
{
"epoch": 1.6768,
"grad_norm": 0.6554425192594432,
"learning_rate": 3.768159597334508e-05,
"loss": 0.4512,
"step": 131
},
{
"epoch": 1.6896,
"grad_norm": 0.5515990558761849,
"learning_rate": 3.762143081404812e-05,
"loss": 0.432,
"step": 132
},
{
"epoch": 1.7024,
"grad_norm": 0.600550529502125,
"learning_rate": 3.756054425423521e-05,
"loss": 0.4653,
"step": 133
},
{
"epoch": 1.7151999999999998,
"grad_norm": 0.6893688591559344,
"learning_rate": 3.749893878653003e-05,
"loss": 0.4542,
"step": 134
},
{
"epoch": 1.728,
"grad_norm": 0.7402084524765938,
"learning_rate": 3.743661693298749e-05,
"loss": 0.4349,
"step": 135
},
{
"epoch": 1.7408000000000001,
"grad_norm": 0.5839603992364941,
"learning_rate": 3.737358124499048e-05,
"loss": 0.4731,
"step": 136
},
{
"epoch": 1.7536,
"grad_norm": 0.7031604105858179,
"learning_rate": 3.730983430314546e-05,
"loss": 0.4731,
"step": 137
},
{
"epoch": 1.7664,
"grad_norm": 0.5510962910938753,
"learning_rate": 3.7245378717176746e-05,
"loss": 0.4522,
"step": 138
},
{
"epoch": 1.7792,
"grad_norm": 0.5805176267423117,
"learning_rate": 3.7180217125819724e-05,
"loss": 0.4279,
"step": 139
},
{
"epoch": 1.792,
"grad_norm": 0.6569058034178186,
"learning_rate": 3.711435219671281e-05,
"loss": 0.4285,
"step": 140
},
{
"epoch": 1.8048,
"grad_norm": 0.4782604481285825,
"learning_rate": 3.704778662628822e-05,
"loss": 0.4415,
"step": 141
},
{
"epoch": 1.8176,
"grad_norm": 0.6462662309715211,
"learning_rate": 3.69805231396616e-05,
"loss": 0.4497,
"step": 142
},
{
"epoch": 1.8304,
"grad_norm": 0.6876661922675077,
"learning_rate": 3.691256449052046e-05,
"loss": 0.48,
"step": 143
},
{
"epoch": 1.8432,
"grad_norm": 0.5384325891746345,
"learning_rate": 3.684391346101144e-05,
"loss": 0.44,
"step": 144
},
{
"epoch": 1.8559999999999999,
"grad_norm": 0.6637508026767504,
"learning_rate": 3.677457286162642e-05,
"loss": 0.4479,
"step": 145
},
{
"epoch": 1.8688,
"grad_norm": 0.6645446611940581,
"learning_rate": 3.6704545531087446e-05,
"loss": 0.4406,
"step": 146
},
{
"epoch": 1.8816000000000002,
"grad_norm": 0.5968030708919606,
"learning_rate": 3.663383433623052e-05,
"loss": 0.423,
"step": 147
},
{
"epoch": 1.8944,
"grad_norm": 0.5582096002850404,
"learning_rate": 3.6562442171888256e-05,
"loss": 0.4474,
"step": 148
},
{
"epoch": 1.9072,
"grad_norm": 0.7402264879185477,
"learning_rate": 3.6490371960771345e-05,
"loss": 0.4793,
"step": 149
},
{
"epoch": 1.92,
"grad_norm": 0.8257667428268111,
"learning_rate": 3.641762665334889e-05,
"loss": 0.4507,
"step": 150
},
{
"epoch": 1.9327999999999999,
"grad_norm": 0.6316062189840759,
"learning_rate": 3.6344209227727676e-05,
"loss": 0.461,
"step": 151
},
{
"epoch": 1.9456,
"grad_norm": 0.6061304680303753,
"learning_rate": 3.6270122689530176e-05,
"loss": 0.4475,
"step": 152
},
{
"epoch": 1.9584000000000001,
"grad_norm": 0.6513650194047896,
"learning_rate": 3.619537007177156e-05,
"loss": 0.4499,
"step": 153
},
{
"epoch": 1.9712,
"grad_norm": 0.5974181056604952,
"learning_rate": 3.611995443473551e-05,
"loss": 0.4409,
"step": 154
},
{
"epoch": 1.984,
"grad_norm": 0.5919313656283548,
"learning_rate": 3.604387886584891e-05,
"loss": 0.4558,
"step": 155
},
{
"epoch": 1.9968,
"grad_norm": 0.9347918851120308,
"learning_rate": 3.596714647955549e-05,
"loss": 0.458,
"step": 156
},
{
"epoch": 2.0096,
"grad_norm": 1.68882508674077,
"learning_rate": 3.588976041718831e-05,
"loss": 0.7147,
"step": 157
},
{
"epoch": 2.0224,
"grad_norm": 0.7396141317421906,
"learning_rate": 3.5811723846841136e-05,
"loss": 0.3494,
"step": 158
},
{
"epoch": 2.0352,
"grad_norm": 1.5555619540369099,
"learning_rate": 3.573303996323879e-05,
"loss": 0.3455,
"step": 159
},
{
"epoch": 2.048,
"grad_norm": 1.0492526740667485,
"learning_rate": 3.5653711987606295e-05,
"loss": 0.3768,
"step": 160
},
{
"epoch": 2.0608,
"grad_norm": 1.1009529864489498,
"learning_rate": 3.557374316753707e-05,
"loss": 0.3405,
"step": 161
},
{
"epoch": 2.0736,
"grad_norm": 0.8963852147067644,
"learning_rate": 3.549313677685993e-05,
"loss": 0.3673,
"step": 162
},
{
"epoch": 2.0864,
"grad_norm": 1.1353914752902645,
"learning_rate": 3.5411896115505093e-05,
"loss": 0.356,
"step": 163
},
{
"epoch": 2.0992,
"grad_norm": 1.1103317507624728,
"learning_rate": 3.5330024509369044e-05,
"loss": 0.3258,
"step": 164
},
{
"epoch": 2.112,
"grad_norm": 0.7624332967449798,
"learning_rate": 3.5247525310178416e-05,
"loss": 0.3587,
"step": 165
},
{
"epoch": 2.1248,
"grad_norm": 1.0631163535464458,
"learning_rate": 3.516440189535276e-05,
"loss": 0.3255,
"step": 166
},
{
"epoch": 2.1376,
"grad_norm": 0.7588188950702179,
"learning_rate": 3.508065766786626e-05,
"loss": 0.353,
"step": 167
},
{
"epoch": 2.1504,
"grad_norm": 0.9260850680586817,
"learning_rate": 3.499629605610846e-05,
"loss": 0.3327,
"step": 168
},
{
"epoch": 2.1632,
"grad_norm": 0.8857538034310635,
"learning_rate": 3.491132051374386e-05,
"loss": 0.3802,
"step": 169
},
{
"epoch": 2.176,
"grad_norm": 0.867301901975402,
"learning_rate": 3.482573451957057e-05,
"loss": 0.3033,
"step": 170
},
{
"epoch": 2.1888,
"grad_norm": 0.9623966007879786,
"learning_rate": 3.4739541577377874e-05,
"loss": 0.3535,
"step": 171
},
{
"epoch": 2.2016,
"grad_norm": 0.712478214609947,
"learning_rate": 3.4652745215802776e-05,
"loss": 0.3295,
"step": 172
},
{
"epoch": 2.2144,
"grad_norm": 0.7561939526359985,
"learning_rate": 3.456534898818556e-05,
"loss": 0.3446,
"step": 173
},
{
"epoch": 2.2272,
"grad_norm": 0.7251207662016594,
"learning_rate": 3.447735647242432e-05,
"loss": 0.3549,
"step": 174
},
{
"epoch": 2.24,
"grad_norm": 0.5830550912281133,
"learning_rate": 3.4388771270828484e-05,
"loss": 0.3249,
"step": 175
},
{
"epoch": 2.2528,
"grad_norm": 0.6750592809315261,
"learning_rate": 3.429959700997133e-05,
"loss": 0.3663,
"step": 176
},
{
"epoch": 2.2656,
"grad_norm": 0.5881141320280098,
"learning_rate": 3.4209837340541526e-05,
"loss": 0.31,
"step": 177
},
{
"epoch": 2.2784,
"grad_norm": 0.6540406338097797,
"learning_rate": 3.411949593719367e-05,
"loss": 0.3417,
"step": 178
},
{
"epoch": 2.2912,
"grad_norm": 0.47356399399718,
"learning_rate": 3.4028576498397875e-05,
"loss": 0.34,
"step": 179
},
{
"epoch": 2.304,
"grad_norm": 0.6242152248297176,
"learning_rate": 3.3937082746288314e-05,
"loss": 0.3339,
"step": 180
},
{
"epoch": 2.3168,
"grad_norm": 0.4381888293534401,
"learning_rate": 3.384501842651088e-05,
"loss": 0.3125,
"step": 181
},
{
"epoch": 2.3296,
"grad_norm": 0.6044780918561927,
"learning_rate": 3.3752387308069844e-05,
"loss": 0.3294,
"step": 182
},
{
"epoch": 2.3424,
"grad_norm": 0.48769761285521435,
"learning_rate": 3.365919318317352e-05,
"loss": 0.3279,
"step": 183
},
{
"epoch": 2.3552,
"grad_norm": 0.6683750856465323,
"learning_rate": 3.356543986707906e-05,
"loss": 0.3562,
"step": 184
},
{
"epoch": 2.368,
"grad_norm": 0.4816943504390966,
"learning_rate": 3.347113119793623e-05,
"loss": 0.3049,
"step": 185
},
{
"epoch": 2.3808,
"grad_norm": 0.7481643721907355,
"learning_rate": 3.337627103663029e-05,
"loss": 0.3621,
"step": 186
},
{
"epoch": 2.3936,
"grad_norm": 0.6810921053657787,
"learning_rate": 3.328086326662395e-05,
"loss": 0.3571,
"step": 187
},
{
"epoch": 2.4064,
"grad_norm": 0.6888563795267724,
"learning_rate": 3.3184911793798354e-05,
"loss": 0.3397,
"step": 188
},
{
"epoch": 2.4192,
"grad_norm": 0.5626087628280371,
"learning_rate": 3.3088420546293216e-05,
"loss": 0.3497,
"step": 189
},
{
"epoch": 2.432,
"grad_norm": 0.6237987815234062,
"learning_rate": 3.2991393474345963e-05,
"loss": 0.3475,
"step": 190
},
{
"epoch": 2.4448,
"grad_norm": 0.6334428971530011,
"learning_rate": 3.2893834550130064e-05,
"loss": 0.3443,
"step": 191
},
{
"epoch": 2.4576000000000002,
"grad_norm": 0.5954885982090595,
"learning_rate": 3.279574776759237e-05,
"loss": 0.3255,
"step": 192
},
{
"epoch": 2.4704,
"grad_norm": 0.5346994876530767,
"learning_rate": 3.269713714228963e-05,
"loss": 0.3641,
"step": 193
},
{
"epoch": 2.4832,
"grad_norm": 0.5233223361539856,
"learning_rate": 3.259800671122412e-05,
"loss": 0.3043,
"step": 194
},
{
"epoch": 2.496,
"grad_norm": 0.5902351865314509,
"learning_rate": 3.249836053267832e-05,
"loss": 0.3654,
"step": 195
},
{
"epoch": 2.5088,
"grad_norm": 0.5310017789767338,
"learning_rate": 3.239820268604881e-05,
"loss": 0.3679,
"step": 196
},
{
"epoch": 2.5216,
"grad_norm": 0.5749019680258777,
"learning_rate": 3.2297537271679246e-05,
"loss": 0.3118,
"step": 197
},
{
"epoch": 2.5343999999999998,
"grad_norm": 0.48887240213564087,
"learning_rate": 3.219636841069254e-05,
"loss": 0.345,
"step": 198
},
{
"epoch": 2.5472,
"grad_norm": 0.46388293415755155,
"learning_rate": 3.2094700244822076e-05,
"loss": 0.3382,
"step": 199
},
{
"epoch": 2.56,
"grad_norm": 0.6580649682431245,
"learning_rate": 3.19925369362422e-05,
"loss": 0.3603,
"step": 200
},
{
"epoch": 2.5728,
"grad_norm": 0.5038834916141244,
"learning_rate": 3.1889882667397824e-05,
"loss": 0.3222,
"step": 201
},
{
"epoch": 2.5856,
"grad_norm": 0.49563807574498886,
"learning_rate": 3.178674164083319e-05,
"loss": 0.3231,
"step": 202
},
{
"epoch": 2.5984,
"grad_norm": 0.575767163541391,
"learning_rate": 3.1683118079019796e-05,
"loss": 0.3394,
"step": 203
},
{
"epoch": 2.6112,
"grad_norm": 0.4597102882311115,
"learning_rate": 3.157901622418361e-05,
"loss": 0.3333,
"step": 204
},
{
"epoch": 2.624,
"grad_norm": 0.5802249813716531,
"learning_rate": 3.147444033813131e-05,
"loss": 0.3691,
"step": 205
},
{
"epoch": 2.6368,
"grad_norm": 0.44036358447569723,
"learning_rate": 3.136939470207587e-05,
"loss": 0.3465,
"step": 206
},
{
"epoch": 2.6496,
"grad_norm": 0.517111374711644,
"learning_rate": 3.126388361646128e-05,
"loss": 0.3537,
"step": 207
},
{
"epoch": 2.6624,
"grad_norm": 0.5563115115312545,
"learning_rate": 3.115791140078646e-05,
"loss": 0.327,
"step": 208
},
{
"epoch": 2.6752000000000002,
"grad_norm": 0.45405966800432573,
"learning_rate": 3.105148239342846e-05,
"loss": 0.3575,
"step": 209
},
{
"epoch": 2.6879999999999997,
"grad_norm": 0.6003208308479673,
"learning_rate": 3.0944600951464854e-05,
"loss": 0.3435,
"step": 210
},
{
"epoch": 2.7008,
"grad_norm": 0.5629265714220094,
"learning_rate": 3.083727145049533e-05,
"loss": 0.3352,
"step": 211
},
{
"epoch": 2.7136,
"grad_norm": 0.505816705000162,
"learning_rate": 3.0729498284462604e-05,
"loss": 0.3412,
"step": 212
},
{
"epoch": 2.7264,
"grad_norm": 0.48662004131731706,
"learning_rate": 3.0621285865472506e-05,
"loss": 0.3177,
"step": 213
},
{
"epoch": 2.7392,
"grad_norm": 0.5166164187609994,
"learning_rate": 3.051263862361334e-05,
"loss": 0.3613,
"step": 214
},
{
"epoch": 2.752,
"grad_norm": 0.45648974173347506,
"learning_rate": 3.040356100677458e-05,
"loss": 0.358,
"step": 215
},
{
"epoch": 2.7648,
"grad_norm": 0.48126890974280656,
"learning_rate": 3.0294057480464722e-05,
"loss": 0.3335,
"step": 216
},
{
"epoch": 2.7776,
"grad_norm": 0.5006985131245671,
"learning_rate": 3.018413252762849e-05,
"loss": 0.364,
"step": 217
},
{
"epoch": 2.7904,
"grad_norm": 0.5570580236592455,
"learning_rate": 3.0073790648463324e-05,
"loss": 0.376,
"step": 218
},
{
"epoch": 2.8032,
"grad_norm": 0.5027618867496092,
"learning_rate": 2.9963036360235116e-05,
"loss": 0.3125,
"step": 219
},
{
"epoch": 2.816,
"grad_norm": 0.4741017296680652,
"learning_rate": 2.9851874197093305e-05,
"loss": 0.3193,
"step": 220
},
{
"epoch": 2.8288,
"grad_norm": 0.5067075189282028,
"learning_rate": 2.974030870988526e-05,
"loss": 0.4042,
"step": 221
},
{
"epoch": 2.8416,
"grad_norm": 0.5403290703799045,
"learning_rate": 2.9628344465969937e-05,
"loss": 0.3474,
"step": 222
},
{
"epoch": 2.8544,
"grad_norm": 0.5051316383199116,
"learning_rate": 2.951598604903094e-05,
"loss": 0.3425,
"step": 223
},
{
"epoch": 2.8672,
"grad_norm": 0.6126411020867858,
"learning_rate": 2.9403238058888838e-05,
"loss": 0.3663,
"step": 224
},
{
"epoch": 2.88,
"grad_norm": 0.44805711180182883,
"learning_rate": 2.929010511131286e-05,
"loss": 0.329,
"step": 225
},
{
"epoch": 2.8928000000000003,
"grad_norm": 0.47140986418516156,
"learning_rate": 2.9176591837831957e-05,
"loss": 0.3734,
"step": 226
},
{
"epoch": 2.9055999999999997,
"grad_norm": 0.4990465943606948,
"learning_rate": 2.906270288554514e-05,
"loss": 0.3695,
"step": 227
},
{
"epoch": 2.9184,
"grad_norm": 0.4459572858943639,
"learning_rate": 2.8948442916931302e-05,
"loss": 0.3716,
"step": 228
},
{
"epoch": 2.9312,
"grad_norm": 0.4373840770734537,
"learning_rate": 2.8833816609658285e-05,
"loss": 0.3496,
"step": 229
},
{
"epoch": 2.944,
"grad_norm": 0.41263208140764535,
"learning_rate": 2.8718828656391408e-05,
"loss": 0.3472,
"step": 230
},
{
"epoch": 2.9568,
"grad_norm": 0.47661903476036704,
"learning_rate": 2.8603483764601346e-05,
"loss": 0.3311,
"step": 231
},
{
"epoch": 2.9696,
"grad_norm": 0.40467849766325453,
"learning_rate": 2.84877866563714e-05,
"loss": 0.3184,
"step": 232
},
{
"epoch": 2.9824,
"grad_norm": 0.550669166928282,
"learning_rate": 2.8371742068204234e-05,
"loss": 0.356,
"step": 233
},
{
"epoch": 2.9952,
"grad_norm": 0.5065651003016768,
"learning_rate": 2.8255354750827885e-05,
"loss": 0.3454,
"step": 234
},
{
"epoch": 3.008,
"grad_norm": 1.1707581320465479,
"learning_rate": 2.8138629469001348e-05,
"loss": 0.5875,
"step": 235
},
{
"epoch": 3.0208,
"grad_norm": 0.620584400015292,
"learning_rate": 2.802157100131947e-05,
"loss": 0.2239,
"step": 236
},
{
"epoch": 3.0336,
"grad_norm": 0.5763638461388164,
"learning_rate": 2.7904184140017337e-05,
"loss": 0.2601,
"step": 237
},
{
"epoch": 3.0464,
"grad_norm": 0.7318463831016421,
"learning_rate": 2.7786473690774083e-05,
"loss": 0.2515,
"step": 238
},
{
"epoch": 3.0592,
"grad_norm": 0.7175785245276742,
"learning_rate": 2.766844447251614e-05,
"loss": 0.2436,
"step": 239
},
{
"epoch": 3.072,
"grad_norm": 0.5769486061062518,
"learning_rate": 2.7550101317219976e-05,
"loss": 0.2405,
"step": 240
},
{
"epoch": 3.0848,
"grad_norm": 0.7356912225196313,
"learning_rate": 2.7431449069714254e-05,
"loss": 0.2338,
"step": 241
},
{
"epoch": 3.0976,
"grad_norm": 0.5482699648987983,
"learning_rate": 2.7312492587481535e-05,
"loss": 0.2527,
"step": 242
},
{
"epoch": 3.1104,
"grad_norm": 0.7278855963720802,
"learning_rate": 2.7193236740459358e-05,
"loss": 0.2535,
"step": 243
},
{
"epoch": 3.1232,
"grad_norm": 0.5209696005166115,
"learning_rate": 2.707368641084092e-05,
"loss": 0.2277,
"step": 244
},
{
"epoch": 3.136,
"grad_norm": 0.5799949293571091,
"learning_rate": 2.695384649287518e-05,
"loss": 0.2519,
"step": 245
},
{
"epoch": 3.1488,
"grad_norm": 0.4295211416414721,
"learning_rate": 2.6833721892666513e-05,
"loss": 0.205,
"step": 246
},
{
"epoch": 3.1616,
"grad_norm": 0.6078391751071174,
"learning_rate": 2.6713317527973837e-05,
"loss": 0.2811,
"step": 247
},
{
"epoch": 3.1744,
"grad_norm": 0.4467418275080068,
"learning_rate": 2.659263832800929e-05,
"loss": 0.218,
"step": 248
},
{
"epoch": 3.1872,
"grad_norm": 0.5194811729182617,
"learning_rate": 2.647168923323646e-05,
"loss": 0.2448,
"step": 249
},
{
"epoch": 3.2,
"grad_norm": 0.44656028840081957,
"learning_rate": 2.635047519516809e-05,
"loss": 0.2132,
"step": 250
},
{
"epoch": 3.2128,
"grad_norm": 0.4800210191899564,
"learning_rate": 2.6229001176163397e-05,
"loss": 0.2365,
"step": 251
},
{
"epoch": 3.2256,
"grad_norm": 0.46280327945182453,
"learning_rate": 2.6107272149224915e-05,
"loss": 0.2582,
"step": 252
},
{
"epoch": 3.2384,
"grad_norm": 0.48826451973349416,
"learning_rate": 2.5985293097794884e-05,
"loss": 0.2479,
"step": 253
},
{
"epoch": 3.2512,
"grad_norm": 0.45436123348613633,
"learning_rate": 2.586306901555128e-05,
"loss": 0.2365,
"step": 254
},
{
"epoch": 3.2640000000000002,
"grad_norm": 0.428227995784899,
"learning_rate": 2.5740604906203314e-05,
"loss": 0.2091,
"step": 255
},
{
"epoch": 3.2768,
"grad_norm": 0.45158948638472934,
"learning_rate": 2.5617905783286655e-05,
"loss": 0.2552,
"step": 256
},
{
"epoch": 3.2896,
"grad_norm": 0.4979540052977787,
"learning_rate": 2.5494976669958128e-05,
"loss": 0.2547,
"step": 257
},
{
"epoch": 3.3024,
"grad_norm": 0.4077547533354734,
"learning_rate": 2.537182259879009e-05,
"loss": 0.2113,
"step": 258
},
{
"epoch": 3.3152,
"grad_norm": 0.48175196724891634,
"learning_rate": 2.524844861156443e-05,
"loss": 0.2123,
"step": 259
},
{
"epoch": 3.328,
"grad_norm": 0.43748528359385047,
"learning_rate": 2.512485975906612e-05,
"loss": 0.2495,
"step": 260
},
{
"epoch": 3.3407999999999998,
"grad_norm": 0.5422169999390144,
"learning_rate": 2.5001061100876464e-05,
"loss": 0.2656,
"step": 261
},
{
"epoch": 3.3536,
"grad_norm": 0.3582074679304393,
"learning_rate": 2.487705770516598e-05,
"loss": 0.2013,
"step": 262
},
{
"epoch": 3.3664,
"grad_norm": 0.42309455082841246,
"learning_rate": 2.4752854648486865e-05,
"loss": 0.2294,
"step": 263
},
{
"epoch": 3.3792,
"grad_norm": 0.41194063893489197,
"learning_rate": 2.462845701556523e-05,
"loss": 0.2391,
"step": 264
},
{
"epoch": 3.392,
"grad_norm": 0.406353093333956,
"learning_rate": 2.4503869899092893e-05,
"loss": 0.2447,
"step": 265
},
{
"epoch": 3.4048,
"grad_norm": 0.4138017967668467,
"learning_rate": 2.437909839951891e-05,
"loss": 0.2337,
"step": 266
},
{
"epoch": 3.4176,
"grad_norm": 0.4319021586998612,
"learning_rate": 2.4254147624840753e-05,
"loss": 0.2639,
"step": 267
},
{
"epoch": 3.4304,
"grad_norm": 0.42478939518199943,
"learning_rate": 2.4129022690395213e-05,
"loss": 0.2422,
"step": 268
},
{
"epoch": 3.4432,
"grad_norm": 0.364790435711411,
"learning_rate": 2.400372871864898e-05,
"loss": 0.2176,
"step": 269
},
{
"epoch": 3.456,
"grad_norm": 0.40879420221558926,
"learning_rate": 2.3878270838988912e-05,
"loss": 0.2528,
"step": 270
},
{
"epoch": 3.4688,
"grad_norm": 0.39869222794843207,
"learning_rate": 2.3752654187512096e-05,
"loss": 0.2289,
"step": 271
},
{
"epoch": 3.4816,
"grad_norm": 0.425952399527957,
"learning_rate": 2.362688390681551e-05,
"loss": 0.2407,
"step": 272
},
{
"epoch": 3.4944,
"grad_norm": 0.43270959684387034,
"learning_rate": 2.3500965145785563e-05,
"loss": 0.2779,
"step": 273
},
{
"epoch": 3.5072,
"grad_norm": 0.4201617504702752,
"learning_rate": 2.3374903059387252e-05,
"loss": 0.2457,
"step": 274
},
{
"epoch": 3.52,
"grad_norm": 0.38118856610528007,
"learning_rate": 2.3248702808453146e-05,
"loss": 0.2271,
"step": 275
},
{
"epoch": 3.5328,
"grad_norm": 0.3985845904701707,
"learning_rate": 2.3122369559472122e-05,
"loss": 0.2356,
"step": 276
},
{
"epoch": 3.5456,
"grad_norm": 0.38237515015330653,
"learning_rate": 2.2995908484377827e-05,
"loss": 0.2455,
"step": 277
},
{
"epoch": 3.5584,
"grad_norm": 0.3732656080587104,
"learning_rate": 2.2869324760336974e-05,
"loss": 0.2197,
"step": 278
},
{
"epoch": 3.5712,
"grad_norm": 0.3862117275595557,
"learning_rate": 2.2742623569537345e-05,
"loss": 0.2407,
"step": 279
},
{
"epoch": 3.584,
"grad_norm": 0.3667106893274838,
"learning_rate": 2.261581009897571e-05,
"loss": 0.2413,
"step": 280
},
{
"epoch": 3.5968,
"grad_norm": 0.4092835203483317,
"learning_rate": 2.2488889540245414e-05,
"loss": 0.2473,
"step": 281
},
{
"epoch": 3.6096,
"grad_norm": 0.3234994874357464,
"learning_rate": 2.2361867089323873e-05,
"loss": 0.2156,
"step": 282
},
{
"epoch": 3.6224,
"grad_norm": 0.4039677518774243,
"learning_rate": 2.223474794635985e-05,
"loss": 0.2383,
"step": 283
},
{
"epoch": 3.6352,
"grad_norm": 0.32831588402257283,
"learning_rate": 2.2107537315460568e-05,
"loss": 0.2189,
"step": 284
},
{
"epoch": 3.648,
"grad_norm": 0.368435445481273,
"learning_rate": 2.198024040447865e-05,
"loss": 0.2408,
"step": 285
},
{
"epoch": 3.6608,
"grad_norm": 0.3344541454476145,
"learning_rate": 2.1852862424798934e-05,
"loss": 0.2246,
"step": 286
},
{
"epoch": 3.6736,
"grad_norm": 0.3610577248521619,
"learning_rate": 2.17254085911251e-05,
"loss": 0.2558,
"step": 287
},
{
"epoch": 3.6864,
"grad_norm": 0.3447647268529026,
"learning_rate": 2.1597884121266215e-05,
"loss": 0.234,
"step": 288
},
{
"epoch": 3.6992000000000003,
"grad_norm": 0.3733623864161173,
"learning_rate": 2.14702942359231e-05,
"loss": 0.2528,
"step": 289
},
{
"epoch": 3.7119999999999997,
"grad_norm": 0.3555964389168844,
"learning_rate": 2.1342644158474614e-05,
"loss": 0.2333,
"step": 290
},
{
"epoch": 3.7248,
"grad_norm": 0.375041889099984,
"learning_rate": 2.12149391147638e-05,
"loss": 0.2293,
"step": 291
},
{
"epoch": 3.7376,
"grad_norm": 0.3753913119349554,
"learning_rate": 2.1087184332883965e-05,
"loss": 0.2681,
"step": 292
},
{
"epoch": 3.7504,
"grad_norm": 0.35812620707782256,
"learning_rate": 2.0959385042964632e-05,
"loss": 0.2572,
"step": 293
},
{
"epoch": 3.7632,
"grad_norm": 0.35370558498337545,
"learning_rate": 2.083154647695743e-05,
"loss": 0.2454,
"step": 294
},
{
"epoch": 3.776,
"grad_norm": 0.33944645923018973,
"learning_rate": 2.0703673868421914e-05,
"loss": 0.2244,
"step": 295
},
{
"epoch": 3.7888,
"grad_norm": 0.43600248171400513,
"learning_rate": 2.057577245231128e-05,
"loss": 0.2802,
"step": 296
},
{
"epoch": 3.8016,
"grad_norm": 0.3514694761026882,
"learning_rate": 2.0447847464758097e-05,
"loss": 0.2164,
"step": 297
},
{
"epoch": 3.8144,
"grad_norm": 0.3838479862720407,
"learning_rate": 2.0319904142859905e-05,
"loss": 0.2501,
"step": 298
},
{
"epoch": 3.8272,
"grad_norm": 0.402834531654162,
"learning_rate": 2.019194772446482e-05,
"loss": 0.246,
"step": 299
},
{
"epoch": 3.84,
"grad_norm": 0.32974960672809106,
"learning_rate": 2.006398344795715e-05,
"loss": 0.2276,
"step": 300
},
{
"epoch": 3.8528000000000002,
"grad_norm": 0.36392611703656436,
"learning_rate": 1.993601655204286e-05,
"loss": 0.2232,
"step": 301
},
{
"epoch": 3.8656,
"grad_norm": 0.3078085468561006,
"learning_rate": 1.9808052275535182e-05,
"loss": 0.2267,
"step": 302
},
{
"epoch": 3.8784,
"grad_norm": 0.3888124374503237,
"learning_rate": 1.96800958571401e-05,
"loss": 0.2225,
"step": 303
},
{
"epoch": 3.8912,
"grad_norm": 0.37003653365201067,
"learning_rate": 1.955215253524191e-05,
"loss": 0.253,
"step": 304
},
{
"epoch": 3.904,
"grad_norm": 0.4409141347947413,
"learning_rate": 1.9424227547688722e-05,
"loss": 0.2538,
"step": 305
},
{
"epoch": 3.9168,
"grad_norm": 0.33863563531226637,
"learning_rate": 1.9296326131578093e-05,
"loss": 0.2453,
"step": 306
},
{
"epoch": 3.9295999999999998,
"grad_norm": 0.43767186797123386,
"learning_rate": 1.916845352304257e-05,
"loss": 0.2335,
"step": 307
},
{
"epoch": 3.9424,
"grad_norm": 0.3701221709120628,
"learning_rate": 1.904061495703537e-05,
"loss": 0.2408,
"step": 308
},
{
"epoch": 3.9552,
"grad_norm": 0.4000488195902585,
"learning_rate": 1.8912815667116038e-05,
"loss": 0.2393,
"step": 309
},
{
"epoch": 3.968,
"grad_norm": 0.3291939266066057,
"learning_rate": 1.87850608852362e-05,
"loss": 0.2437,
"step": 310
},
{
"epoch": 3.9808,
"grad_norm": 0.3752298897806994,
"learning_rate": 1.8657355841525396e-05,
"loss": 0.2537,
"step": 311
},
{
"epoch": 3.9936,
"grad_norm": 0.33430834935473724,
"learning_rate": 1.8529705764076905e-05,
"loss": 0.2408,
"step": 312
},
{
"epoch": 4.0064,
"grad_norm": 0.909382249596848,
"learning_rate": 1.840211587873379e-05,
"loss": 0.3532,
"step": 313
},
{
"epoch": 4.0192,
"grad_norm": 0.4310906385465686,
"learning_rate": 1.82745914088749e-05,
"loss": 0.1459,
"step": 314
},
{
"epoch": 4.032,
"grad_norm": 0.40574720154778543,
"learning_rate": 1.8147137575201076e-05,
"loss": 0.1472,
"step": 315
},
{
"epoch": 4.0448,
"grad_norm": 0.6093359073366565,
"learning_rate": 1.8019759595521358e-05,
"loss": 0.1701,
"step": 316
},
{
"epoch": 4.0576,
"grad_norm": 0.4920569212315349,
"learning_rate": 1.789246268453944e-05,
"loss": 0.1576,
"step": 317
},
{
"epoch": 4.0704,
"grad_norm": 0.4877907338475741,
"learning_rate": 1.7765252053640157e-05,
"loss": 0.1669,
"step": 318
},
{
"epoch": 4.0832,
"grad_norm": 0.4533612882213416,
"learning_rate": 1.7638132910676134e-05,
"loss": 0.1708,
"step": 319
},
{
"epoch": 4.096,
"grad_norm": 0.36478829337463853,
"learning_rate": 1.751111045975459e-05,
"loss": 0.1308,
"step": 320
},
{
"epoch": 4.1088,
"grad_norm": 0.4673076443480191,
"learning_rate": 1.738418990102429e-05,
"loss": 0.1682,
"step": 321
},
{
"epoch": 4.1216,
"grad_norm": 0.4130602587529781,
"learning_rate": 1.725737643046266e-05,
"loss": 0.1522,
"step": 322
},
{
"epoch": 4.1344,
"grad_norm": 0.4341361583946463,
"learning_rate": 1.7130675239663033e-05,
"loss": 0.1541,
"step": 323
},
{
"epoch": 4.1472,
"grad_norm": 0.40016423381977084,
"learning_rate": 1.7004091515622173e-05,
"loss": 0.1504,
"step": 324
},
{
"epoch": 4.16,
"grad_norm": 0.42920828279796386,
"learning_rate": 1.6877630440527885e-05,
"loss": 0.1463,
"step": 325
},
{
"epoch": 4.1728,
"grad_norm": 0.4107476302460468,
"learning_rate": 1.675129719154686e-05,
"loss": 0.1712,
"step": 326
},
{
"epoch": 4.1856,
"grad_norm": 0.421702005417959,
"learning_rate": 1.6625096940612758e-05,
"loss": 0.1582,
"step": 327
},
{
"epoch": 4.1984,
"grad_norm": 0.35270460243933205,
"learning_rate": 1.649903485421445e-05,
"loss": 0.1519,
"step": 328
},
{
"epoch": 4.2112,
"grad_norm": 0.3787760485501793,
"learning_rate": 1.6373116093184495e-05,
"loss": 0.152,
"step": 329
},
{
"epoch": 4.224,
"grad_norm": 0.35542585180643543,
"learning_rate": 1.624734581248791e-05,
"loss": 0.1403,
"step": 330
},
{
"epoch": 4.2368,
"grad_norm": 0.36324202783135395,
"learning_rate": 1.6121729161011085e-05,
"loss": 0.1433,
"step": 331
},
{
"epoch": 4.2496,
"grad_norm": 0.3792486507898538,
"learning_rate": 1.5996271281351028e-05,
"loss": 0.1391,
"step": 332
},
{
"epoch": 4.2624,
"grad_norm": 0.3473181132349184,
"learning_rate": 1.587097730960479e-05,
"loss": 0.1251,
"step": 333
},
{
"epoch": 4.2752,
"grad_norm": 0.32774630705591523,
"learning_rate": 1.574585237515925e-05,
"loss": 0.1368,
"step": 334
},
{
"epoch": 4.288,
"grad_norm": 0.36420129915015437,
"learning_rate": 1.5620901600481098e-05,
"loss": 0.1528,
"step": 335
},
{
"epoch": 4.3008,
"grad_norm": 0.3257369647693055,
"learning_rate": 1.5496130100907114e-05,
"loss": 0.1585,
"step": 336
},
{
"epoch": 4.3136,
"grad_norm": 0.31078781425198293,
"learning_rate": 1.5371542984434775e-05,
"loss": 0.1396,
"step": 337
},
{
"epoch": 4.3264,
"grad_norm": 0.35096965427751897,
"learning_rate": 1.5247145351513137e-05,
"loss": 0.1795,
"step": 338
},
{
"epoch": 4.3392,
"grad_norm": 0.31748462140242223,
"learning_rate": 1.5122942294834031e-05,
"loss": 0.1492,
"step": 339
},
{
"epoch": 4.352,
"grad_norm": 0.3592126234671409,
"learning_rate": 1.499893889912354e-05,
"loss": 0.1639,
"step": 340
},
{
"epoch": 4.3648,
"grad_norm": 0.3357832784658898,
"learning_rate": 1.4875140240933886e-05,
"loss": 0.1461,
"step": 341
},
{
"epoch": 4.3776,
"grad_norm": 0.33572402102576526,
"learning_rate": 1.4751551388435576e-05,
"loss": 0.1292,
"step": 342
},
{
"epoch": 4.3904,
"grad_norm": 0.39703969920878845,
"learning_rate": 1.4628177401209916e-05,
"loss": 0.2001,
"step": 343
},
{
"epoch": 4.4032,
"grad_norm": 0.3082100040904492,
"learning_rate": 1.4505023330041879e-05,
"loss": 0.1282,
"step": 344
},
{
"epoch": 4.416,
"grad_norm": 0.35087116310392413,
"learning_rate": 1.4382094216713345e-05,
"loss": 0.1459,
"step": 345
},
{
"epoch": 4.4288,
"grad_norm": 0.34352246467690006,
"learning_rate": 1.4259395093796689e-05,
"loss": 0.1462,
"step": 346
},
{
"epoch": 4.4416,
"grad_norm": 0.3539760852726465,
"learning_rate": 1.4136930984448722e-05,
"loss": 0.1507,
"step": 347
},
{
"epoch": 4.4544,
"grad_norm": 0.33563922640509175,
"learning_rate": 1.4014706902205114e-05,
"loss": 0.1364,
"step": 348
},
{
"epoch": 4.4672,
"grad_norm": 0.3310662314502733,
"learning_rate": 1.3892727850775092e-05,
"loss": 0.1515,
"step": 349
},
{
"epoch": 4.48,
"grad_norm": 0.34201559486194577,
"learning_rate": 1.3770998823836608e-05,
"loss": 0.1606,
"step": 350
},
{
"epoch": 4.4928,
"grad_norm": 0.333112082877024,
"learning_rate": 1.3649524804831915e-05,
"loss": 0.1367,
"step": 351
},
{
"epoch": 4.5056,
"grad_norm": 0.3482364710131343,
"learning_rate": 1.3528310766763544e-05,
"loss": 0.1553,
"step": 352
},
{
"epoch": 4.5184,
"grad_norm": 0.3221419556427051,
"learning_rate": 1.3407361671990717e-05,
"loss": 0.142,
"step": 353
},
{
"epoch": 4.5312,
"grad_norm": 0.3162750341141183,
"learning_rate": 1.3286682472026171e-05,
"loss": 0.1345,
"step": 354
},
{
"epoch": 4.5440000000000005,
"grad_norm": 0.3459384680722617,
"learning_rate": 1.316627810733349e-05,
"loss": 0.15,
"step": 355
},
{
"epoch": 4.5568,
"grad_norm": 0.3088476211153587,
"learning_rate": 1.3046153507124823e-05,
"loss": 0.1353,
"step": 356
},
{
"epoch": 4.5696,
"grad_norm": 0.32355485484922075,
"learning_rate": 1.2926313589159087e-05,
"loss": 0.1416,
"step": 357
},
{
"epoch": 4.5824,
"grad_norm": 0.3172828460504271,
"learning_rate": 1.2806763259540649e-05,
"loss": 0.1455,
"step": 358
},
{
"epoch": 4.5952,
"grad_norm": 0.31594903154371135,
"learning_rate": 1.2687507412518478e-05,
"loss": 0.1425,
"step": 359
},
{
"epoch": 4.608,
"grad_norm": 0.28722609114916,
"learning_rate": 1.256855093028575e-05,
"loss": 0.1251,
"step": 360
},
{
"epoch": 4.6208,
"grad_norm": 0.3494860219590851,
"learning_rate": 1.2449898682780034e-05,
"loss": 0.1643,
"step": 361
},
{
"epoch": 4.6336,
"grad_norm": 0.2792982354613206,
"learning_rate": 1.2331555527483863e-05,
"loss": 0.1238,
"step": 362
},
{
"epoch": 4.6464,
"grad_norm": 0.34708282948447133,
"learning_rate": 1.2213526309225925e-05,
"loss": 0.1572,
"step": 363
},
{
"epoch": 4.6592,
"grad_norm": 0.30907236312253966,
"learning_rate": 1.2095815859982666e-05,
"loss": 0.1457,
"step": 364
},
{
"epoch": 4.672,
"grad_norm": 0.330593410029408,
"learning_rate": 1.1978428998680534e-05,
"loss": 0.1573,
"step": 365
},
{
"epoch": 4.6848,
"grad_norm": 0.3063338936126667,
"learning_rate": 1.1861370530998659e-05,
"loss": 0.1313,
"step": 366
},
{
"epoch": 4.6975999999999996,
"grad_norm": 0.3092050471454206,
"learning_rate": 1.1744645249172122e-05,
"loss": 0.1334,
"step": 367
},
{
"epoch": 4.7104,
"grad_norm": 0.31926202851312846,
"learning_rate": 1.1628257931795774e-05,
"loss": 0.1517,
"step": 368
},
{
"epoch": 4.7232,
"grad_norm": 0.27438667357341145,
"learning_rate": 1.1512213343628602e-05,
"loss": 0.1325,
"step": 369
},
{
"epoch": 4.736,
"grad_norm": 0.30486319248530797,
"learning_rate": 1.1396516235398668e-05,
"loss": 0.141,
"step": 370
},
{
"epoch": 4.7488,
"grad_norm": 0.3277252504475326,
"learning_rate": 1.1281171343608592e-05,
"loss": 0.1589,
"step": 371
},
{
"epoch": 4.7616,
"grad_norm": 0.31380641171615914,
"learning_rate": 1.1166183390341713e-05,
"loss": 0.1539,
"step": 372
},
{
"epoch": 4.7744,
"grad_norm": 0.27802001379095087,
"learning_rate": 1.10515570830687e-05,
"loss": 0.1171,
"step": 373
},
{
"epoch": 4.7872,
"grad_norm": 0.3387070969699864,
"learning_rate": 1.0937297114454867e-05,
"loss": 0.1551,
"step": 374
},
{
"epoch": 4.8,
"grad_norm": 0.3423477879004459,
"learning_rate": 1.082340816216805e-05,
"loss": 0.1816,
"step": 375
},
{
"epoch": 4.8128,
"grad_norm": 0.2835804016433388,
"learning_rate": 1.0709894888687145e-05,
"loss": 0.1219,
"step": 376
},
{
"epoch": 4.8256,
"grad_norm": 0.30445425411648763,
"learning_rate": 1.0596761941111169e-05,
"loss": 0.1438,
"step": 377
},
{
"epoch": 4.8384,
"grad_norm": 0.2974271887909385,
"learning_rate": 1.0484013950969056e-05,
"loss": 0.1448,
"step": 378
},
{
"epoch": 4.8512,
"grad_norm": 0.2829878963033833,
"learning_rate": 1.0371655534030061e-05,
"loss": 0.1394,
"step": 379
},
{
"epoch": 4.864,
"grad_norm": 0.3168908715483024,
"learning_rate": 1.0259691290114744e-05,
"loss": 0.1482,
"step": 380
},
{
"epoch": 4.8768,
"grad_norm": 0.2902424139282325,
"learning_rate": 1.0148125802906704e-05,
"loss": 0.1309,
"step": 381
},
{
"epoch": 4.8896,
"grad_norm": 0.28123559328151027,
"learning_rate": 1.0036963639764892e-05,
"loss": 0.1391,
"step": 382
},
{
"epoch": 4.9024,
"grad_norm": 0.3355658849713151,
"learning_rate": 9.92620935153669e-06,
"loss": 0.1593,
"step": 383
},
{
"epoch": 4.9152000000000005,
"grad_norm": 0.27897881946986414,
"learning_rate": 9.815867472371515e-06,
"loss": 0.1333,
"step": 384
},
{
"epoch": 4.928,
"grad_norm": 0.3183236125485041,
"learning_rate": 9.705942519535284e-06,
"loss": 0.1506,
"step": 385
},
{
"epoch": 4.9408,
"grad_norm": 0.3049827192706868,
"learning_rate": 9.59643899322542e-06,
"loss": 0.1509,
"step": 386
},
{
"epoch": 4.9536,
"grad_norm": 0.2858699032372514,
"learning_rate": 9.487361376386661e-06,
"loss": 0.1308,
"step": 387
},
{
"epoch": 4.9664,
"grad_norm": 0.2913513182816591,
"learning_rate": 9.378714134527503e-06,
"loss": 0.1438,
"step": 388
},
{
"epoch": 4.9792,
"grad_norm": 0.3053549644512981,
"learning_rate": 9.270501715537392e-06,
"loss": 0.1525,
"step": 389
},
{
"epoch": 4.992,
"grad_norm": 0.3132718395321514,
"learning_rate": 9.162728549504675e-06,
"loss": 0.1439,
"step": 390
},
{
"epoch": 5.0048,
"grad_norm": 0.8707671150228724,
"learning_rate": 9.055399048535153e-06,
"loss": 0.1964,
"step": 391
},
{
"epoch": 5.0176,
"grad_norm": 0.39054630324184525,
"learning_rate": 8.948517606571548e-06,
"loss": 0.0856,
"step": 392
},
{
"epoch": 5.0304,
"grad_norm": 0.38007443731247337,
"learning_rate": 8.842088599213545e-06,
"loss": 0.097,
"step": 393
},
{
"epoch": 5.0432,
"grad_norm": 0.30708666949205676,
"learning_rate": 8.736116383538726e-06,
"loss": 0.0855,
"step": 394
},
{
"epoch": 5.056,
"grad_norm": 0.36470044425057635,
"learning_rate": 8.630605297924132e-06,
"loss": 0.075,
"step": 395
},
{
"epoch": 5.0688,
"grad_norm": 0.4634764402379278,
"learning_rate": 8.525559661868692e-06,
"loss": 0.0828,
"step": 396
},
{
"epoch": 5.0816,
"grad_norm": 0.37047664644415645,
"learning_rate": 8.420983775816402e-06,
"loss": 0.0818,
"step": 397
},
{
"epoch": 5.0944,
"grad_norm": 0.33388419569865535,
"learning_rate": 8.316881920980207e-06,
"loss": 0.0967,
"step": 398
},
{
"epoch": 5.1072,
"grad_norm": 0.29708449854774804,
"learning_rate": 8.213258359166823e-06,
"loss": 0.0873,
"step": 399
},
{
"epoch": 5.12,
"grad_norm": 0.323665531189395,
"learning_rate": 8.110117332602175e-06,
"loss": 0.1032,
"step": 400
},
{
"epoch": 5.1328,
"grad_norm": 0.3328853139713512,
"learning_rate": 8.0074630637578e-06,
"loss": 0.0926,
"step": 401
},
{
"epoch": 5.1456,
"grad_norm": 0.2581244268581389,
"learning_rate": 7.905299755177929e-06,
"loss": 0.0683,
"step": 402
},
{
"epoch": 5.1584,
"grad_norm": 0.3058625811208563,
"learning_rate": 7.803631589307458e-06,
"loss": 0.0955,
"step": 403
},
{
"epoch": 5.1712,
"grad_norm": 0.2980858661173279,
"learning_rate": 7.702462728320759e-06,
"loss": 0.0855,
"step": 404
},
{
"epoch": 5.184,
"grad_norm": 0.2926274107334555,
"learning_rate": 7.601797313951198e-06,
"loss": 0.0766,
"step": 405
},
{
"epoch": 5.1968,
"grad_norm": 0.34341674424270835,
"learning_rate": 7.501639467321688e-06,
"loss": 0.0922,
"step": 406
},
{
"epoch": 5.2096,
"grad_norm": 0.28146578162575314,
"learning_rate": 7.401993288775888e-06,
"loss": 0.0864,
"step": 407
},
{
"epoch": 5.2224,
"grad_norm": 0.3091916861391297,
"learning_rate": 7.3028628577103754e-06,
"loss": 0.0908,
"step": 408
},
{
"epoch": 5.2352,
"grad_norm": 0.27533725921725816,
"learning_rate": 7.204252232407638e-06,
"loss": 0.0831,
"step": 409
},
{
"epoch": 5.248,
"grad_norm": 0.2929332015338904,
"learning_rate": 7.106165449869946e-06,
"loss": 0.0883,
"step": 410
},
{
"epoch": 5.2608,
"grad_norm": 0.27623225456083456,
"learning_rate": 7.008606525654045e-06,
"loss": 0.0782,
"step": 411
},
{
"epoch": 5.2736,
"grad_norm": 0.288011722575726,
"learning_rate": 6.911579453706787e-06,
"loss": 0.0799,
"step": 412
},
{
"epoch": 5.2864,
"grad_norm": 0.2808173486775667,
"learning_rate": 6.815088206201648e-06,
"loss": 0.084,
"step": 413
},
{
"epoch": 5.2992,
"grad_norm": 0.2769334215855372,
"learning_rate": 6.719136733376057e-06,
"loss": 0.0897,
"step": 414
},
{
"epoch": 5.312,
"grad_norm": 0.2640890010895359,
"learning_rate": 6.623728963369715e-06,
"loss": 0.0785,
"step": 415
},
{
"epoch": 5.3248,
"grad_norm": 0.28366255851169087,
"learning_rate": 6.528868802063774e-06,
"loss": 0.0861,
"step": 416
},
{
"epoch": 5.3376,
"grad_norm": 0.26612785503838554,
"learning_rate": 6.434560132920944e-06,
"loss": 0.0726,
"step": 417
},
{
"epoch": 5.3504,
"grad_norm": 0.2566370337258043,
"learning_rate": 6.340806816826486e-06,
"loss": 0.0719,
"step": 418
},
{
"epoch": 5.3632,
"grad_norm": 0.2802651648602639,
"learning_rate": 6.2476126919301604e-06,
"loss": 0.0849,
"step": 419
},
{
"epoch": 5.376,
"grad_norm": 0.26234153435624524,
"learning_rate": 6.154981573489125e-06,
"loss": 0.0861,
"step": 420
},
{
"epoch": 5.3888,
"grad_norm": 0.25013916978026923,
"learning_rate": 6.062917253711697e-06,
"loss": 0.0759,
"step": 421
},
{
"epoch": 5.4016,
"grad_norm": 0.2782322390161653,
"learning_rate": 5.971423501602136e-06,
"loss": 0.0975,
"step": 422
},
{
"epoch": 5.4144,
"grad_norm": 0.25853590872421234,
"learning_rate": 5.880504062806329e-06,
"loss": 0.0776,
"step": 423
},
{
"epoch": 5.4272,
"grad_norm": 0.2632918340497073,
"learning_rate": 5.790162659458478e-06,
"loss": 0.0793,
"step": 424
},
{
"epoch": 5.44,
"grad_norm": 0.2807515354914946,
"learning_rate": 5.700402990028675e-06,
"loss": 0.0926,
"step": 425
},
{
"epoch": 5.4528,
"grad_norm": 0.2701285303742261,
"learning_rate": 5.611228729171516e-06,
"loss": 0.0907,
"step": 426
},
{
"epoch": 5.4656,
"grad_norm": 0.23610290783563515,
"learning_rate": 5.522643527575682e-06,
"loss": 0.0655,
"step": 427
},
{
"epoch": 5.4784,
"grad_norm": 0.2799093514778747,
"learning_rate": 5.434651011814447e-06,
"loss": 0.0859,
"step": 428
},
{
"epoch": 5.4912,
"grad_norm": 0.23884787730117085,
"learning_rate": 5.347254784197233e-06,
"loss": 0.0665,
"step": 429
},
{
"epoch": 5.504,
"grad_norm": 0.24803806185942293,
"learning_rate": 5.260458422622128e-06,
"loss": 0.0706,
"step": 430
},
{
"epoch": 5.5168,
"grad_norm": 0.24986860431317282,
"learning_rate": 5.1742654804294346e-06,
"loss": 0.0733,
"step": 431
},
{
"epoch": 5.5296,
"grad_norm": 0.25232462132822314,
"learning_rate": 5.088679486256141e-06,
"loss": 0.0841,
"step": 432
},
{
"epoch": 5.5424,
"grad_norm": 0.26863695864156556,
"learning_rate": 5.003703943891545e-06,
"loss": 0.0909,
"step": 433
},
{
"epoch": 5.5552,
"grad_norm": 0.26379924980992814,
"learning_rate": 4.919342332133738e-06,
"loss": 0.0802,
"step": 434
},
{
"epoch": 5.568,
"grad_norm": 0.25337851637428144,
"learning_rate": 4.835598104647243e-06,
"loss": 0.0784,
"step": 435
},
{
"epoch": 5.5808,
"grad_norm": 0.2855931530520814,
"learning_rate": 4.752474689821587e-06,
"loss": 0.0905,
"step": 436
},
{
"epoch": 5.5936,
"grad_norm": 0.2653743725914835,
"learning_rate": 4.669975490630956e-06,
"loss": 0.09,
"step": 437
},
{
"epoch": 5.6064,
"grad_norm": 0.24324675052642777,
"learning_rate": 4.588103884494914e-06,
"loss": 0.0779,
"step": 438
},
{
"epoch": 5.6192,
"grad_norm": 0.28836723375731815,
"learning_rate": 4.50686322314007e-06,
"loss": 0.0899,
"step": 439
},
{
"epoch": 5.632,
"grad_norm": 0.27824379721099174,
"learning_rate": 4.426256832462936e-06,
"loss": 0.0819,
"step": 440
},
{
"epoch": 5.6448,
"grad_norm": 0.25867262760227655,
"learning_rate": 4.346288012393707e-06,
"loss": 0.0796,
"step": 441
},
{
"epoch": 5.6576,
"grad_norm": 0.2540036528454018,
"learning_rate": 4.266960036761216e-06,
"loss": 0.0772,
"step": 442
},
{
"epoch": 5.6704,
"grad_norm": 0.2403694214215447,
"learning_rate": 4.188276153158866e-06,
"loss": 0.0785,
"step": 443
},
{
"epoch": 5.6832,
"grad_norm": 0.2719134198375216,
"learning_rate": 4.110239582811693e-06,
"loss": 0.0893,
"step": 444
},
{
"epoch": 5.696,
"grad_norm": 0.22647867415580442,
"learning_rate": 4.032853520444518e-06,
"loss": 0.0672,
"step": 445
},
{
"epoch": 5.7088,
"grad_norm": 0.27361004742591205,
"learning_rate": 3.9561211341510945e-06,
"loss": 0.0958,
"step": 446
},
{
"epoch": 5.7216000000000005,
"grad_norm": 0.2768586626290287,
"learning_rate": 3.880045565264496e-06,
"loss": 0.0845,
"step": 447
},
{
"epoch": 5.7344,
"grad_norm": 0.24049847606098695,
"learning_rate": 3.804629928228438e-06,
"loss": 0.0826,
"step": 448
},
{
"epoch": 5.7472,
"grad_norm": 0.2647770307338421,
"learning_rate": 3.7298773104698273e-06,
"loss": 0.0872,
"step": 449
},
{
"epoch": 5.76,
"grad_norm": 0.24567196188345414,
"learning_rate": 3.655790772272332e-06,
"loss": 0.072,
"step": 450
},
{
"epoch": 5.7728,
"grad_norm": 0.25557146471035863,
"learning_rate": 3.582373346651111e-06,
"loss": 0.0845,
"step": 451
},
{
"epoch": 5.7856,
"grad_norm": 0.24864423351249698,
"learning_rate": 3.5096280392286676e-06,
"loss": 0.0821,
"step": 452
},
{
"epoch": 5.7984,
"grad_norm": 0.2629783009150278,
"learning_rate": 3.437557828111746e-06,
"loss": 0.0954,
"step": 453
},
{
"epoch": 5.8112,
"grad_norm": 0.2435300816146765,
"learning_rate": 3.366165663769483e-06,
"loss": 0.0795,
"step": 454
},
{
"epoch": 5.824,
"grad_norm": 0.2536128868225129,
"learning_rate": 3.2954544689125578e-06,
"loss": 0.0829,
"step": 455
},
{
"epoch": 5.8368,
"grad_norm": 0.26326100623271814,
"learning_rate": 3.225427138373589e-06,
"loss": 0.0858,
"step": 456
},
{
"epoch": 5.8496,
"grad_norm": 0.24822954283948143,
"learning_rate": 3.156086538988563e-06,
"loss": 0.0725,
"step": 457
},
{
"epoch": 5.8624,
"grad_norm": 0.24403030181937907,
"learning_rate": 3.0874355094795484e-06,
"loss": 0.083,
"step": 458
},
{
"epoch": 5.8751999999999995,
"grad_norm": 0.30479561935813754,
"learning_rate": 3.0194768603384083e-06,
"loss": 0.0941,
"step": 459
},
{
"epoch": 5.888,
"grad_norm": 0.26001164187141773,
"learning_rate": 2.952213373711783e-06,
"loss": 0.0799,
"step": 460
},
{
"epoch": 5.9008,
"grad_norm": 0.26744959620234826,
"learning_rate": 2.8856478032871906e-06,
"loss": 0.086,
"step": 461
},
{
"epoch": 5.9136,
"grad_norm": 0.2479889061044048,
"learning_rate": 2.819782874180277e-06,
"loss": 0.0824,
"step": 462
},
{
"epoch": 5.9264,
"grad_norm": 0.2522879651320666,
"learning_rate": 2.75462128282326e-06,
"loss": 0.0751,
"step": 463
},
{
"epoch": 5.9392,
"grad_norm": 0.24943472624291574,
"learning_rate": 2.6901656968545455e-06,
"loss": 0.0798,
"step": 464
},
{
"epoch": 5.952,
"grad_norm": 0.2377282733369092,
"learning_rate": 2.626418755009523e-06,
"loss": 0.0787,
"step": 465
},
{
"epoch": 5.9648,
"grad_norm": 0.25278482416359105,
"learning_rate": 2.563383067012519e-06,
"loss": 0.0816,
"step": 466
},
{
"epoch": 5.9776,
"grad_norm": 0.2606783205225798,
"learning_rate": 2.5010612134699706e-06,
"loss": 0.0965,
"step": 467
},
{
"epoch": 5.9904,
"grad_norm": 0.25250470215575255,
"learning_rate": 2.4394557457647894e-06,
"loss": 0.0974,
"step": 468
},
{
"epoch": 6.0032,
"grad_norm": 0.6307515992424928,
"learning_rate": 2.3785691859518824e-06,
"loss": 0.1148,
"step": 469
},
{
"epoch": 6.016,
"grad_norm": 0.31873807207565263,
"learning_rate": 2.318404026654928e-06,
"loss": 0.0587,
"step": 470
},
{
"epoch": 6.0288,
"grad_norm": 0.24869481585780664,
"learning_rate": 2.2589627309643182e-06,
"loss": 0.0515,
"step": 471
},
{
"epoch": 6.0416,
"grad_norm": 0.2624844971478034,
"learning_rate": 2.2002477323363314e-06,
"loss": 0.0604,
"step": 472
},
{
"epoch": 6.0544,
"grad_norm": 0.2067843885434314,
"learning_rate": 2.1422614344935e-06,
"loss": 0.0491,
"step": 473
},
{
"epoch": 6.0672,
"grad_norm": 0.21301266282959322,
"learning_rate": 2.0850062113262014e-06,
"loss": 0.0602,
"step": 474
},
{
"epoch": 6.08,
"grad_norm": 0.23913788889439205,
"learning_rate": 2.0284844067955013e-06,
"loss": 0.0582,
"step": 475
},
{
"epoch": 6.0928,
"grad_norm": 0.24737157702610824,
"learning_rate": 1.972698334837155e-06,
"loss": 0.0552,
"step": 476
},
{
"epoch": 6.1056,
"grad_norm": 0.2830484576941645,
"learning_rate": 1.9176502792669048e-06,
"loss": 0.0598,
"step": 477
},
{
"epoch": 6.1184,
"grad_norm": 0.29743523726617643,
"learning_rate": 1.8633424936869747e-06,
"loss": 0.0659,
"step": 478
},
{
"epoch": 6.1312,
"grad_norm": 0.2508507804956114,
"learning_rate": 1.8097772013938187e-06,
"loss": 0.0526,
"step": 479
},
{
"epoch": 6.144,
"grad_norm": 0.27920118945455913,
"learning_rate": 1.756956595287085e-06,
"loss": 0.0633,
"step": 480
},
{
"epoch": 6.1568,
"grad_norm": 0.22698911436680633,
"learning_rate": 1.7048828377798531e-06,
"loss": 0.0509,
"step": 481
},
{
"epoch": 6.1696,
"grad_norm": 0.21351689251879283,
"learning_rate": 1.6535580607101055e-06,
"loss": 0.0533,
"step": 482
},
{
"epoch": 6.1824,
"grad_norm": 0.2134241611710577,
"learning_rate": 1.6029843652534571e-06,
"loss": 0.059,
"step": 483
},
{
"epoch": 6.1952,
"grad_norm": 0.2089174965210443,
"learning_rate": 1.553163821837127e-06,
"loss": 0.0527,
"step": 484
},
{
"epoch": 6.208,
"grad_norm": 0.21694868914769955,
"learning_rate": 1.5040984700551752e-06,
"loss": 0.0593,
"step": 485
},
{
"epoch": 6.2208,
"grad_norm": 0.2247435527500204,
"learning_rate": 1.4557903185850308e-06,
"loss": 0.0618,
"step": 486
},
{
"epoch": 6.2336,
"grad_norm": 0.19569237729410577,
"learning_rate": 1.4082413451052058e-06,
"loss": 0.0534,
"step": 487
},
{
"epoch": 6.2464,
"grad_norm": 0.21659528175315748,
"learning_rate": 1.3614534962143932e-06,
"loss": 0.0624,
"step": 488
},
{
"epoch": 6.2592,
"grad_norm": 0.1920895954701789,
"learning_rate": 1.3154286873517318e-06,
"loss": 0.0468,
"step": 489
},
{
"epoch": 6.272,
"grad_norm": 0.21069873163924976,
"learning_rate": 1.2701688027184123e-06,
"loss": 0.0549,
"step": 490
},
{
"epoch": 6.2848,
"grad_norm": 0.21095594160716954,
"learning_rate": 1.22567569520053e-06,
"loss": 0.0598,
"step": 491
},
{
"epoch": 6.2976,
"grad_norm": 0.21732951466081074,
"learning_rate": 1.1819511862932242e-06,
"loss": 0.0583,
"step": 492
},
{
"epoch": 6.3104,
"grad_norm": 0.199756792134096,
"learning_rate": 1.1389970660261396e-06,
"loss": 0.0535,
"step": 493
},
{
"epoch": 6.3232,
"grad_norm": 0.2080483888215097,
"learning_rate": 1.0968150928900912e-06,
"loss": 0.0588,
"step": 494
},
{
"epoch": 6.336,
"grad_norm": 0.22078274255706784,
"learning_rate": 1.0554069937651335e-06,
"loss": 0.0612,
"step": 495
},
{
"epoch": 6.3488,
"grad_norm": 0.21284506643865078,
"learning_rate": 1.0147744638498146e-06,
"loss": 0.0599,
"step": 496
},
{
"epoch": 6.3616,
"grad_norm": 0.1939478710319105,
"learning_rate": 9.749191665918122e-07,
"loss": 0.05,
"step": 497
},
{
"epoch": 6.3744,
"grad_norm": 0.21905210500235428,
"learning_rate": 9.358427336198073e-07,
"loss": 0.061,
"step": 498
},
{
"epoch": 6.3872,
"grad_norm": 0.20367086506090404,
"learning_rate": 8.975467646767045e-07,
"loss": 0.0429,
"step": 499
},
{
"epoch": 6.4,
"grad_norm": 0.2204978599221063,
"learning_rate": 8.600328275541425e-07,
"loss": 0.0632,
"step": 500
},
{
"epoch": 6.4128,
"grad_norm": 0.19657411605198546,
"learning_rate": 8.233024580282811e-07,
"loss": 0.0486,
"step": 501
},
{
"epoch": 6.4256,
"grad_norm": 0.1929878032267413,
"learning_rate": 7.873571597969753e-07,
"loss": 0.0512,
"step": 502
},
{
"epoch": 6.4384,
"grad_norm": 0.21297734998628096,
"learning_rate": 7.521984044181763e-07,
"loss": 0.061,
"step": 503
},
{
"epoch": 6.4512,
"grad_norm": 0.2036017581226651,
"learning_rate": 7.178276312497101e-07,
"loss": 0.0549,
"step": 504
},
{
"epoch": 6.464,
"grad_norm": 0.2157949678208667,
"learning_rate": 6.842462473903299e-07,
"loss": 0.059,
"step": 505
},
{
"epoch": 6.4768,
"grad_norm": 0.19947687051049257,
"learning_rate": 6.51455627622144e-07,
"loss": 0.0536,
"step": 506
},
{
"epoch": 6.4896,
"grad_norm": 0.21745771596116842,
"learning_rate": 6.194571143543027e-07,
"loss": 0.0612,
"step": 507
},
{
"epoch": 6.5024,
"grad_norm": 0.2101529082646709,
"learning_rate": 5.882520175680539e-07,
"loss": 0.0505,
"step": 508
},
{
"epoch": 6.5152,
"grad_norm": 0.19411610830588563,
"learning_rate": 5.578416147631216e-07,
"loss": 0.0447,
"step": 509
},
{
"epoch": 6.5280000000000005,
"grad_norm": 0.22526486934316098,
"learning_rate": 5.282271509053916e-07,
"loss": 0.0615,
"step": 510
},
{
"epoch": 6.5408,
"grad_norm": 0.20270004269056,
"learning_rate": 4.994098383759571e-07,
"loss": 0.0528,
"step": 511
},
{
"epoch": 6.5536,
"grad_norm": 0.20352924552183632,
"learning_rate": 4.71390856921472e-07,
"loss": 0.0499,
"step": 512
},
{
"epoch": 6.5664,
"grad_norm": 0.20082311361176847,
"learning_rate": 4.441713536058734e-07,
"loss": 0.0535,
"step": 513
},
{
"epoch": 6.5792,
"grad_norm": 0.19152806714606765,
"learning_rate": 4.177524427633972e-07,
"loss": 0.0479,
"step": 514
},
{
"epoch": 6.592,
"grad_norm": 0.20900178436356592,
"learning_rate": 3.9213520595297484e-07,
"loss": 0.0539,
"step": 515
},
{
"epoch": 6.6048,
"grad_norm": 0.2154189515893567,
"learning_rate": 3.673206919139616e-07,
"loss": 0.0583,
"step": 516
},
{
"epoch": 6.6176,
"grad_norm": 0.20160762615144787,
"learning_rate": 3.4330991652317793e-07,
"loss": 0.06,
"step": 517
},
{
"epoch": 6.6304,
"grad_norm": 0.21267833321164703,
"learning_rate": 3.201038627533448e-07,
"loss": 0.061,
"step": 518
},
{
"epoch": 6.6432,
"grad_norm": 0.19672661747979087,
"learning_rate": 2.977034806328294e-07,
"loss": 0.0487,
"step": 519
},
{
"epoch": 6.656,
"grad_norm": 0.21364651184647268,
"learning_rate": 2.7610968720675813e-07,
"loss": 0.0602,
"step": 520
},
{
"epoch": 6.6688,
"grad_norm": 0.21531511298839284,
"learning_rate": 2.553233664994692e-07,
"loss": 0.0547,
"step": 521
},
{
"epoch": 6.6815999999999995,
"grad_norm": 0.19923340943076429,
"learning_rate": 2.3534536947832364e-07,
"loss": 0.0515,
"step": 522
},
{
"epoch": 6.6944,
"grad_norm": 0.2063755392379561,
"learning_rate": 2.1617651401886875e-07,
"loss": 0.0553,
"step": 523
},
{
"epoch": 6.7072,
"grad_norm": 0.20324639288183224,
"learning_rate": 1.9781758487135373e-07,
"loss": 0.0511,
"step": 524
},
{
"epoch": 6.72,
"grad_norm": 0.21382930992061455,
"learning_rate": 1.8026933362859988e-07,
"loss": 0.0617,
"step": 525
},
{
"epoch": 6.7328,
"grad_norm": 0.20091432072129906,
"learning_rate": 1.635324786952408e-07,
"loss": 0.056,
"step": 526
},
{
"epoch": 6.7456,
"grad_norm": 0.20499113368449215,
"learning_rate": 1.476077052583036e-07,
"loss": 0.0548,
"step": 527
},
{
"epoch": 6.7584,
"grad_norm": 0.19997098829776122,
"learning_rate": 1.3249566525916024e-07,
"loss": 0.0515,
"step": 528
},
{
"epoch": 6.7712,
"grad_norm": 0.19730024827668835,
"learning_rate": 1.1819697736683567e-07,
"loss": 0.0555,
"step": 529
},
{
"epoch": 6.784,
"grad_norm": 0.18914493404170932,
"learning_rate": 1.0471222695268346e-07,
"loss": 0.0479,
"step": 530
},
{
"epoch": 6.7968,
"grad_norm": 0.2001098720255446,
"learning_rate": 9.204196606642512e-08,
"loss": 0.0522,
"step": 531
},
{
"epoch": 6.8096,
"grad_norm": 0.19566555347609557,
"learning_rate": 8.018671341353702e-08,
"loss": 0.0501,
"step": 532
},
{
"epoch": 6.8224,
"grad_norm": 0.20308185664037973,
"learning_rate": 6.914695433403174e-08,
"loss": 0.0582,
"step": 533
},
{
"epoch": 6.8352,
"grad_norm": 0.2021394190243187,
"learning_rate": 5.8923140782574106e-08,
"loss": 0.0602,
"step": 534
},
{
"epoch": 6.848,
"grad_norm": 0.20063291184587487,
"learning_rate": 4.951569130998479e-08,
"loss": 0.0517,
"step": 535
},
{
"epoch": 6.8608,
"grad_norm": 0.21687113775307834,
"learning_rate": 4.092499104611403e-08,
"loss": 0.0645,
"step": 536
},
{
"epoch": 6.8736,
"grad_norm": 0.20473541823298777,
"learning_rate": 3.315139168405423e-08,
"loss": 0.0457,
"step": 537
},
{
"epoch": 6.8864,
"grad_norm": 0.21253873775704507,
"learning_rate": 2.619521146576487e-08,
"loss": 0.0552,
"step": 538
},
{
"epoch": 6.8992,
"grad_norm": 0.19677860005085293,
"learning_rate": 2.0056735169025064e-08,
"loss": 0.0521,
"step": 539
},
{
"epoch": 6.912,
"grad_norm": 0.2130449480569404,
"learning_rate": 1.4736214095789625e-08,
"loss": 0.0604,
"step": 540
},
{
"epoch": 6.9248,
"grad_norm": 0.2057866822827188,
"learning_rate": 1.0233866061892806e-08,
"loss": 0.0563,
"step": 541
},
{
"epoch": 6.9376,
"grad_norm": 0.20786044919437346,
"learning_rate": 6.54987538813101e-09,
"loss": 0.0511,
"step": 542
},
{
"epoch": 6.9504,
"grad_norm": 0.20591521352687323,
"learning_rate": 3.6843928927221552e-09,
"loss": 0.0525,
"step": 543
},
{
"epoch": 6.9632,
"grad_norm": 0.1932156399001302,
"learning_rate": 1.6375358851261625e-09,
"loss": 0.0528,
"step": 544
},
{
"epoch": 6.976,
"grad_norm": 0.21810263966806365,
"learning_rate": 4.0938816124880263e-10,
"loss": 0.0587,
"step": 545
},
{
"epoch": 6.9888,
"grad_norm": 0.19749085938012026,
"learning_rate": 0.0,
"loss": 0.0537,
"step": 546
},
{
"epoch": 6.9888,
"step": 546,
"total_flos": 1.3527969808368271e+18,
"train_loss": 0.27728078796804606,
"train_runtime": 40114.8445,
"train_samples_per_second": 1.744,
"train_steps_per_second": 0.014
}
],
"logging_steps": 1.0,
"max_steps": 546,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.3527969808368271e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}