Files
ModelHub XC dc00b8786e 初始化项目,由ModelHub XC社区提供模型
Model: longtermrisk/Qwen2.5-7B-Instruct-ftjob-bf700f8824c9
Source: Original Platform
2026-05-12 00:48:13 +08:00

2226 lines
50 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 313,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0032,
"grad_norm": 9.548905372619629,
"learning_rate": 0.0,
"loss": 1.6041,
"step": 1
},
{
"epoch": 0.0064,
"grad_norm": 8.360369682312012,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.43,
"step": 2
},
{
"epoch": 0.0096,
"grad_norm": 9.501611709594727,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6751,
"step": 3
},
{
"epoch": 0.0128,
"grad_norm": 8.665339469909668,
"learning_rate": 6e-06,
"loss": 1.6014,
"step": 4
},
{
"epoch": 0.016,
"grad_norm": 6.536843776702881,
"learning_rate": 8.000000000000001e-06,
"loss": 1.3807,
"step": 5
},
{
"epoch": 0.0192,
"grad_norm": 3.9980669021606445,
"learning_rate": 1e-05,
"loss": 1.2621,
"step": 6
},
{
"epoch": 0.0224,
"grad_norm": 2.882711172103882,
"learning_rate": 9.967532467532468e-06,
"loss": 1.3812,
"step": 7
},
{
"epoch": 0.0256,
"grad_norm": 2.067737340927124,
"learning_rate": 9.935064935064936e-06,
"loss": 1.1674,
"step": 8
},
{
"epoch": 0.0288,
"grad_norm": 2.1736371517181396,
"learning_rate": 9.902597402597403e-06,
"loss": 1.2078,
"step": 9
},
{
"epoch": 0.032,
"grad_norm": 2.2333147525787354,
"learning_rate": 9.87012987012987e-06,
"loss": 1.2477,
"step": 10
},
{
"epoch": 0.0352,
"grad_norm": 1.869605541229248,
"learning_rate": 9.837662337662337e-06,
"loss": 1.1323,
"step": 11
},
{
"epoch": 0.0384,
"grad_norm": 1.9734994173049927,
"learning_rate": 9.805194805194806e-06,
"loss": 1.258,
"step": 12
},
{
"epoch": 0.0416,
"grad_norm": 2.027984142303467,
"learning_rate": 9.772727272727273e-06,
"loss": 1.1692,
"step": 13
},
{
"epoch": 0.0448,
"grad_norm": 1.8902798891067505,
"learning_rate": 9.740259740259742e-06,
"loss": 1.1181,
"step": 14
},
{
"epoch": 0.048,
"grad_norm": 1.6616740226745605,
"learning_rate": 9.707792207792209e-06,
"loss": 1.1082,
"step": 15
},
{
"epoch": 0.0512,
"grad_norm": 2.1065773963928223,
"learning_rate": 9.675324675324677e-06,
"loss": 1.0953,
"step": 16
},
{
"epoch": 0.0544,
"grad_norm": 1.6929274797439575,
"learning_rate": 9.642857142857144e-06,
"loss": 0.9976,
"step": 17
},
{
"epoch": 0.0576,
"grad_norm": 1.7909464836120605,
"learning_rate": 9.610389610389611e-06,
"loss": 1.0779,
"step": 18
},
{
"epoch": 0.0608,
"grad_norm": 1.987488031387329,
"learning_rate": 9.577922077922078e-06,
"loss": 1.0974,
"step": 19
},
{
"epoch": 0.064,
"grad_norm": 1.535858154296875,
"learning_rate": 9.545454545454547e-06,
"loss": 1.0124,
"step": 20
},
{
"epoch": 0.0672,
"grad_norm": 1.6738166809082031,
"learning_rate": 9.512987012987014e-06,
"loss": 0.9932,
"step": 21
},
{
"epoch": 0.0704,
"grad_norm": 1.4918556213378906,
"learning_rate": 9.48051948051948e-06,
"loss": 0.9481,
"step": 22
},
{
"epoch": 0.0736,
"grad_norm": 1.652398705482483,
"learning_rate": 9.448051948051948e-06,
"loss": 0.9542,
"step": 23
},
{
"epoch": 0.0768,
"grad_norm": 1.567749261856079,
"learning_rate": 9.415584415584416e-06,
"loss": 0.8848,
"step": 24
},
{
"epoch": 0.08,
"grad_norm": 1.6268699169158936,
"learning_rate": 9.383116883116883e-06,
"loss": 1.0485,
"step": 25
},
{
"epoch": 0.0832,
"grad_norm": 1.528889775276184,
"learning_rate": 9.350649350649352e-06,
"loss": 0.941,
"step": 26
},
{
"epoch": 0.0864,
"grad_norm": 1.8066990375518799,
"learning_rate": 9.318181818181819e-06,
"loss": 1.0402,
"step": 27
},
{
"epoch": 0.0896,
"grad_norm": 1.2178040742874146,
"learning_rate": 9.285714285714288e-06,
"loss": 0.9057,
"step": 28
},
{
"epoch": 0.0928,
"grad_norm": 1.5407291650772095,
"learning_rate": 9.253246753246755e-06,
"loss": 0.921,
"step": 29
},
{
"epoch": 0.096,
"grad_norm": 1.5522805452346802,
"learning_rate": 9.220779220779221e-06,
"loss": 0.9231,
"step": 30
},
{
"epoch": 0.0992,
"grad_norm": 1.1725654602050781,
"learning_rate": 9.188311688311688e-06,
"loss": 0.7628,
"step": 31
},
{
"epoch": 0.1024,
"grad_norm": 1.5114904642105103,
"learning_rate": 9.155844155844157e-06,
"loss": 0.8904,
"step": 32
},
{
"epoch": 0.1056,
"grad_norm": 2.2382700443267822,
"learning_rate": 9.123376623376624e-06,
"loss": 1.0447,
"step": 33
},
{
"epoch": 0.1088,
"grad_norm": 1.2792514562606812,
"learning_rate": 9.090909090909091e-06,
"loss": 0.8466,
"step": 34
},
{
"epoch": 0.112,
"grad_norm": 1.5901352167129517,
"learning_rate": 9.05844155844156e-06,
"loss": 0.8383,
"step": 35
},
{
"epoch": 0.1152,
"grad_norm": 1.8127880096435547,
"learning_rate": 9.025974025974027e-06,
"loss": 0.9088,
"step": 36
},
{
"epoch": 0.1184,
"grad_norm": 1.3327851295471191,
"learning_rate": 8.993506493506494e-06,
"loss": 0.8263,
"step": 37
},
{
"epoch": 0.1216,
"grad_norm": 1.2125405073165894,
"learning_rate": 8.96103896103896e-06,
"loss": 0.846,
"step": 38
},
{
"epoch": 0.1248,
"grad_norm": 1.4686274528503418,
"learning_rate": 8.92857142857143e-06,
"loss": 0.9285,
"step": 39
},
{
"epoch": 0.128,
"grad_norm": 1.7080440521240234,
"learning_rate": 8.896103896103896e-06,
"loss": 0.9183,
"step": 40
},
{
"epoch": 0.1312,
"grad_norm": 1.402506709098816,
"learning_rate": 8.863636363636365e-06,
"loss": 0.7918,
"step": 41
},
{
"epoch": 0.1344,
"grad_norm": 1.311579942703247,
"learning_rate": 8.831168831168832e-06,
"loss": 0.8007,
"step": 42
},
{
"epoch": 0.1376,
"grad_norm": 1.3540467023849487,
"learning_rate": 8.7987012987013e-06,
"loss": 0.792,
"step": 43
},
{
"epoch": 0.1408,
"grad_norm": 1.3443299531936646,
"learning_rate": 8.766233766233767e-06,
"loss": 0.8446,
"step": 44
},
{
"epoch": 0.144,
"grad_norm": 1.6124398708343506,
"learning_rate": 8.733766233766234e-06,
"loss": 0.873,
"step": 45
},
{
"epoch": 0.1472,
"grad_norm": 1.4039077758789062,
"learning_rate": 8.701298701298701e-06,
"loss": 0.9067,
"step": 46
},
{
"epoch": 0.1504,
"grad_norm": 1.3932620286941528,
"learning_rate": 8.66883116883117e-06,
"loss": 0.7678,
"step": 47
},
{
"epoch": 0.1536,
"grad_norm": 1.4655569791793823,
"learning_rate": 8.636363636363637e-06,
"loss": 0.8846,
"step": 48
},
{
"epoch": 0.1568,
"grad_norm": 1.6178548336029053,
"learning_rate": 8.603896103896104e-06,
"loss": 0.8972,
"step": 49
},
{
"epoch": 0.16,
"grad_norm": 1.2229878902435303,
"learning_rate": 8.571428571428571e-06,
"loss": 0.7186,
"step": 50
},
{
"epoch": 0.1632,
"grad_norm": 1.399183988571167,
"learning_rate": 8.53896103896104e-06,
"loss": 0.8156,
"step": 51
},
{
"epoch": 0.1664,
"grad_norm": 1.337349534034729,
"learning_rate": 8.506493506493507e-06,
"loss": 0.7844,
"step": 52
},
{
"epoch": 0.1696,
"grad_norm": 1.311928391456604,
"learning_rate": 8.474025974025975e-06,
"loss": 0.8665,
"step": 53
},
{
"epoch": 0.1728,
"grad_norm": 1.3711683750152588,
"learning_rate": 8.441558441558442e-06,
"loss": 0.764,
"step": 54
},
{
"epoch": 0.176,
"grad_norm": 1.4377758502960205,
"learning_rate": 8.40909090909091e-06,
"loss": 0.8027,
"step": 55
},
{
"epoch": 0.1792,
"grad_norm": 1.3840374946594238,
"learning_rate": 8.376623376623378e-06,
"loss": 0.9163,
"step": 56
},
{
"epoch": 0.1824,
"grad_norm": 1.5715651512145996,
"learning_rate": 8.344155844155845e-06,
"loss": 0.8111,
"step": 57
},
{
"epoch": 0.1856,
"grad_norm": 1.2862898111343384,
"learning_rate": 8.311688311688313e-06,
"loss": 0.7984,
"step": 58
},
{
"epoch": 0.1888,
"grad_norm": 1.4305953979492188,
"learning_rate": 8.27922077922078e-06,
"loss": 0.7762,
"step": 59
},
{
"epoch": 0.192,
"grad_norm": 1.514124870300293,
"learning_rate": 8.246753246753247e-06,
"loss": 0.6909,
"step": 60
},
{
"epoch": 0.1952,
"grad_norm": 1.4759447574615479,
"learning_rate": 8.214285714285714e-06,
"loss": 0.8051,
"step": 61
},
{
"epoch": 0.1984,
"grad_norm": 1.3367384672164917,
"learning_rate": 8.181818181818183e-06,
"loss": 0.8096,
"step": 62
},
{
"epoch": 0.2016,
"grad_norm": 1.262237310409546,
"learning_rate": 8.14935064935065e-06,
"loss": 0.7599,
"step": 63
},
{
"epoch": 0.2048,
"grad_norm": 1.4441957473754883,
"learning_rate": 8.116883116883117e-06,
"loss": 0.7741,
"step": 64
},
{
"epoch": 0.208,
"grad_norm": 1.4128937721252441,
"learning_rate": 8.084415584415586e-06,
"loss": 0.7929,
"step": 65
},
{
"epoch": 0.2112,
"grad_norm": 1.3074737787246704,
"learning_rate": 8.051948051948052e-06,
"loss": 0.7569,
"step": 66
},
{
"epoch": 0.2144,
"grad_norm": 1.2770249843597412,
"learning_rate": 8.019480519480521e-06,
"loss": 0.7327,
"step": 67
},
{
"epoch": 0.2176,
"grad_norm": 1.3476999998092651,
"learning_rate": 7.987012987012988e-06,
"loss": 0.7398,
"step": 68
},
{
"epoch": 0.2208,
"grad_norm": 1.3660588264465332,
"learning_rate": 7.954545454545455e-06,
"loss": 0.7428,
"step": 69
},
{
"epoch": 0.224,
"grad_norm": 1.3757730722427368,
"learning_rate": 7.922077922077924e-06,
"loss": 0.772,
"step": 70
},
{
"epoch": 0.2272,
"grad_norm": 1.418833613395691,
"learning_rate": 7.88961038961039e-06,
"loss": 0.7315,
"step": 71
},
{
"epoch": 0.2304,
"grad_norm": 1.497719645500183,
"learning_rate": 7.857142857142858e-06,
"loss": 0.7603,
"step": 72
},
{
"epoch": 0.2336,
"grad_norm": 1.6543736457824707,
"learning_rate": 7.824675324675325e-06,
"loss": 0.7426,
"step": 73
},
{
"epoch": 0.2368,
"grad_norm": 1.2009284496307373,
"learning_rate": 7.792207792207793e-06,
"loss": 0.7149,
"step": 74
},
{
"epoch": 0.24,
"grad_norm": 1.5950077772140503,
"learning_rate": 7.75974025974026e-06,
"loss": 0.6904,
"step": 75
},
{
"epoch": 0.2432,
"grad_norm": 1.7591907978057861,
"learning_rate": 7.727272727272727e-06,
"loss": 0.8181,
"step": 76
},
{
"epoch": 0.2464,
"grad_norm": 1.5061492919921875,
"learning_rate": 7.694805194805194e-06,
"loss": 0.6687,
"step": 77
},
{
"epoch": 0.2496,
"grad_norm": 1.391204595565796,
"learning_rate": 7.662337662337663e-06,
"loss": 0.7099,
"step": 78
},
{
"epoch": 0.2528,
"grad_norm": 1.6681373119354248,
"learning_rate": 7.62987012987013e-06,
"loss": 0.7715,
"step": 79
},
{
"epoch": 0.256,
"grad_norm": 1.4587377309799194,
"learning_rate": 7.597402597402598e-06,
"loss": 0.7986,
"step": 80
},
{
"epoch": 0.2592,
"grad_norm": 1.4327019453048706,
"learning_rate": 7.564935064935065e-06,
"loss": 0.7615,
"step": 81
},
{
"epoch": 0.2624,
"grad_norm": 1.592335820198059,
"learning_rate": 7.532467532467533e-06,
"loss": 0.7194,
"step": 82
},
{
"epoch": 0.2656,
"grad_norm": 1.818969488143921,
"learning_rate": 7.500000000000001e-06,
"loss": 0.7778,
"step": 83
},
{
"epoch": 0.2688,
"grad_norm": 1.5635945796966553,
"learning_rate": 7.467532467532468e-06,
"loss": 0.6832,
"step": 84
},
{
"epoch": 0.272,
"grad_norm": 1.6165601015090942,
"learning_rate": 7.435064935064936e-06,
"loss": 0.7262,
"step": 85
},
{
"epoch": 0.2752,
"grad_norm": 1.6714136600494385,
"learning_rate": 7.402597402597404e-06,
"loss": 0.6945,
"step": 86
},
{
"epoch": 0.2784,
"grad_norm": 1.4669193029403687,
"learning_rate": 7.370129870129871e-06,
"loss": 0.7597,
"step": 87
},
{
"epoch": 0.2816,
"grad_norm": 1.6006850004196167,
"learning_rate": 7.3376623376623375e-06,
"loss": 0.6943,
"step": 88
},
{
"epoch": 0.2848,
"grad_norm": 1.5513739585876465,
"learning_rate": 7.305194805194806e-06,
"loss": 0.6766,
"step": 89
},
{
"epoch": 0.288,
"grad_norm": 1.5769884586334229,
"learning_rate": 7.272727272727273e-06,
"loss": 0.7036,
"step": 90
},
{
"epoch": 0.2912,
"grad_norm": 1.698893666267395,
"learning_rate": 7.240259740259741e-06,
"loss": 0.7322,
"step": 91
},
{
"epoch": 0.2944,
"grad_norm": 1.6237844228744507,
"learning_rate": 7.207792207792208e-06,
"loss": 0.756,
"step": 92
},
{
"epoch": 0.2976,
"grad_norm": 1.5962598323822021,
"learning_rate": 7.175324675324677e-06,
"loss": 0.6466,
"step": 93
},
{
"epoch": 0.3008,
"grad_norm": 1.3866199254989624,
"learning_rate": 7.1428571428571436e-06,
"loss": 0.5878,
"step": 94
},
{
"epoch": 0.304,
"grad_norm": 1.7351548671722412,
"learning_rate": 7.1103896103896105e-06,
"loss": 0.7033,
"step": 95
},
{
"epoch": 0.3072,
"grad_norm": 1.7491967678070068,
"learning_rate": 7.077922077922078e-06,
"loss": 0.7007,
"step": 96
},
{
"epoch": 0.3104,
"grad_norm": 1.5318310260772705,
"learning_rate": 7.045454545454546e-06,
"loss": 0.578,
"step": 97
},
{
"epoch": 0.3136,
"grad_norm": 1.6933001279830933,
"learning_rate": 7.012987012987014e-06,
"loss": 0.6657,
"step": 98
},
{
"epoch": 0.3168,
"grad_norm": 1.7131991386413574,
"learning_rate": 6.980519480519481e-06,
"loss": 0.7085,
"step": 99
},
{
"epoch": 0.32,
"grad_norm": 1.897113561630249,
"learning_rate": 6.948051948051948e-06,
"loss": 0.6948,
"step": 100
},
{
"epoch": 0.3232,
"grad_norm": 1.5741852521896362,
"learning_rate": 6.9155844155844165e-06,
"loss": 0.6236,
"step": 101
},
{
"epoch": 0.3264,
"grad_norm": 1.8281790018081665,
"learning_rate": 6.8831168831168835e-06,
"loss": 0.5968,
"step": 102
},
{
"epoch": 0.3296,
"grad_norm": 1.6088893413543701,
"learning_rate": 6.850649350649351e-06,
"loss": 0.6262,
"step": 103
},
{
"epoch": 0.3328,
"grad_norm": 1.8895440101623535,
"learning_rate": 6.818181818181818e-06,
"loss": 0.6655,
"step": 104
},
{
"epoch": 0.336,
"grad_norm": 1.8878438472747803,
"learning_rate": 6.785714285714287e-06,
"loss": 0.5968,
"step": 105
},
{
"epoch": 0.3392,
"grad_norm": 1.8233320713043213,
"learning_rate": 6.753246753246754e-06,
"loss": 0.6842,
"step": 106
},
{
"epoch": 0.3424,
"grad_norm": 1.6819425821304321,
"learning_rate": 6.720779220779221e-06,
"loss": 0.6533,
"step": 107
},
{
"epoch": 0.3456,
"grad_norm": 2.240962505340576,
"learning_rate": 6.688311688311689e-06,
"loss": 0.7833,
"step": 108
},
{
"epoch": 0.3488,
"grad_norm": 1.8028863668441772,
"learning_rate": 6.6558441558441565e-06,
"loss": 0.5872,
"step": 109
},
{
"epoch": 0.352,
"grad_norm": 2.085261106491089,
"learning_rate": 6.623376623376624e-06,
"loss": 0.6819,
"step": 110
},
{
"epoch": 0.3552,
"grad_norm": 1.844897985458374,
"learning_rate": 6.590909090909091e-06,
"loss": 0.6996,
"step": 111
},
{
"epoch": 0.3584,
"grad_norm": 1.9914166927337646,
"learning_rate": 6.55844155844156e-06,
"loss": 0.674,
"step": 112
},
{
"epoch": 0.3616,
"grad_norm": 1.8009718656539917,
"learning_rate": 6.525974025974027e-06,
"loss": 0.625,
"step": 113
},
{
"epoch": 0.3648,
"grad_norm": 2.120251178741455,
"learning_rate": 6.493506493506494e-06,
"loss": 0.6252,
"step": 114
},
{
"epoch": 0.368,
"grad_norm": 1.9561840295791626,
"learning_rate": 6.461038961038961e-06,
"loss": 0.6218,
"step": 115
},
{
"epoch": 0.3712,
"grad_norm": 1.9256573915481567,
"learning_rate": 6.4285714285714295e-06,
"loss": 0.6251,
"step": 116
},
{
"epoch": 0.3744,
"grad_norm": 2.0886967182159424,
"learning_rate": 6.3961038961038964e-06,
"loss": 0.5972,
"step": 117
},
{
"epoch": 0.3776,
"grad_norm": 1.90208101272583,
"learning_rate": 6.363636363636364e-06,
"loss": 0.6392,
"step": 118
},
{
"epoch": 0.3808,
"grad_norm": 2.1293461322784424,
"learning_rate": 6.331168831168831e-06,
"loss": 0.6637,
"step": 119
},
{
"epoch": 0.384,
"grad_norm": 1.7344480752944946,
"learning_rate": 6.2987012987013e-06,
"loss": 0.5419,
"step": 120
},
{
"epoch": 0.3872,
"grad_norm": 2.242717742919922,
"learning_rate": 6.266233766233767e-06,
"loss": 0.69,
"step": 121
},
{
"epoch": 0.3904,
"grad_norm": 1.9519375562667847,
"learning_rate": 6.233766233766234e-06,
"loss": 0.6116,
"step": 122
},
{
"epoch": 0.3936,
"grad_norm": 2.716726541519165,
"learning_rate": 6.201298701298702e-06,
"loss": 0.6661,
"step": 123
},
{
"epoch": 0.3968,
"grad_norm": 1.9421472549438477,
"learning_rate": 6.168831168831169e-06,
"loss": 0.6495,
"step": 124
},
{
"epoch": 0.4,
"grad_norm": 1.7099575996398926,
"learning_rate": 6.136363636363637e-06,
"loss": 0.5694,
"step": 125
},
{
"epoch": 0.4032,
"grad_norm": 1.9398987293243408,
"learning_rate": 6.103896103896104e-06,
"loss": 0.6332,
"step": 126
},
{
"epoch": 0.4064,
"grad_norm": 1.8356436491012573,
"learning_rate": 6.071428571428571e-06,
"loss": 0.5879,
"step": 127
},
{
"epoch": 0.4096,
"grad_norm": 2.187277317047119,
"learning_rate": 6.03896103896104e-06,
"loss": 0.5762,
"step": 128
},
{
"epoch": 0.4128,
"grad_norm": 2.1066439151763916,
"learning_rate": 6.006493506493507e-06,
"loss": 0.6246,
"step": 129
},
{
"epoch": 0.416,
"grad_norm": 2.073390483856201,
"learning_rate": 5.9740259740259746e-06,
"loss": 0.5941,
"step": 130
},
{
"epoch": 0.4192,
"grad_norm": 2.0324959754943848,
"learning_rate": 5.9415584415584415e-06,
"loss": 0.6146,
"step": 131
},
{
"epoch": 0.4224,
"grad_norm": 1.9881010055541992,
"learning_rate": 5.90909090909091e-06,
"loss": 0.5945,
"step": 132
},
{
"epoch": 0.4256,
"grad_norm": 2.017544984817505,
"learning_rate": 5.876623376623377e-06,
"loss": 0.5837,
"step": 133
},
{
"epoch": 0.4288,
"grad_norm": 2.583054780960083,
"learning_rate": 5.844155844155844e-06,
"loss": 0.6035,
"step": 134
},
{
"epoch": 0.432,
"grad_norm": 2.6116082668304443,
"learning_rate": 5.811688311688313e-06,
"loss": 0.6499,
"step": 135
},
{
"epoch": 0.4352,
"grad_norm": 2.4798545837402344,
"learning_rate": 5.77922077922078e-06,
"loss": 0.635,
"step": 136
},
{
"epoch": 0.4384,
"grad_norm": 2.100008010864258,
"learning_rate": 5.7467532467532475e-06,
"loss": 0.5438,
"step": 137
},
{
"epoch": 0.4416,
"grad_norm": 2.369692325592041,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.5559,
"step": 138
},
{
"epoch": 0.4448,
"grad_norm": 2.6044960021972656,
"learning_rate": 5.681818181818183e-06,
"loss": 0.6192,
"step": 139
},
{
"epoch": 0.448,
"grad_norm": 2.3004958629608154,
"learning_rate": 5.64935064935065e-06,
"loss": 0.5644,
"step": 140
},
{
"epoch": 0.4512,
"grad_norm": 2.30646014213562,
"learning_rate": 5.616883116883117e-06,
"loss": 0.6024,
"step": 141
},
{
"epoch": 0.4544,
"grad_norm": 2.3673393726348877,
"learning_rate": 5.584415584415585e-06,
"loss": 0.5238,
"step": 142
},
{
"epoch": 0.4576,
"grad_norm": 2.66957950592041,
"learning_rate": 5.551948051948053e-06,
"loss": 0.6148,
"step": 143
},
{
"epoch": 0.4608,
"grad_norm": 2.209986925125122,
"learning_rate": 5.5194805194805205e-06,
"loss": 0.5579,
"step": 144
},
{
"epoch": 0.464,
"grad_norm": 2.405188798904419,
"learning_rate": 5.4870129870129875e-06,
"loss": 0.5783,
"step": 145
},
{
"epoch": 0.4672,
"grad_norm": 2.380112886428833,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.5438,
"step": 146
},
{
"epoch": 0.4704,
"grad_norm": 2.145167350769043,
"learning_rate": 5.422077922077923e-06,
"loss": 0.5081,
"step": 147
},
{
"epoch": 0.4736,
"grad_norm": 2.42675518989563,
"learning_rate": 5.38961038961039e-06,
"loss": 0.5667,
"step": 148
},
{
"epoch": 0.4768,
"grad_norm": 2.2153475284576416,
"learning_rate": 5.357142857142857e-06,
"loss": 0.495,
"step": 149
},
{
"epoch": 0.48,
"grad_norm": 2.5394628047943115,
"learning_rate": 5.324675324675325e-06,
"loss": 0.4709,
"step": 150
},
{
"epoch": 0.4832,
"grad_norm": 2.5719780921936035,
"learning_rate": 5.292207792207793e-06,
"loss": 0.5384,
"step": 151
},
{
"epoch": 0.4864,
"grad_norm": 2.4524574279785156,
"learning_rate": 5.2597402597402605e-06,
"loss": 0.5615,
"step": 152
},
{
"epoch": 0.4896,
"grad_norm": 2.5788793563842773,
"learning_rate": 5.2272727272727274e-06,
"loss": 0.4973,
"step": 153
},
{
"epoch": 0.4928,
"grad_norm": 2.253735065460205,
"learning_rate": 5.194805194805194e-06,
"loss": 0.48,
"step": 154
},
{
"epoch": 0.496,
"grad_norm": 2.8777077198028564,
"learning_rate": 5.162337662337663e-06,
"loss": 0.527,
"step": 155
},
{
"epoch": 0.4992,
"grad_norm": 2.1467268466949463,
"learning_rate": 5.12987012987013e-06,
"loss": 0.5227,
"step": 156
},
{
"epoch": 0.5024,
"grad_norm": 2.4068822860717773,
"learning_rate": 5.097402597402598e-06,
"loss": 0.4767,
"step": 157
},
{
"epoch": 0.5056,
"grad_norm": 2.4299392700195312,
"learning_rate": 5.064935064935065e-06,
"loss": 0.508,
"step": 158
},
{
"epoch": 0.5088,
"grad_norm": 2.200183868408203,
"learning_rate": 5.0324675324675334e-06,
"loss": 0.5159,
"step": 159
},
{
"epoch": 0.512,
"grad_norm": 2.351933240890503,
"learning_rate": 5e-06,
"loss": 0.4603,
"step": 160
},
{
"epoch": 0.5152,
"grad_norm": 2.501340389251709,
"learning_rate": 4.967532467532468e-06,
"loss": 0.4853,
"step": 161
},
{
"epoch": 0.5184,
"grad_norm": 2.415330171585083,
"learning_rate": 4.935064935064935e-06,
"loss": 0.5096,
"step": 162
},
{
"epoch": 0.5216,
"grad_norm": 3.2392561435699463,
"learning_rate": 4.902597402597403e-06,
"loss": 0.4772,
"step": 163
},
{
"epoch": 0.5248,
"grad_norm": 2.5991477966308594,
"learning_rate": 4.870129870129871e-06,
"loss": 0.4631,
"step": 164
},
{
"epoch": 0.528,
"grad_norm": 3.1602790355682373,
"learning_rate": 4.837662337662339e-06,
"loss": 0.5219,
"step": 165
},
{
"epoch": 0.5312,
"grad_norm": 3.0979714393615723,
"learning_rate": 4.805194805194806e-06,
"loss": 0.5795,
"step": 166
},
{
"epoch": 0.5344,
"grad_norm": 2.6634860038757324,
"learning_rate": 4.772727272727273e-06,
"loss": 0.5505,
"step": 167
},
{
"epoch": 0.5376,
"grad_norm": 2.6327335834503174,
"learning_rate": 4.74025974025974e-06,
"loss": 0.482,
"step": 168
},
{
"epoch": 0.5408,
"grad_norm": 2.570263624191284,
"learning_rate": 4.707792207792208e-06,
"loss": 0.4346,
"step": 169
},
{
"epoch": 0.544,
"grad_norm": 2.69173526763916,
"learning_rate": 4.675324675324676e-06,
"loss": 0.5307,
"step": 170
},
{
"epoch": 0.5472,
"grad_norm": 2.4208245277404785,
"learning_rate": 4.642857142857144e-06,
"loss": 0.4918,
"step": 171
},
{
"epoch": 0.5504,
"grad_norm": 2.279787063598633,
"learning_rate": 4.610389610389611e-06,
"loss": 0.4563,
"step": 172
},
{
"epoch": 0.5536,
"grad_norm": 2.5185399055480957,
"learning_rate": 4.5779220779220786e-06,
"loss": 0.4685,
"step": 173
},
{
"epoch": 0.5568,
"grad_norm": 2.4868409633636475,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.4616,
"step": 174
},
{
"epoch": 0.56,
"grad_norm": 3.0586249828338623,
"learning_rate": 4.512987012987013e-06,
"loss": 0.4981,
"step": 175
},
{
"epoch": 0.5632,
"grad_norm": 2.484553575515747,
"learning_rate": 4.48051948051948e-06,
"loss": 0.5173,
"step": 176
},
{
"epoch": 0.5664,
"grad_norm": 2.8379547595977783,
"learning_rate": 4.448051948051948e-06,
"loss": 0.5163,
"step": 177
},
{
"epoch": 0.5696,
"grad_norm": 3.016439914703369,
"learning_rate": 4.415584415584416e-06,
"loss": 0.4193,
"step": 178
},
{
"epoch": 0.5728,
"grad_norm": 3.060291290283203,
"learning_rate": 4.383116883116884e-06,
"loss": 0.4838,
"step": 179
},
{
"epoch": 0.576,
"grad_norm": 2.8870880603790283,
"learning_rate": 4.350649350649351e-06,
"loss": 0.4921,
"step": 180
},
{
"epoch": 0.5792,
"grad_norm": 2.58658766746521,
"learning_rate": 4.3181818181818185e-06,
"loss": 0.4667,
"step": 181
},
{
"epoch": 0.5824,
"grad_norm": 2.6489756107330322,
"learning_rate": 4.2857142857142855e-06,
"loss": 0.4268,
"step": 182
},
{
"epoch": 0.5856,
"grad_norm": 3.263758897781372,
"learning_rate": 4.253246753246753e-06,
"loss": 0.4556,
"step": 183
},
{
"epoch": 0.5888,
"grad_norm": 3.113347053527832,
"learning_rate": 4.220779220779221e-06,
"loss": 0.4584,
"step": 184
},
{
"epoch": 0.592,
"grad_norm": 2.749751091003418,
"learning_rate": 4.188311688311689e-06,
"loss": 0.4366,
"step": 185
},
{
"epoch": 0.5952,
"grad_norm": 2.726654052734375,
"learning_rate": 4.155844155844157e-06,
"loss": 0.4574,
"step": 186
},
{
"epoch": 0.5984,
"grad_norm": 2.737936019897461,
"learning_rate": 4.123376623376624e-06,
"loss": 0.4458,
"step": 187
},
{
"epoch": 0.6016,
"grad_norm": 2.5224568843841553,
"learning_rate": 4.0909090909090915e-06,
"loss": 0.4375,
"step": 188
},
{
"epoch": 0.6048,
"grad_norm": 3.1188995838165283,
"learning_rate": 4.0584415584415584e-06,
"loss": 0.4735,
"step": 189
},
{
"epoch": 0.608,
"grad_norm": 3.059140920639038,
"learning_rate": 4.025974025974026e-06,
"loss": 0.4596,
"step": 190
},
{
"epoch": 0.6112,
"grad_norm": 2.5312676429748535,
"learning_rate": 3.993506493506494e-06,
"loss": 0.4069,
"step": 191
},
{
"epoch": 0.6144,
"grad_norm": 2.821013927459717,
"learning_rate": 3.961038961038962e-06,
"loss": 0.4671,
"step": 192
},
{
"epoch": 0.6176,
"grad_norm": 3.2510814666748047,
"learning_rate": 3.928571428571429e-06,
"loss": 0.4492,
"step": 193
},
{
"epoch": 0.6208,
"grad_norm": 3.137798547744751,
"learning_rate": 3.896103896103897e-06,
"loss": 0.379,
"step": 194
},
{
"epoch": 0.624,
"grad_norm": 2.846541404724121,
"learning_rate": 3.863636363636364e-06,
"loss": 0.3914,
"step": 195
},
{
"epoch": 0.6272,
"grad_norm": 3.1899781227111816,
"learning_rate": 3.831168831168831e-06,
"loss": 0.4699,
"step": 196
},
{
"epoch": 0.6304,
"grad_norm": 3.118363857269287,
"learning_rate": 3.798701298701299e-06,
"loss": 0.4115,
"step": 197
},
{
"epoch": 0.6336,
"grad_norm": 3.8301401138305664,
"learning_rate": 3.7662337662337666e-06,
"loss": 0.4093,
"step": 198
},
{
"epoch": 0.6368,
"grad_norm": 3.856610059738159,
"learning_rate": 3.733766233766234e-06,
"loss": 0.4603,
"step": 199
},
{
"epoch": 0.64,
"grad_norm": 4.301602363586426,
"learning_rate": 3.701298701298702e-06,
"loss": 0.4026,
"step": 200
},
{
"epoch": 0.6432,
"grad_norm": 3.5105443000793457,
"learning_rate": 3.6688311688311688e-06,
"loss": 0.5042,
"step": 201
},
{
"epoch": 0.6464,
"grad_norm": 3.22503399848938,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.4417,
"step": 202
},
{
"epoch": 0.6496,
"grad_norm": 3.0266528129577637,
"learning_rate": 3.603896103896104e-06,
"loss": 0.4204,
"step": 203
},
{
"epoch": 0.6528,
"grad_norm": 3.440232992172241,
"learning_rate": 3.5714285714285718e-06,
"loss": 0.4388,
"step": 204
},
{
"epoch": 0.656,
"grad_norm": 3.1369011402130127,
"learning_rate": 3.538961038961039e-06,
"loss": 0.3727,
"step": 205
},
{
"epoch": 0.6592,
"grad_norm": 3.406059503555298,
"learning_rate": 3.506493506493507e-06,
"loss": 0.3845,
"step": 206
},
{
"epoch": 0.6624,
"grad_norm": 3.070361614227295,
"learning_rate": 3.474025974025974e-06,
"loss": 0.3876,
"step": 207
},
{
"epoch": 0.6656,
"grad_norm": 3.1251604557037354,
"learning_rate": 3.4415584415584418e-06,
"loss": 0.4594,
"step": 208
},
{
"epoch": 0.6688,
"grad_norm": 3.755077838897705,
"learning_rate": 3.409090909090909e-06,
"loss": 0.4547,
"step": 209
},
{
"epoch": 0.672,
"grad_norm": 3.0717198848724365,
"learning_rate": 3.376623376623377e-06,
"loss": 0.3853,
"step": 210
},
{
"epoch": 0.6752,
"grad_norm": 3.4697611331939697,
"learning_rate": 3.3441558441558443e-06,
"loss": 0.3974,
"step": 211
},
{
"epoch": 0.6784,
"grad_norm": 3.2027981281280518,
"learning_rate": 3.311688311688312e-06,
"loss": 0.3518,
"step": 212
},
{
"epoch": 0.6816,
"grad_norm": 3.3500893115997314,
"learning_rate": 3.27922077922078e-06,
"loss": 0.4752,
"step": 213
},
{
"epoch": 0.6848,
"grad_norm": 3.9136343002319336,
"learning_rate": 3.246753246753247e-06,
"loss": 0.4509,
"step": 214
},
{
"epoch": 0.688,
"grad_norm": 3.5852739810943604,
"learning_rate": 3.2142857142857147e-06,
"loss": 0.3698,
"step": 215
},
{
"epoch": 0.6912,
"grad_norm": 2.958652973175049,
"learning_rate": 3.181818181818182e-06,
"loss": 0.404,
"step": 216
},
{
"epoch": 0.6944,
"grad_norm": 2.812950611114502,
"learning_rate": 3.14935064935065e-06,
"loss": 0.323,
"step": 217
},
{
"epoch": 0.6976,
"grad_norm": 3.6003265380859375,
"learning_rate": 3.116883116883117e-06,
"loss": 0.3955,
"step": 218
},
{
"epoch": 0.7008,
"grad_norm": 3.6587672233581543,
"learning_rate": 3.0844155844155847e-06,
"loss": 0.386,
"step": 219
},
{
"epoch": 0.704,
"grad_norm": 3.6365511417388916,
"learning_rate": 3.051948051948052e-06,
"loss": 0.3928,
"step": 220
},
{
"epoch": 0.7072,
"grad_norm": 3.3309619426727295,
"learning_rate": 3.01948051948052e-06,
"loss": 0.4252,
"step": 221
},
{
"epoch": 0.7104,
"grad_norm": 3.8079402446746826,
"learning_rate": 2.9870129870129873e-06,
"loss": 0.3709,
"step": 222
},
{
"epoch": 0.7136,
"grad_norm": 3.5054643154144287,
"learning_rate": 2.954545454545455e-06,
"loss": 0.3754,
"step": 223
},
{
"epoch": 0.7168,
"grad_norm": 3.159898519515991,
"learning_rate": 2.922077922077922e-06,
"loss": 0.3728,
"step": 224
},
{
"epoch": 0.72,
"grad_norm": 3.584296226501465,
"learning_rate": 2.88961038961039e-06,
"loss": 0.4081,
"step": 225
},
{
"epoch": 0.7232,
"grad_norm": 3.1787877082824707,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.3665,
"step": 226
},
{
"epoch": 0.7264,
"grad_norm": 2.677522897720337,
"learning_rate": 2.824675324675325e-06,
"loss": 0.2992,
"step": 227
},
{
"epoch": 0.7296,
"grad_norm": 3.978600263595581,
"learning_rate": 2.7922077922077925e-06,
"loss": 0.3937,
"step": 228
},
{
"epoch": 0.7328,
"grad_norm": 3.122856855392456,
"learning_rate": 2.7597402597402603e-06,
"loss": 0.3803,
"step": 229
},
{
"epoch": 0.736,
"grad_norm": 3.339524507522583,
"learning_rate": 2.7272727272727272e-06,
"loss": 0.386,
"step": 230
},
{
"epoch": 0.7392,
"grad_norm": 3.5689985752105713,
"learning_rate": 2.694805194805195e-06,
"loss": 0.3727,
"step": 231
},
{
"epoch": 0.7424,
"grad_norm": 3.6701812744140625,
"learning_rate": 2.6623376623376624e-06,
"loss": 0.3603,
"step": 232
},
{
"epoch": 0.7456,
"grad_norm": 3.027395486831665,
"learning_rate": 2.6298701298701302e-06,
"loss": 0.3522,
"step": 233
},
{
"epoch": 0.7488,
"grad_norm": 3.4681172370910645,
"learning_rate": 2.597402597402597e-06,
"loss": 0.4836,
"step": 234
},
{
"epoch": 0.752,
"grad_norm": 3.5065665245056152,
"learning_rate": 2.564935064935065e-06,
"loss": 0.3834,
"step": 235
},
{
"epoch": 0.7552,
"grad_norm": 4.68280029296875,
"learning_rate": 2.5324675324675324e-06,
"loss": 0.3449,
"step": 236
},
{
"epoch": 0.7584,
"grad_norm": 4.197664737701416,
"learning_rate": 2.5e-06,
"loss": 0.3756,
"step": 237
},
{
"epoch": 0.7616,
"grad_norm": 3.1506834030151367,
"learning_rate": 2.4675324675324676e-06,
"loss": 0.3334,
"step": 238
},
{
"epoch": 0.7648,
"grad_norm": 4.261498928070068,
"learning_rate": 2.4350649350649354e-06,
"loss": 0.3947,
"step": 239
},
{
"epoch": 0.768,
"grad_norm": 3.613182783126831,
"learning_rate": 2.402597402597403e-06,
"loss": 0.291,
"step": 240
},
{
"epoch": 0.7712,
"grad_norm": 3.1160547733306885,
"learning_rate": 2.37012987012987e-06,
"loss": 0.3419,
"step": 241
},
{
"epoch": 0.7744,
"grad_norm": 3.765911102294922,
"learning_rate": 2.337662337662338e-06,
"loss": 0.3947,
"step": 242
},
{
"epoch": 0.7776,
"grad_norm": 3.1016063690185547,
"learning_rate": 2.3051948051948054e-06,
"loss": 0.3245,
"step": 243
},
{
"epoch": 0.7808,
"grad_norm": 3.860008955001831,
"learning_rate": 2.2727272727272728e-06,
"loss": 0.3445,
"step": 244
},
{
"epoch": 0.784,
"grad_norm": 3.2103567123413086,
"learning_rate": 2.24025974025974e-06,
"loss": 0.2996,
"step": 245
},
{
"epoch": 0.7872,
"grad_norm": 3.3398399353027344,
"learning_rate": 2.207792207792208e-06,
"loss": 0.378,
"step": 246
},
{
"epoch": 0.7904,
"grad_norm": 3.529299020767212,
"learning_rate": 2.1753246753246753e-06,
"loss": 0.3466,
"step": 247
},
{
"epoch": 0.7936,
"grad_norm": 3.3010692596435547,
"learning_rate": 2.1428571428571427e-06,
"loss": 0.2845,
"step": 248
},
{
"epoch": 0.7968,
"grad_norm": 3.961313486099243,
"learning_rate": 2.1103896103896105e-06,
"loss": 0.3889,
"step": 249
},
{
"epoch": 0.8,
"grad_norm": 3.386698007583618,
"learning_rate": 2.0779220779220784e-06,
"loss": 0.2975,
"step": 250
},
{
"epoch": 0.8032,
"grad_norm": 3.718106269836426,
"learning_rate": 2.0454545454545457e-06,
"loss": 0.3472,
"step": 251
},
{
"epoch": 0.8064,
"grad_norm": 3.8275556564331055,
"learning_rate": 2.012987012987013e-06,
"loss": 0.3176,
"step": 252
},
{
"epoch": 0.8096,
"grad_norm": 3.5234034061431885,
"learning_rate": 1.980519480519481e-06,
"loss": 0.3279,
"step": 253
},
{
"epoch": 0.8128,
"grad_norm": 4.082868576049805,
"learning_rate": 1.9480519480519483e-06,
"loss": 0.3111,
"step": 254
},
{
"epoch": 0.816,
"grad_norm": 3.8824350833892822,
"learning_rate": 1.9155844155844157e-06,
"loss": 0.3334,
"step": 255
},
{
"epoch": 0.8192,
"grad_norm": 3.439039707183838,
"learning_rate": 1.8831168831168833e-06,
"loss": 0.3136,
"step": 256
},
{
"epoch": 0.8224,
"grad_norm": 4.407830715179443,
"learning_rate": 1.850649350649351e-06,
"loss": 0.3089,
"step": 257
},
{
"epoch": 0.8256,
"grad_norm": 4.113597869873047,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.3666,
"step": 258
},
{
"epoch": 0.8288,
"grad_norm": 4.972888469696045,
"learning_rate": 1.7857142857142859e-06,
"loss": 0.335,
"step": 259
},
{
"epoch": 0.832,
"grad_norm": 4.1458048820495605,
"learning_rate": 1.7532467532467535e-06,
"loss": 0.3818,
"step": 260
},
{
"epoch": 0.8352,
"grad_norm": 4.115975379943848,
"learning_rate": 1.7207792207792209e-06,
"loss": 0.3342,
"step": 261
},
{
"epoch": 0.8384,
"grad_norm": 3.344860076904297,
"learning_rate": 1.6883116883116885e-06,
"loss": 0.3054,
"step": 262
},
{
"epoch": 0.8416,
"grad_norm": 3.544015407562256,
"learning_rate": 1.655844155844156e-06,
"loss": 0.3118,
"step": 263
},
{
"epoch": 0.8448,
"grad_norm": 3.5486655235290527,
"learning_rate": 1.6233766233766235e-06,
"loss": 0.3515,
"step": 264
},
{
"epoch": 0.848,
"grad_norm": 2.9218409061431885,
"learning_rate": 1.590909090909091e-06,
"loss": 0.3812,
"step": 265
},
{
"epoch": 0.8512,
"grad_norm": 4.031822204589844,
"learning_rate": 1.5584415584415584e-06,
"loss": 0.3563,
"step": 266
},
{
"epoch": 0.8544,
"grad_norm": 3.7376978397369385,
"learning_rate": 1.525974025974026e-06,
"loss": 0.3629,
"step": 267
},
{
"epoch": 0.8576,
"grad_norm": 3.612359046936035,
"learning_rate": 1.4935064935064936e-06,
"loss": 0.3124,
"step": 268
},
{
"epoch": 0.8608,
"grad_norm": 4.43179988861084,
"learning_rate": 1.461038961038961e-06,
"loss": 0.378,
"step": 269
},
{
"epoch": 0.864,
"grad_norm": 4.0608391761779785,
"learning_rate": 1.4285714285714286e-06,
"loss": 0.342,
"step": 270
},
{
"epoch": 0.8672,
"grad_norm": 2.922579050064087,
"learning_rate": 1.3961038961038962e-06,
"loss": 0.2483,
"step": 271
},
{
"epoch": 0.8704,
"grad_norm": 4.325706958770752,
"learning_rate": 1.3636363636363636e-06,
"loss": 0.3178,
"step": 272
},
{
"epoch": 0.8736,
"grad_norm": 3.271789312362671,
"learning_rate": 1.3311688311688312e-06,
"loss": 0.2458,
"step": 273
},
{
"epoch": 0.8768,
"grad_norm": 3.6045310497283936,
"learning_rate": 1.2987012987012986e-06,
"loss": 0.3291,
"step": 274
},
{
"epoch": 0.88,
"grad_norm": 3.202625036239624,
"learning_rate": 1.2662337662337662e-06,
"loss": 0.3202,
"step": 275
},
{
"epoch": 0.8832,
"grad_norm": 3.570035696029663,
"learning_rate": 1.2337662337662338e-06,
"loss": 0.3006,
"step": 276
},
{
"epoch": 0.8864,
"grad_norm": 3.309915065765381,
"learning_rate": 1.2012987012987014e-06,
"loss": 0.3388,
"step": 277
},
{
"epoch": 0.8896,
"grad_norm": 4.571963310241699,
"learning_rate": 1.168831168831169e-06,
"loss": 0.3483,
"step": 278
},
{
"epoch": 0.8928,
"grad_norm": 3.655355930328369,
"learning_rate": 1.1363636363636364e-06,
"loss": 0.2964,
"step": 279
},
{
"epoch": 0.896,
"grad_norm": 3.7896673679351807,
"learning_rate": 1.103896103896104e-06,
"loss": 0.2922,
"step": 280
},
{
"epoch": 0.8992,
"grad_norm": 4.307418346405029,
"learning_rate": 1.0714285714285714e-06,
"loss": 0.2949,
"step": 281
},
{
"epoch": 0.9024,
"grad_norm": 3.3083884716033936,
"learning_rate": 1.0389610389610392e-06,
"loss": 0.3209,
"step": 282
},
{
"epoch": 0.9056,
"grad_norm": 4.244633197784424,
"learning_rate": 1.0064935064935066e-06,
"loss": 0.2946,
"step": 283
},
{
"epoch": 0.9088,
"grad_norm": 3.999847888946533,
"learning_rate": 9.740259740259742e-07,
"loss": 0.3211,
"step": 284
},
{
"epoch": 0.912,
"grad_norm": 3.737175226211548,
"learning_rate": 9.415584415584417e-07,
"loss": 0.226,
"step": 285
},
{
"epoch": 0.9152,
"grad_norm": 3.8389108180999756,
"learning_rate": 9.090909090909091e-07,
"loss": 0.278,
"step": 286
},
{
"epoch": 0.9184,
"grad_norm": 3.7956488132476807,
"learning_rate": 8.766233766233767e-07,
"loss": 0.2682,
"step": 287
},
{
"epoch": 0.9216,
"grad_norm": 3.7749340534210205,
"learning_rate": 8.441558441558442e-07,
"loss": 0.3251,
"step": 288
},
{
"epoch": 0.9248,
"grad_norm": 5.137296676635742,
"learning_rate": 8.116883116883117e-07,
"loss": 0.401,
"step": 289
},
{
"epoch": 0.928,
"grad_norm": 3.7601916790008545,
"learning_rate": 7.792207792207792e-07,
"loss": 0.3065,
"step": 290
},
{
"epoch": 0.9312,
"grad_norm": 4.77811861038208,
"learning_rate": 7.467532467532468e-07,
"loss": 0.3074,
"step": 291
},
{
"epoch": 0.9344,
"grad_norm": 3.95403790473938,
"learning_rate": 7.142857142857143e-07,
"loss": 0.3167,
"step": 292
},
{
"epoch": 0.9376,
"grad_norm": 3.9109158515930176,
"learning_rate": 6.818181818181818e-07,
"loss": 0.354,
"step": 293
},
{
"epoch": 0.9408,
"grad_norm": 3.9957079887390137,
"learning_rate": 6.493506493506493e-07,
"loss": 0.3079,
"step": 294
},
{
"epoch": 0.944,
"grad_norm": 4.9614739418029785,
"learning_rate": 6.168831168831169e-07,
"loss": 0.3258,
"step": 295
},
{
"epoch": 0.9472,
"grad_norm": 3.6851398944854736,
"learning_rate": 5.844155844155845e-07,
"loss": 0.2817,
"step": 296
},
{
"epoch": 0.9504,
"grad_norm": 3.8794970512390137,
"learning_rate": 5.51948051948052e-07,
"loss": 0.2766,
"step": 297
},
{
"epoch": 0.9536,
"grad_norm": 3.5052332878112793,
"learning_rate": 5.194805194805196e-07,
"loss": 0.306,
"step": 298
},
{
"epoch": 0.9568,
"grad_norm": 3.526350259780884,
"learning_rate": 4.870129870129871e-07,
"loss": 0.3138,
"step": 299
},
{
"epoch": 0.96,
"grad_norm": 4.306396007537842,
"learning_rate": 4.5454545454545457e-07,
"loss": 0.3048,
"step": 300
},
{
"epoch": 0.9632,
"grad_norm": 3.977013111114502,
"learning_rate": 4.220779220779221e-07,
"loss": 0.2984,
"step": 301
},
{
"epoch": 0.9664,
"grad_norm": 3.4203877449035645,
"learning_rate": 3.896103896103896e-07,
"loss": 0.3002,
"step": 302
},
{
"epoch": 0.9696,
"grad_norm": 3.6374948024749756,
"learning_rate": 3.5714285714285716e-07,
"loss": 0.2961,
"step": 303
},
{
"epoch": 0.9728,
"grad_norm": 3.726452350616455,
"learning_rate": 3.2467532467532465e-07,
"loss": 0.2844,
"step": 304
},
{
"epoch": 0.976,
"grad_norm": 4.53134822845459,
"learning_rate": 2.9220779220779225e-07,
"loss": 0.2937,
"step": 305
},
{
"epoch": 0.9792,
"grad_norm": 4.388988494873047,
"learning_rate": 2.597402597402598e-07,
"loss": 0.3295,
"step": 306
},
{
"epoch": 0.9824,
"grad_norm": 3.973243236541748,
"learning_rate": 2.2727272727272729e-07,
"loss": 0.2991,
"step": 307
},
{
"epoch": 0.9856,
"grad_norm": 4.007715225219727,
"learning_rate": 1.948051948051948e-07,
"loss": 0.2812,
"step": 308
},
{
"epoch": 0.9888,
"grad_norm": 3.9321532249450684,
"learning_rate": 1.6233766233766232e-07,
"loss": 0.2825,
"step": 309
},
{
"epoch": 0.992,
"grad_norm": 4.078246593475342,
"learning_rate": 1.298701298701299e-07,
"loss": 0.2848,
"step": 310
},
{
"epoch": 0.9952,
"grad_norm": 4.222702980041504,
"learning_rate": 9.74025974025974e-08,
"loss": 0.2945,
"step": 311
},
{
"epoch": 0.9984,
"grad_norm": 4.369868755340576,
"learning_rate": 6.493506493506495e-08,
"loss": 0.2944,
"step": 312
},
{
"epoch": 1.0,
"grad_norm": 5.1346235275268555,
"learning_rate": 3.2467532467532474e-08,
"loss": 0.2697,
"step": 313
}
],
"logging_steps": 1,
"max_steps": 313,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.3318933877534515e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}