model_ed6715ce / checkpoint-170 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
978952e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.984375,
"eval_steps": 500,
"global_step": 170,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01171875,
"grad_norm": 34.936946868896484,
"learning_rate": 5.0000000000000004e-08,
"loss": 4.5195,
"step": 1
},
{
"epoch": 0.0234375,
"grad_norm": 35.17010498046875,
"learning_rate": 1.0000000000000001e-07,
"loss": 4.5214,
"step": 2
},
{
"epoch": 0.03515625,
"grad_norm": 36.44556427001953,
"learning_rate": 1.5000000000000002e-07,
"loss": 4.5497,
"step": 3
},
{
"epoch": 0.046875,
"grad_norm": 35.30234146118164,
"learning_rate": 2.0000000000000002e-07,
"loss": 4.5195,
"step": 4
},
{
"epoch": 0.05859375,
"grad_norm": 35.90467834472656,
"learning_rate": 2.5000000000000004e-07,
"loss": 4.5572,
"step": 5
},
{
"epoch": 0.0703125,
"grad_norm": 35.25331497192383,
"learning_rate": 3.0000000000000004e-07,
"loss": 4.522,
"step": 6
},
{
"epoch": 0.08203125,
"grad_norm": 35.77690124511719,
"learning_rate": 3.5000000000000004e-07,
"loss": 4.532,
"step": 7
},
{
"epoch": 0.09375,
"grad_norm": 35.59796905517578,
"learning_rate": 4.0000000000000003e-07,
"loss": 4.5413,
"step": 8
},
{
"epoch": 0.10546875,
"grad_norm": 34.550079345703125,
"learning_rate": 4.5000000000000003e-07,
"loss": 4.444,
"step": 9
},
{
"epoch": 0.1171875,
"grad_norm": 35.464324951171875,
"learning_rate": 5.000000000000001e-07,
"loss": 4.3859,
"step": 10
},
{
"epoch": 0.12890625,
"grad_norm": 34.73582458496094,
"learning_rate": 5.5e-07,
"loss": 4.4206,
"step": 11
},
{
"epoch": 0.140625,
"grad_norm": 34.19432067871094,
"learning_rate": 6.000000000000001e-07,
"loss": 4.3844,
"step": 12
},
{
"epoch": 0.15234375,
"grad_norm": 33.5693473815918,
"learning_rate": 6.5e-07,
"loss": 4.3484,
"step": 13
},
{
"epoch": 0.1640625,
"grad_norm": 33.903499603271484,
"learning_rate": 7.000000000000001e-07,
"loss": 4.3156,
"step": 14
},
{
"epoch": 0.17578125,
"grad_norm": 31.61307716369629,
"learning_rate": 7.5e-07,
"loss": 4.1674,
"step": 15
},
{
"epoch": 0.1875,
"grad_norm": 29.78888702392578,
"learning_rate": 8.000000000000001e-07,
"loss": 4.0061,
"step": 16
},
{
"epoch": 0.19921875,
"grad_norm": 28.59884262084961,
"learning_rate": 8.500000000000001e-07,
"loss": 3.9706,
"step": 17
},
{
"epoch": 0.2109375,
"grad_norm": 25.763689041137695,
"learning_rate": 9.000000000000001e-07,
"loss": 3.7961,
"step": 18
},
{
"epoch": 0.22265625,
"grad_norm": 24.51258659362793,
"learning_rate": 9.500000000000001e-07,
"loss": 3.7835,
"step": 19
},
{
"epoch": 0.234375,
"grad_norm": 22.484188079833984,
"learning_rate": 1.0000000000000002e-06,
"loss": 3.5655,
"step": 20
},
{
"epoch": 0.24609375,
"grad_norm": 20.98280143737793,
"learning_rate": 1.0500000000000001e-06,
"loss": 3.483,
"step": 21
},
{
"epoch": 0.2578125,
"grad_norm": 19.596670150756836,
"learning_rate": 1.1e-06,
"loss": 3.3479,
"step": 22
},
{
"epoch": 0.26953125,
"grad_norm": 18.059001922607422,
"learning_rate": 1.1500000000000002e-06,
"loss": 3.1264,
"step": 23
},
{
"epoch": 0.28125,
"grad_norm": 17.812040328979492,
"learning_rate": 1.2000000000000002e-06,
"loss": 3.1063,
"step": 24
},
{
"epoch": 0.29296875,
"grad_norm": 18.554685592651367,
"learning_rate": 1.25e-06,
"loss": 2.9743,
"step": 25
},
{
"epoch": 0.3046875,
"grad_norm": 19.290931701660156,
"learning_rate": 1.3e-06,
"loss": 2.7898,
"step": 26
},
{
"epoch": 0.31640625,
"grad_norm": 20.526958465576172,
"learning_rate": 1.3500000000000002e-06,
"loss": 2.6767,
"step": 27
},
{
"epoch": 0.328125,
"grad_norm": 20.140962600708008,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.476,
"step": 28
},
{
"epoch": 0.33984375,
"grad_norm": 18.80613136291504,
"learning_rate": 1.45e-06,
"loss": 2.4107,
"step": 29
},
{
"epoch": 0.3515625,
"grad_norm": 16.77231788635254,
"learning_rate": 1.5e-06,
"loss": 2.2789,
"step": 30
},
{
"epoch": 0.36328125,
"grad_norm": 15.546438217163086,
"learning_rate": 1.5500000000000002e-06,
"loss": 2.118,
"step": 31
},
{
"epoch": 0.375,
"grad_norm": 15.454617500305176,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.9487,
"step": 32
},
{
"epoch": 0.38671875,
"grad_norm": 15.873698234558105,
"learning_rate": 1.6500000000000003e-06,
"loss": 1.8438,
"step": 33
},
{
"epoch": 0.3984375,
"grad_norm": 15.691689491271973,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.6935,
"step": 34
},
{
"epoch": 0.41015625,
"grad_norm": 15.127069473266602,
"learning_rate": 1.75e-06,
"loss": 1.5188,
"step": 35
},
{
"epoch": 0.421875,
"grad_norm": 14.441194534301758,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.345,
"step": 36
},
{
"epoch": 0.43359375,
"grad_norm": 14.392739295959473,
"learning_rate": 1.85e-06,
"loss": 1.2395,
"step": 37
},
{
"epoch": 0.4453125,
"grad_norm": 14.283534049987793,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.0954,
"step": 38
},
{
"epoch": 0.45703125,
"grad_norm": 13.821670532226562,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.9594,
"step": 39
},
{
"epoch": 0.46875,
"grad_norm": 13.498543739318848,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.7972,
"step": 40
},
{
"epoch": 0.48046875,
"grad_norm": 12.805685997009277,
"learning_rate": 2.05e-06,
"loss": 0.6578,
"step": 41
},
{
"epoch": 0.4921875,
"grad_norm": 11.584136962890625,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.5148,
"step": 42
},
{
"epoch": 0.50390625,
"grad_norm": 9.801186561584473,
"learning_rate": 2.15e-06,
"loss": 0.416,
"step": 43
},
{
"epoch": 0.515625,
"grad_norm": 9.404278755187988,
"learning_rate": 2.2e-06,
"loss": 0.3419,
"step": 44
},
{
"epoch": 0.52734375,
"grad_norm": 7.185790061950684,
"learning_rate": 2.25e-06,
"loss": 0.24,
"step": 45
},
{
"epoch": 0.5390625,
"grad_norm": 4.915873050689697,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.1769,
"step": 46
},
{
"epoch": 0.55078125,
"grad_norm": 2.8505806922912598,
"learning_rate": 2.35e-06,
"loss": 0.1435,
"step": 47
},
{
"epoch": 0.5625,
"grad_norm": 1.7713755369186401,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.119,
"step": 48
},
{
"epoch": 0.57421875,
"grad_norm": 1.5673104524612427,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.1064,
"step": 49
},
{
"epoch": 0.5859375,
"grad_norm": 1.3322486877441406,
"learning_rate": 2.5e-06,
"loss": 0.0995,
"step": 50
},
{
"epoch": 0.59765625,
"grad_norm": 1.2245675325393677,
"learning_rate": 2.55e-06,
"loss": 0.0889,
"step": 51
},
{
"epoch": 0.609375,
"grad_norm": 0.8981238007545471,
"learning_rate": 2.6e-06,
"loss": 0.0847,
"step": 52
},
{
"epoch": 0.62109375,
"grad_norm": 0.6747678518295288,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0731,
"step": 53
},
{
"epoch": 0.6328125,
"grad_norm": 0.7690777778625488,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0812,
"step": 54
},
{
"epoch": 0.64453125,
"grad_norm": 0.9659140706062317,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0827,
"step": 55
},
{
"epoch": 0.65625,
"grad_norm": 0.7463306784629822,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0734,
"step": 56
},
{
"epoch": 0.66796875,
"grad_norm": 0.6388681530952454,
"learning_rate": 2.85e-06,
"loss": 0.0741,
"step": 57
},
{
"epoch": 0.6796875,
"grad_norm": 0.5176859498023987,
"learning_rate": 2.9e-06,
"loss": 0.0687,
"step": 58
},
{
"epoch": 0.69140625,
"grad_norm": 0.5809365510940552,
"learning_rate": 2.95e-06,
"loss": 0.0759,
"step": 59
},
{
"epoch": 0.703125,
"grad_norm": 0.4900883436203003,
"learning_rate": 3e-06,
"loss": 0.0637,
"step": 60
},
{
"epoch": 0.71484375,
"grad_norm": 0.46506503224372864,
"learning_rate": 3.05e-06,
"loss": 0.066,
"step": 61
},
{
"epoch": 0.7265625,
"grad_norm": 0.4315766394138336,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0619,
"step": 62
},
{
"epoch": 0.73828125,
"grad_norm": 0.6561943888664246,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0718,
"step": 63
},
{
"epoch": 0.75,
"grad_norm": 0.44578853249549866,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0662,
"step": 64
},
{
"epoch": 0.76171875,
"grad_norm": 0.352586567401886,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0612,
"step": 65
},
{
"epoch": 0.7734375,
"grad_norm": 0.3779674172401428,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0696,
"step": 66
},
{
"epoch": 0.78515625,
"grad_norm": 0.45150119066238403,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.0665,
"step": 67
},
{
"epoch": 0.796875,
"grad_norm": 0.32507383823394775,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0652,
"step": 68
},
{
"epoch": 0.80859375,
"grad_norm": 0.3733697533607483,
"learning_rate": 3.45e-06,
"loss": 0.061,
"step": 69
},
{
"epoch": 0.8203125,
"grad_norm": 0.3483797609806061,
"learning_rate": 3.5e-06,
"loss": 0.067,
"step": 70
},
{
"epoch": 0.83203125,
"grad_norm": 0.2772752642631531,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0597,
"step": 71
},
{
"epoch": 0.84375,
"grad_norm": 0.32659995555877686,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0657,
"step": 72
},
{
"epoch": 0.85546875,
"grad_norm": 0.3197411000728607,
"learning_rate": 3.65e-06,
"loss": 0.0649,
"step": 73
},
{
"epoch": 0.8671875,
"grad_norm": 0.36947256326675415,
"learning_rate": 3.7e-06,
"loss": 0.0666,
"step": 74
},
{
"epoch": 0.87890625,
"grad_norm": 0.2516244351863861,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0618,
"step": 75
},
{
"epoch": 0.890625,
"grad_norm": 0.27707308530807495,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0629,
"step": 76
},
{
"epoch": 0.90234375,
"grad_norm": 0.31011566519737244,
"learning_rate": 3.85e-06,
"loss": 0.0639,
"step": 77
},
{
"epoch": 0.9140625,
"grad_norm": 0.42964762449264526,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0575,
"step": 78
},
{
"epoch": 0.92578125,
"grad_norm": 0.2871685326099396,
"learning_rate": 3.95e-06,
"loss": 0.056,
"step": 79
},
{
"epoch": 0.9375,
"grad_norm": 0.2593545615673065,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0578,
"step": 80
},
{
"epoch": 0.94921875,
"grad_norm": 0.27979350090026855,
"learning_rate": 4.05e-06,
"loss": 0.0582,
"step": 81
},
{
"epoch": 0.9609375,
"grad_norm": 0.47774314880371094,
"learning_rate": 4.1e-06,
"loss": 0.0657,
"step": 82
},
{
"epoch": 0.97265625,
"grad_norm": 0.46003803610801697,
"learning_rate": 4.15e-06,
"loss": 0.0591,
"step": 83
},
{
"epoch": 0.984375,
"grad_norm": 0.28047817945480347,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0585,
"step": 84
},
{
"epoch": 0.99609375,
"grad_norm": 0.3024386763572693,
"learning_rate": 4.25e-06,
"loss": 0.0597,
"step": 85
},
{
"epoch": 1.0,
"grad_norm": 0.3024386763572693,
"learning_rate": 4.3e-06,
"loss": 0.0612,
"step": 86
},
{
"epoch": 1.01171875,
"grad_norm": 1.1462472677230835,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0505,
"step": 87
},
{
"epoch": 1.0234375,
"grad_norm": 0.28574419021606445,
"learning_rate": 4.4e-06,
"loss": 0.0575,
"step": 88
},
{
"epoch": 1.03515625,
"grad_norm": 0.23733267188072205,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0567,
"step": 89
},
{
"epoch": 1.046875,
"grad_norm": 0.25351643562316895,
"learning_rate": 4.5e-06,
"loss": 0.0595,
"step": 90
},
{
"epoch": 1.05859375,
"grad_norm": 0.3286800980567932,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.056,
"step": 91
},
{
"epoch": 1.0703125,
"grad_norm": 0.2708681523799896,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0541,
"step": 92
},
{
"epoch": 1.08203125,
"grad_norm": 0.30789315700531006,
"learning_rate": 4.65e-06,
"loss": 0.0583,
"step": 93
},
{
"epoch": 1.09375,
"grad_norm": 0.3800869882106781,
"learning_rate": 4.7e-06,
"loss": 0.059,
"step": 94
},
{
"epoch": 1.10546875,
"grad_norm": 0.2756796181201935,
"learning_rate": 4.75e-06,
"loss": 0.0587,
"step": 95
},
{
"epoch": 1.1171875,
"grad_norm": 0.29054075479507446,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0545,
"step": 96
},
{
"epoch": 1.12890625,
"grad_norm": 0.24633410573005676,
"learning_rate": 4.85e-06,
"loss": 0.0576,
"step": 97
},
{
"epoch": 1.140625,
"grad_norm": 0.23658645153045654,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0566,
"step": 98
},
{
"epoch": 1.15234375,
"grad_norm": 0.2314174473285675,
"learning_rate": 4.95e-06,
"loss": 0.0535,
"step": 99
},
{
"epoch": 1.1640625,
"grad_norm": 0.1932941973209381,
"learning_rate": 5e-06,
"loss": 0.0576,
"step": 100
},
{
"epoch": 1.17578125,
"grad_norm": 0.22639156877994537,
"learning_rate": 4.999926609487568e-06,
"loss": 0.0519,
"step": 101
},
{
"epoch": 1.1875,
"grad_norm": 0.23717834055423737,
"learning_rate": 4.999706442259205e-06,
"loss": 0.0487,
"step": 102
},
{
"epoch": 1.19921875,
"grad_norm": 0.25690606236457825,
"learning_rate": 4.999339511241458e-06,
"loss": 0.0542,
"step": 103
},
{
"epoch": 1.2109375,
"grad_norm": 0.28705868124961853,
"learning_rate": 4.9988258379777334e-06,
"loss": 0.0534,
"step": 104
},
{
"epoch": 1.22265625,
"grad_norm": 0.24628855288028717,
"learning_rate": 4.998165452627025e-06,
"loss": 0.0536,
"step": 105
},
{
"epoch": 1.234375,
"grad_norm": 0.38239291310310364,
"learning_rate": 4.99735839396215e-06,
"loss": 0.0545,
"step": 106
},
{
"epoch": 1.24609375,
"grad_norm": 0.22199885547161102,
"learning_rate": 4.996404709367466e-06,
"loss": 0.0525,
"step": 107
},
{
"epoch": 1.2578125,
"grad_norm": 0.2303021103143692,
"learning_rate": 4.995304454836095e-06,
"loss": 0.0544,
"step": 108
},
{
"epoch": 1.26953125,
"grad_norm": 0.245191752910614,
"learning_rate": 4.994057694966632e-06,
"loss": 0.0521,
"step": 109
},
{
"epoch": 1.28125,
"grad_norm": 0.267315149307251,
"learning_rate": 4.992664502959351e-06,
"loss": 0.0503,
"step": 110
},
{
"epoch": 1.29296875,
"grad_norm": 0.23672722280025482,
"learning_rate": 4.991124960611916e-06,
"loss": 0.0471,
"step": 111
},
{
"epoch": 1.3046875,
"grad_norm": 0.2500607371330261,
"learning_rate": 4.989439158314566e-06,
"loss": 0.0547,
"step": 112
},
{
"epoch": 1.31640625,
"grad_norm": 0.27703896164894104,
"learning_rate": 4.9876071950448185e-06,
"loss": 0.0508,
"step": 113
},
{
"epoch": 1.328125,
"grad_norm": 0.271287739276886,
"learning_rate": 4.98562917836165e-06,
"loss": 0.049,
"step": 114
},
{
"epoch": 1.33984375,
"grad_norm": 0.25890663266181946,
"learning_rate": 4.983505224399188e-06,
"loss": 0.0509,
"step": 115
},
{
"epoch": 1.3515625,
"grad_norm": 0.2870018780231476,
"learning_rate": 4.9812354578598876e-06,
"loss": 0.0518,
"step": 116
},
{
"epoch": 1.36328125,
"grad_norm": 0.2725720703601837,
"learning_rate": 4.978820012007213e-06,
"loss": 0.047,
"step": 117
},
{
"epoch": 1.375,
"grad_norm": 0.19925664365291595,
"learning_rate": 4.976259028657812e-06,
"loss": 0.0493,
"step": 118
},
{
"epoch": 1.38671875,
"grad_norm": 0.22143645584583282,
"learning_rate": 4.973552658173186e-06,
"loss": 0.0514,
"step": 119
},
{
"epoch": 1.3984375,
"grad_norm": 0.22685761749744415,
"learning_rate": 4.970701059450872e-06,
"loss": 0.0525,
"step": 120
},
{
"epoch": 1.41015625,
"grad_norm": 0.21121999621391296,
"learning_rate": 4.9677043999151e-06,
"loss": 0.051,
"step": 121
},
{
"epoch": 1.421875,
"grad_norm": 0.23914238810539246,
"learning_rate": 4.964562855506976e-06,
"loss": 0.0469,
"step": 122
},
{
"epoch": 1.43359375,
"grad_norm": 0.24409078061580658,
"learning_rate": 4.961276610674141e-06,
"loss": 0.0508,
"step": 123
},
{
"epoch": 1.4453125,
"grad_norm": 0.23388482630252838,
"learning_rate": 4.9578458583599495e-06,
"loss": 0.051,
"step": 124
},
{
"epoch": 1.45703125,
"grad_norm": 0.23801520466804504,
"learning_rate": 4.954270799992138e-06,
"loss": 0.0506,
"step": 125
},
{
"epoch": 1.46875,
"grad_norm": 0.24522367119789124,
"learning_rate": 4.950551645470998e-06,
"loss": 0.0496,
"step": 126
},
{
"epoch": 1.48046875,
"grad_norm": 0.22810965776443481,
"learning_rate": 4.9466886131570565e-06,
"loss": 0.0493,
"step": 127
},
{
"epoch": 1.4921875,
"grad_norm": 0.21910196542739868,
"learning_rate": 4.942681929858249e-06,
"loss": 0.048,
"step": 128
},
{
"epoch": 1.50390625,
"grad_norm": 0.22025763988494873,
"learning_rate": 4.9385318308166065e-06,
"loss": 0.0448,
"step": 129
},
{
"epoch": 1.515625,
"grad_norm": 0.2766706049442291,
"learning_rate": 4.934238559694448e-06,
"loss": 0.0463,
"step": 130
},
{
"epoch": 1.52734375,
"grad_norm": 0.22292804718017578,
"learning_rate": 4.929802368560066e-06,
"loss": 0.0433,
"step": 131
},
{
"epoch": 1.5390625,
"grad_norm": 0.312200129032135,
"learning_rate": 4.925223517872934e-06,
"loss": 0.0477,
"step": 132
},
{
"epoch": 1.55078125,
"grad_norm": 0.21522150933742523,
"learning_rate": 4.920502276468408e-06,
"loss": 0.0476,
"step": 133
},
{
"epoch": 1.5625,
"grad_norm": 0.2599612772464752,
"learning_rate": 4.915638921541952e-06,
"loss": 0.0472,
"step": 134
},
{
"epoch": 1.57421875,
"grad_norm": 0.2079230546951294,
"learning_rate": 4.9106337386328524e-06,
"loss": 0.0437,
"step": 135
},
{
"epoch": 1.5859375,
"grad_norm": 0.23645609617233276,
"learning_rate": 4.905487021607462e-06,
"loss": 0.0418,
"step": 136
},
{
"epoch": 1.59765625,
"grad_norm": 0.24720944464206696,
"learning_rate": 4.900199072641937e-06,
"loss": 0.0471,
"step": 137
},
{
"epoch": 1.609375,
"grad_norm": 0.24982096254825592,
"learning_rate": 4.894770202204509e-06,
"loss": 0.0427,
"step": 138
},
{
"epoch": 1.62109375,
"grad_norm": 0.2666509747505188,
"learning_rate": 4.889200729037241e-06,
"loss": 0.0457,
"step": 139
},
{
"epoch": 1.6328125,
"grad_norm": 0.2664203345775604,
"learning_rate": 4.883490980137327e-06,
"loss": 0.0467,
"step": 140
},
{
"epoch": 1.64453125,
"grad_norm": 0.250724732875824,
"learning_rate": 4.8776412907378845e-06,
"loss": 0.0389,
"step": 141
},
{
"epoch": 1.65625,
"grad_norm": 0.3050763010978699,
"learning_rate": 4.871652004288275e-06,
"loss": 0.0447,
"step": 142
},
{
"epoch": 1.66796875,
"grad_norm": 0.3108248710632324,
"learning_rate": 4.865523472433942e-06,
"loss": 0.0486,
"step": 143
},
{
"epoch": 1.6796875,
"grad_norm": 0.24726933240890503,
"learning_rate": 4.859256054995758e-06,
"loss": 0.0425,
"step": 144
},
{
"epoch": 1.69140625,
"grad_norm": 0.2529606819152832,
"learning_rate": 4.8528501199489045e-06,
"loss": 0.0468,
"step": 145
},
{
"epoch": 1.703125,
"grad_norm": 0.2741091847419739,
"learning_rate": 4.846306043401268e-06,
"loss": 0.043,
"step": 146
},
{
"epoch": 1.71484375,
"grad_norm": 0.22653311491012573,
"learning_rate": 4.839624209571352e-06,
"loss": 0.0436,
"step": 147
},
{
"epoch": 1.7265625,
"grad_norm": 0.2258974015712738,
"learning_rate": 4.832805010765724e-06,
"loss": 0.0489,
"step": 148
},
{
"epoch": 1.73828125,
"grad_norm": 0.2763097584247589,
"learning_rate": 4.8258488473559794e-06,
"loss": 0.0408,
"step": 149
},
{
"epoch": 1.75,
"grad_norm": 0.23488503694534302,
"learning_rate": 4.8187561277552376e-06,
"loss": 0.0396,
"step": 150
},
{
"epoch": 1.76171875,
"grad_norm": 0.2815094590187073,
"learning_rate": 4.811527268394157e-06,
"loss": 0.0422,
"step": 151
},
{
"epoch": 1.7734375,
"grad_norm": 0.2870430648326874,
"learning_rate": 4.804162693696494e-06,
"loss": 0.0417,
"step": 152
},
{
"epoch": 1.78515625,
"grad_norm": 0.34226351976394653,
"learning_rate": 4.796662836054176e-06,
"loss": 0.0453,
"step": 153
},
{
"epoch": 1.796875,
"grad_norm": 0.3671925961971283,
"learning_rate": 4.789028135801919e-06,
"loss": 0.043,
"step": 154
},
{
"epoch": 1.80859375,
"grad_norm": 0.26639413833618164,
"learning_rate": 4.7812590411913755e-06,
"loss": 0.0437,
"step": 155
},
{
"epoch": 1.8203125,
"grad_norm": 0.24375365674495697,
"learning_rate": 4.773356008364812e-06,
"loss": 0.0376,
"step": 156
},
{
"epoch": 1.83203125,
"grad_norm": 0.23922622203826904,
"learning_rate": 4.765319501328332e-06,
"loss": 0.0459,
"step": 157
},
{
"epoch": 1.84375,
"grad_norm": 0.21677494049072266,
"learning_rate": 4.757149991924633e-06,
"loss": 0.0429,
"step": 158
},
{
"epoch": 1.85546875,
"grad_norm": 0.2717846632003784,
"learning_rate": 4.748847959805297e-06,
"loss": 0.0403,
"step": 159
},
{
"epoch": 1.8671875,
"grad_norm": 0.23092707991600037,
"learning_rate": 4.740413892402639e-06,
"loss": 0.0417,
"step": 160
},
{
"epoch": 1.87890625,
"grad_norm": 0.23728156089782715,
"learning_rate": 4.731848284901082e-06,
"loss": 0.0445,
"step": 161
},
{
"epoch": 1.890625,
"grad_norm": 0.22474321722984314,
"learning_rate": 4.723151640208084e-06,
"loss": 0.0409,
"step": 162
},
{
"epoch": 1.90234375,
"grad_norm": 0.22294431924819946,
"learning_rate": 4.714324468924614e-06,
"loss": 0.0387,
"step": 163
},
{
"epoch": 1.9140625,
"grad_norm": 0.21790871024131775,
"learning_rate": 4.705367289315172e-06,
"loss": 0.0424,
"step": 164
},
{
"epoch": 1.92578125,
"grad_norm": 0.24538278579711914,
"learning_rate": 4.696280627277356e-06,
"loss": 0.0399,
"step": 165
},
{
"epoch": 1.9375,
"grad_norm": 0.2369818389415741,
"learning_rate": 4.687065016310996e-06,
"loss": 0.0386,
"step": 166
},
{
"epoch": 1.94921875,
"grad_norm": 0.2826277017593384,
"learning_rate": 4.6777209974868194e-06,
"loss": 0.0404,
"step": 167
},
{
"epoch": 1.9609375,
"grad_norm": 0.26429814100265503,
"learning_rate": 4.668249119414692e-06,
"loss": 0.0407,
"step": 168
},
{
"epoch": 1.97265625,
"grad_norm": 0.2524208426475525,
"learning_rate": 4.6586499382113985e-06,
"loss": 0.037,
"step": 169
},
{
"epoch": 1.984375,
"grad_norm": 0.22663331031799316,
"learning_rate": 4.648924017468003e-06,
"loss": 0.0337,
"step": 170
}
],
"logging_steps": 1,
"max_steps": 510,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 85,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.787708462666875e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}