prometheus-vision-13b-v1.0 / trainer_state.json
Seongyun's picture
Upload folder using huggingface_hub
5cec83c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 185,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.7688,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-06,
"loss": 1.7391,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.7429,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.5504,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.5264,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 1.4713,
"step": 6
},
{
"epoch": 0.04,
"learning_rate": 1.9998459887166635e-05,
"loss": 1.4709,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 1.9993840023056045e-05,
"loss": 1.4435,
"step": 8
},
{
"epoch": 0.05,
"learning_rate": 1.9986141830690626e-05,
"loss": 1.4711,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1.9975367681287358e-05,
"loss": 1.4134,
"step": 10
},
{
"epoch": 0.06,
"learning_rate": 1.9961520893527385e-05,
"loss": 1.3935,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 1.994460573253382e-05,
"loss": 1.3918,
"step": 12
},
{
"epoch": 0.07,
"learning_rate": 1.9924627408557963e-05,
"loss": 1.3569,
"step": 13
},
{
"epoch": 0.08,
"learning_rate": 1.9901592075374447e-05,
"loss": 1.3551,
"step": 14
},
{
"epoch": 0.08,
"learning_rate": 1.9875506828385723e-05,
"loss": 1.3527,
"step": 15
},
{
"epoch": 0.09,
"learning_rate": 1.9846379702436518e-05,
"loss": 1.333,
"step": 16
},
{
"epoch": 0.09,
"learning_rate": 1.981421966933893e-05,
"loss": 1.3099,
"step": 17
},
{
"epoch": 0.1,
"learning_rate": 1.9779036635108892e-05,
"loss": 1.323,
"step": 18
},
{
"epoch": 0.1,
"learning_rate": 1.9740841436914917e-05,
"loss": 1.2945,
"step": 19
},
{
"epoch": 0.11,
"learning_rate": 1.9699645839739987e-05,
"loss": 1.3023,
"step": 20
},
{
"epoch": 0.11,
"learning_rate": 1.9655462532757677e-05,
"loss": 1.2992,
"step": 21
},
{
"epoch": 0.12,
"learning_rate": 1.9608305125423608e-05,
"loss": 1.3281,
"step": 22
},
{
"epoch": 0.12,
"learning_rate": 1.9558188143283425e-05,
"loss": 1.2941,
"step": 23
},
{
"epoch": 0.13,
"learning_rate": 1.9505127023498603e-05,
"loss": 1.2721,
"step": 24
},
{
"epoch": 0.14,
"learning_rate": 1.9449138110091444e-05,
"loss": 1.3167,
"step": 25
},
{
"epoch": 0.14,
"learning_rate": 1.9390238648910765e-05,
"loss": 1.293,
"step": 26
},
{
"epoch": 0.15,
"learning_rate": 1.932844678231977e-05,
"loss": 1.2798,
"step": 27
},
{
"epoch": 0.15,
"learning_rate": 1.9263781543607817e-05,
"loss": 1.2861,
"step": 28
},
{
"epoch": 0.16,
"learning_rate": 1.9196262851127695e-05,
"loss": 1.2495,
"step": 29
},
{
"epoch": 0.16,
"learning_rate": 1.9125911502160365e-05,
"loss": 1.2827,
"step": 30
},
{
"epoch": 0.17,
"learning_rate": 1.905274916650891e-05,
"loss": 1.2822,
"step": 31
},
{
"epoch": 0.17,
"learning_rate": 1.897679837982373e-05,
"loss": 1.2671,
"step": 32
},
{
"epoch": 0.18,
"learning_rate": 1.8898082536661097e-05,
"loss": 1.291,
"step": 33
},
{
"epoch": 0.18,
"learning_rate": 1.8816625883277044e-05,
"loss": 1.2679,
"step": 34
},
{
"epoch": 0.19,
"learning_rate": 1.8732453510159025e-05,
"loss": 1.2845,
"step": 35
},
{
"epoch": 0.19,
"learning_rate": 1.864559134429745e-05,
"loss": 1.2779,
"step": 36
},
{
"epoch": 0.2,
"learning_rate": 1.85560661411996e-05,
"loss": 1.2692,
"step": 37
},
{
"epoch": 0.21,
"learning_rate": 1.846390547664831e-05,
"loss": 1.229,
"step": 38
},
{
"epoch": 0.21,
"learning_rate": 1.836913773820802e-05,
"loss": 1.2301,
"step": 39
},
{
"epoch": 0.22,
"learning_rate": 1.8271792116480767e-05,
"loss": 1.2511,
"step": 40
},
{
"epoch": 0.22,
"learning_rate": 1.8171898596114804e-05,
"loss": 1.256,
"step": 41
},
{
"epoch": 0.23,
"learning_rate": 1.8069487946568675e-05,
"loss": 1.2418,
"step": 42
},
{
"epoch": 0.23,
"learning_rate": 1.79645917126335e-05,
"loss": 1.2505,
"step": 43
},
{
"epoch": 0.24,
"learning_rate": 1.7857242204716497e-05,
"loss": 1.241,
"step": 44
},
{
"epoch": 0.24,
"learning_rate": 1.7747472488888622e-05,
"loss": 1.2763,
"step": 45
},
{
"epoch": 0.25,
"learning_rate": 1.763531637669949e-05,
"loss": 1.2408,
"step": 46
},
{
"epoch": 0.25,
"learning_rate": 1.752080841476264e-05,
"loss": 1.2506,
"step": 47
},
{
"epoch": 0.26,
"learning_rate": 1.7403983874114422e-05,
"loss": 1.2697,
"step": 48
},
{
"epoch": 0.26,
"learning_rate": 1.728487873934969e-05,
"loss": 1.243,
"step": 49
},
{
"epoch": 0.27,
"learning_rate": 1.7163529697537756e-05,
"loss": 1.2553,
"step": 50
},
{
"epoch": 0.28,
"learning_rate": 1.7039974126921946e-05,
"loss": 1.2179,
"step": 51
},
{
"epoch": 0.28,
"learning_rate": 1.691425008540625e-05,
"loss": 1.2576,
"step": 52
},
{
"epoch": 0.29,
"learning_rate": 1.6786396298832622e-05,
"loss": 1.2363,
"step": 53
},
{
"epoch": 0.29,
"learning_rate": 1.6656452149052568e-05,
"loss": 1.2538,
"step": 54
},
{
"epoch": 0.3,
"learning_rate": 1.6524457661796626e-05,
"loss": 1.2724,
"step": 55
},
{
"epoch": 0.3,
"learning_rate": 1.639045349434554e-05,
"loss": 1.2504,
"step": 56
},
{
"epoch": 0.31,
"learning_rate": 1.6254480923006924e-05,
"loss": 1.2342,
"step": 57
},
{
"epoch": 0.31,
"learning_rate": 1.6116581830401193e-05,
"loss": 1.2184,
"step": 58
},
{
"epoch": 0.32,
"learning_rate": 1.5976798692560796e-05,
"loss": 1.2136,
"step": 59
},
{
"epoch": 0.32,
"learning_rate": 1.5835174565846624e-05,
"loss": 1.244,
"step": 60
},
{
"epoch": 0.33,
"learning_rate": 1.5691753073685692e-05,
"loss": 1.2311,
"step": 61
},
{
"epoch": 0.34,
"learning_rate": 1.554657839313413e-05,
"loss": 1.2291,
"step": 62
},
{
"epoch": 0.34,
"learning_rate": 1.539969524126967e-05,
"loss": 1.2385,
"step": 63
},
{
"epoch": 0.35,
"learning_rate": 1.5251148861417733e-05,
"loss": 1.2122,
"step": 64
},
{
"epoch": 0.35,
"learning_rate": 1.5100985009215519e-05,
"loss": 1.2445,
"step": 65
},
{
"epoch": 0.36,
"learning_rate": 1.4949249938518203e-05,
"loss": 1.2076,
"step": 66
},
{
"epoch": 0.36,
"learning_rate": 1.4795990387151719e-05,
"loss": 1.2294,
"step": 67
},
{
"epoch": 0.37,
"learning_rate": 1.464125356251644e-05,
"loss": 1.2505,
"step": 68
},
{
"epoch": 0.37,
"learning_rate": 1.4485087127046256e-05,
"loss": 1.2479,
"step": 69
},
{
"epoch": 0.38,
"learning_rate": 1.4327539183527447e-05,
"loss": 1.2212,
"step": 70
},
{
"epoch": 0.38,
"learning_rate": 1.4168658260281944e-05,
"loss": 1.2062,
"step": 71
},
{
"epoch": 0.39,
"learning_rate": 1.400849329621953e-05,
"loss": 1.2641,
"step": 72
},
{
"epoch": 0.39,
"learning_rate": 1.3847093625763517e-05,
"loss": 1.221,
"step": 73
},
{
"epoch": 0.4,
"learning_rate": 1.3684508963654667e-05,
"loss": 1.2079,
"step": 74
},
{
"epoch": 0.41,
"learning_rate": 1.3520789389637898e-05,
"loss": 1.2164,
"step": 75
},
{
"epoch": 0.41,
"learning_rate": 1.335598533303662e-05,
"loss": 1.23,
"step": 76
},
{
"epoch": 0.42,
"learning_rate": 1.319014755721934e-05,
"loss": 1.2413,
"step": 77
},
{
"epoch": 0.42,
"learning_rate": 1.3023327143963415e-05,
"loss": 1.2242,
"step": 78
},
{
"epoch": 0.43,
"learning_rate": 1.285557547772072e-05,
"loss": 1.2217,
"step": 79
},
{
"epoch": 0.43,
"learning_rate": 1.2686944229790044e-05,
"loss": 1.2362,
"step": 80
},
{
"epoch": 0.44,
"learning_rate": 1.2517485342401201e-05,
"loss": 1.2078,
"step": 81
},
{
"epoch": 0.44,
"learning_rate": 1.2347251012715629e-05,
"loss": 1.2465,
"step": 82
},
{
"epoch": 0.45,
"learning_rate": 1.2176293676748494e-05,
"loss": 1.2225,
"step": 83
},
{
"epoch": 0.45,
"learning_rate": 1.200466599321721e-05,
"loss": 1.2061,
"step": 84
},
{
"epoch": 0.46,
"learning_rate": 1.1832420827321374e-05,
"loss": 1.2216,
"step": 85
},
{
"epoch": 0.46,
"learning_rate": 1.165961123445908e-05,
"loss": 1.1804,
"step": 86
},
{
"epoch": 0.47,
"learning_rate": 1.1486290443884666e-05,
"loss": 1.2526,
"step": 87
},
{
"epoch": 0.48,
"learning_rate": 1.131251184231291e-05,
"loss": 1.2134,
"step": 88
},
{
"epoch": 0.48,
"learning_rate": 1.1138328957474691e-05,
"loss": 1.2322,
"step": 89
},
{
"epoch": 0.49,
"learning_rate": 1.0963795441629275e-05,
"loss": 1.2102,
"step": 90
},
{
"epoch": 0.49,
"learning_rate": 1.0788965055038179e-05,
"loss": 1.2534,
"step": 91
},
{
"epoch": 0.5,
"learning_rate": 1.0613891649405816e-05,
"loss": 1.2404,
"step": 92
},
{
"epoch": 0.5,
"learning_rate": 1.0438629151291944e-05,
"loss": 1.2152,
"step": 93
},
{
"epoch": 0.51,
"learning_rate": 1.0263231545501068e-05,
"loss": 1.196,
"step": 94
},
{
"epoch": 0.51,
"learning_rate": 1.0087752858453923e-05,
"loss": 1.2154,
"step": 95
},
{
"epoch": 0.52,
"learning_rate": 9.91224714154608e-06,
"loss": 1.1875,
"step": 96
},
{
"epoch": 0.52,
"learning_rate": 9.736768454498935e-06,
"loss": 1.202,
"step": 97
},
{
"epoch": 0.53,
"learning_rate": 9.561370848708061e-06,
"loss": 1.1861,
"step": 98
},
{
"epoch": 0.54,
"learning_rate": 9.38610835059419e-06,
"loss": 1.215,
"step": 99
},
{
"epoch": 0.54,
"learning_rate": 9.211034944961825e-06,
"loss": 1.2148,
"step": 100
},
{
"epoch": 0.55,
"learning_rate": 9.036204558370725e-06,
"loss": 1.2427,
"step": 101
},
{
"epoch": 0.55,
"learning_rate": 8.861671042525312e-06,
"loss": 1.1882,
"step": 102
},
{
"epoch": 0.56,
"learning_rate": 8.68748815768709e-06,
"loss": 1.2084,
"step": 103
},
{
"epoch": 0.56,
"learning_rate": 8.513709556115335e-06,
"loss": 1.2053,
"step": 104
},
{
"epoch": 0.57,
"learning_rate": 8.340388765540923e-06,
"loss": 1.2001,
"step": 105
},
{
"epoch": 0.57,
"learning_rate": 8.16757917267863e-06,
"loss": 1.2031,
"step": 106
},
{
"epoch": 0.58,
"learning_rate": 7.995334006782793e-06,
"loss": 1.2149,
"step": 107
},
{
"epoch": 0.58,
"learning_rate": 7.823706323251512e-06,
"loss": 1.2038,
"step": 108
},
{
"epoch": 0.59,
"learning_rate": 7.652748987284375e-06,
"loss": 1.2453,
"step": 109
},
{
"epoch": 0.59,
"learning_rate": 7.4825146575988e-06,
"loss": 1.1945,
"step": 110
},
{
"epoch": 0.6,
"learning_rate": 7.313055770209961e-06,
"loss": 1.1938,
"step": 111
},
{
"epoch": 0.61,
"learning_rate": 7.144424522279283e-06,
"loss": 1.2203,
"step": 112
},
{
"epoch": 0.61,
"learning_rate": 6.976672856036586e-06,
"loss": 1.1908,
"step": 113
},
{
"epoch": 0.62,
"learning_rate": 6.809852442780664e-06,
"loss": 1.1897,
"step": 114
},
{
"epoch": 0.62,
"learning_rate": 6.6440146669633855e-06,
"loss": 1.2205,
"step": 115
},
{
"epoch": 0.63,
"learning_rate": 6.479210610362103e-06,
"loss": 1.1937,
"step": 116
},
{
"epoch": 0.63,
"learning_rate": 6.315491036345338e-06,
"loss": 1.183,
"step": 117
},
{
"epoch": 0.64,
"learning_rate": 6.1529063742364844e-06,
"loss": 1.2156,
"step": 118
},
{
"epoch": 0.64,
"learning_rate": 5.991506703780475e-06,
"loss": 1.2159,
"step": 119
},
{
"epoch": 0.65,
"learning_rate": 5.831341739718055e-06,
"loss": 1.1891,
"step": 120
},
{
"epoch": 0.65,
"learning_rate": 5.672460816472556e-06,
"loss": 1.1802,
"step": 121
},
{
"epoch": 0.66,
"learning_rate": 5.514912872953746e-06,
"loss": 1.2037,
"step": 122
},
{
"epoch": 0.66,
"learning_rate": 5.35874643748356e-06,
"loss": 1.2053,
"step": 123
},
{
"epoch": 0.67,
"learning_rate": 5.204009612848288e-06,
"loss": 1.1801,
"step": 124
},
{
"epoch": 0.68,
"learning_rate": 5.050750061481799e-06,
"loss": 1.1906,
"step": 125
},
{
"epoch": 0.68,
"learning_rate": 4.899014990784485e-06,
"loss": 1.2055,
"step": 126
},
{
"epoch": 0.69,
"learning_rate": 4.748851138582269e-06,
"loss": 1.182,
"step": 127
},
{
"epoch": 0.69,
"learning_rate": 4.6003047587303376e-06,
"loss": 1.2159,
"step": 128
},
{
"epoch": 0.7,
"learning_rate": 4.453421606865869e-06,
"loss": 1.2238,
"step": 129
},
{
"epoch": 0.7,
"learning_rate": 4.308246926314307e-06,
"loss": 1.2076,
"step": 130
},
{
"epoch": 0.71,
"learning_rate": 4.164825434153381e-06,
"loss": 1.2064,
"step": 131
},
{
"epoch": 0.71,
"learning_rate": 4.0232013074392065e-06,
"loss": 1.2111,
"step": 132
},
{
"epoch": 0.72,
"learning_rate": 3.883418169598808e-06,
"loss": 1.1995,
"step": 133
},
{
"epoch": 0.72,
"learning_rate": 3.745519076993078e-06,
"loss": 1.2339,
"step": 134
},
{
"epoch": 0.73,
"learning_rate": 3.609546505654462e-06,
"loss": 1.1774,
"step": 135
},
{
"epoch": 0.74,
"learning_rate": 3.475542338203377e-06,
"loss": 1.1799,
"step": 136
},
{
"epoch": 0.74,
"learning_rate": 3.343547850947434e-06,
"loss": 1.1655,
"step": 137
},
{
"epoch": 0.75,
"learning_rate": 3.2136037011673803e-06,
"loss": 1.1912,
"step": 138
},
{
"epoch": 0.75,
"learning_rate": 3.085749914593752e-06,
"loss": 1.1725,
"step": 139
},
{
"epoch": 0.76,
"learning_rate": 2.9600258730780564e-06,
"loss": 1.1919,
"step": 140
},
{
"epoch": 0.76,
"learning_rate": 2.8364703024622474e-06,
"loss": 1.2078,
"step": 141
},
{
"epoch": 0.77,
"learning_rate": 2.7151212606503164e-06,
"loss": 1.1955,
"step": 142
},
{
"epoch": 0.77,
"learning_rate": 2.5960161258855807e-06,
"loss": 1.2058,
"step": 143
},
{
"epoch": 0.78,
"learning_rate": 2.4791915852373604e-06,
"loss": 1.181,
"step": 144
},
{
"epoch": 0.78,
"learning_rate": 2.3646836233005133e-06,
"loss": 1.2011,
"step": 145
},
{
"epoch": 0.79,
"learning_rate": 2.252527511111381e-06,
"loss": 1.2147,
"step": 146
},
{
"epoch": 0.79,
"learning_rate": 2.1427577952835044e-06,
"loss": 1.1643,
"step": 147
},
{
"epoch": 0.8,
"learning_rate": 2.0354082873665015e-06,
"loss": 1.197,
"step": 148
},
{
"epoch": 0.81,
"learning_rate": 1.9305120534313295e-06,
"loss": 1.1915,
"step": 149
},
{
"epoch": 0.81,
"learning_rate": 1.8281014038851963e-06,
"loss": 1.1849,
"step": 150
},
{
"epoch": 0.82,
"learning_rate": 1.7282078835192362e-06,
"loss": 1.1688,
"step": 151
},
{
"epoch": 0.82,
"learning_rate": 1.6308622617919823e-06,
"loss": 1.1591,
"step": 152
},
{
"epoch": 0.83,
"learning_rate": 1.5360945233516933e-06,
"loss": 1.1911,
"step": 153
},
{
"epoch": 0.83,
"learning_rate": 1.4439338588004005e-06,
"loss": 1.1419,
"step": 154
},
{
"epoch": 0.84,
"learning_rate": 1.3544086557025493e-06,
"loss": 1.2014,
"step": 155
},
{
"epoch": 0.84,
"learning_rate": 1.2675464898409772e-06,
"loss": 1.2176,
"step": 156
},
{
"epoch": 0.85,
"learning_rate": 1.1833741167229584e-06,
"loss": 1.1694,
"step": 157
},
{
"epoch": 0.85,
"learning_rate": 1.1019174633389073e-06,
"loss": 1.2077,
"step": 158
},
{
"epoch": 0.86,
"learning_rate": 1.0232016201762696e-06,
"loss": 1.1956,
"step": 159
},
{
"epoch": 0.86,
"learning_rate": 9.472508334910946e-07,
"loss": 1.2032,
"step": 160
},
{
"epoch": 0.87,
"learning_rate": 8.740884978396358e-07,
"loss": 1.1866,
"step": 161
},
{
"epoch": 0.88,
"learning_rate": 8.037371488723078e-07,
"loss": 1.166,
"step": 162
},
{
"epoch": 0.88,
"learning_rate": 7.36218456392187e-07,
"loss": 1.218,
"step": 163
},
{
"epoch": 0.89,
"learning_rate": 6.715532176802298e-07,
"loss": 1.2047,
"step": 164
},
{
"epoch": 0.89,
"learning_rate": 6.097613510892364e-07,
"loss": 1.172,
"step": 165
},
{
"epoch": 0.9,
"learning_rate": 5.508618899085583e-07,
"loss": 1.2032,
"step": 166
},
{
"epoch": 0.9,
"learning_rate": 4.948729765014004e-07,
"loss": 1.2064,
"step": 167
},
{
"epoch": 0.91,
"learning_rate": 4.4181185671657634e-07,
"loss": 1.2207,
"step": 168
},
{
"epoch": 0.91,
"learning_rate": 3.916948745763938e-07,
"loss": 1.1999,
"step": 169
},
{
"epoch": 0.92,
"learning_rate": 3.445374672423252e-07,
"loss": 1.2194,
"step": 170
},
{
"epoch": 0.92,
"learning_rate": 3.0035416026001573e-07,
"loss": 1.1676,
"step": 171
},
{
"epoch": 0.93,
"learning_rate": 2.591585630850835e-07,
"loss": 1.1848,
"step": 172
},
{
"epoch": 0.94,
"learning_rate": 2.2096336489111025e-07,
"loss": 1.177,
"step": 173
},
{
"epoch": 0.94,
"learning_rate": 1.8578033066107392e-07,
"loss": 1.1548,
"step": 174
},
{
"epoch": 0.95,
"learning_rate": 1.5362029756348373e-07,
"loss": 1.196,
"step": 175
},
{
"epoch": 0.95,
"learning_rate": 1.2449317161427942e-07,
"loss": 1.2112,
"step": 176
},
{
"epoch": 0.96,
"learning_rate": 9.840792462555426e-08,
"loss": 1.2175,
"step": 177
},
{
"epoch": 0.96,
"learning_rate": 7.53725914420378e-08,
"loss": 1.1724,
"step": 178
},
{
"epoch": 0.97,
"learning_rate": 5.539426746618337e-08,
"loss": 1.2084,
"step": 179
},
{
"epoch": 0.97,
"learning_rate": 3.847910647261754e-08,
"loss": 1.1959,
"step": 180
},
{
"epoch": 0.98,
"learning_rate": 2.4632318712646264e-08,
"loss": 1.1975,
"step": 181
},
{
"epoch": 0.98,
"learning_rate": 1.3858169309376446e-08,
"loss": 1.1917,
"step": 182
},
{
"epoch": 0.99,
"learning_rate": 6.1599769439590896e-09,
"loss": 1.2194,
"step": 183
},
{
"epoch": 0.99,
"learning_rate": 1.540112833366969e-09,
"loss": 1.1811,
"step": 184
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.1073,
"step": 185
},
{
"epoch": 1.0,
"step": 185,
"total_flos": 210210073214976.0,
"train_loss": 1.2432800080325153,
"train_runtime": 3708.5887,
"train_samples_per_second": 6.365,
"train_steps_per_second": 0.05
}
],
"max_steps": 185,
"num_train_epochs": 1,
"total_flos": 210210073214976.0,
"trial_name": null,
"trial_params": null
}