llavadoom-v1.5-7b / trainer_state.json
Leptok's picture
Add model
d5cdaa0
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.996523754345307,
"eval_steps": 500,
"global_step": 215,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.4877,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.4202,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 8.571428571428571e-06,
"loss": 1.3918,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.8286,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 1.4285714285714287e-05,
"loss": 0.4804,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.4722,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 0.291,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 1.9998859396174982e-05,
"loss": 0.2307,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 1.9995437844895337e-05,
"loss": 0.2097,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1.998973612668796e-05,
"loss": 0.1493,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 1.9981755542233175e-05,
"loss": 0.1437,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 1.9971497912068014e-05,
"loss": 0.122,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1.995896557617091e-05,
"loss": 0.1068,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 1.9944161393427923e-05,
"loss": 0.0966,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.992708874098054e-05,
"loss": 0.0902,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 1.99077515134553e-05,
"loss": 0.0871,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 1.9886154122075344e-05,
"loss": 0.0882,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 1.986230149365411e-05,
"loss": 0.087,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 1.983619906947144e-05,
"loss": 0.0795,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 1.9807852804032306e-05,
"loss": 0.074,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 1.977726916370847e-05,
"loss": 0.0855,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 1.974445512526336e-05,
"loss": 0.0786,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 1.9709418174260523e-05,
"loss": 0.0791,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 1.967216630335603e-05,
"loss": 0.0759,
"step": 24
},
{
"epoch": 0.12,
"learning_rate": 1.9632708010475166e-05,
"loss": 0.0758,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 1.959105229687389e-05,
"loss": 0.0788,
"step": 26
},
{
"epoch": 0.13,
"learning_rate": 1.954720866508546e-05,
"loss": 0.0786,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 1.9501187116752694e-05,
"loss": 0.0747,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 1.9452998150346403e-05,
"loss": 0.0832,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 1.9402652758770476e-05,
"loss": 0.0796,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 1.9350162426854152e-05,
"loss": 0.0782,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 1.9295539128732096e-05,
"loss": 0.0746,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 1.9238795325112867e-05,
"loss": 0.076,
"step": 33
},
{
"epoch": 0.16,
"learning_rate": 1.917994396043636e-05,
"loss": 0.0776,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 1.91189984599209e-05,
"loss": 0.0766,
"step": 35
},
{
"epoch": 0.17,
"learning_rate": 1.9055972726500696e-05,
"loss": 0.0766,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 1.899088113765426e-05,
"loss": 0.0757,
"step": 37
},
{
"epoch": 0.18,
"learning_rate": 1.8923738542124644e-05,
"loss": 0.0748,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 1.8854560256532098e-05,
"loss": 0.0731,
"step": 39
},
{
"epoch": 0.19,
"learning_rate": 1.8783362061880063e-05,
"loss": 0.0778,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 1.8710160199955158e-05,
"loss": 0.0771,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 1.863497136962213e-05,
"loss": 0.0765,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 1.8557812723014476e-05,
"loss": 0.076,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 1.8478701861621686e-05,
"loss": 0.0772,
"step": 44
},
{
"epoch": 0.21,
"learning_rate": 1.8397656832273982e-05,
"loss": 0.078,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 1.8314696123025456e-05,
"loss": 0.0766,
"step": 46
},
{
"epoch": 0.22,
"learning_rate": 1.8229838658936566e-05,
"loss": 0.0757,
"step": 47
},
{
"epoch": 0.22,
"learning_rate": 1.8143103797756942e-05,
"loss": 0.0766,
"step": 48
},
{
"epoch": 0.23,
"learning_rate": 1.805451132550946e-05,
"loss": 0.0756,
"step": 49
},
{
"epoch": 0.23,
"learning_rate": 1.7964081451976673e-05,
"loss": 0.0793,
"step": 50
},
{
"epoch": 0.24,
"learning_rate": 1.7871834806090502e-05,
"loss": 0.0756,
"step": 51
},
{
"epoch": 0.24,
"learning_rate": 1.7777792431226384e-05,
"loss": 0.073,
"step": 52
},
{
"epoch": 0.25,
"learning_rate": 1.7681975780402807e-05,
"loss": 0.0731,
"step": 53
},
{
"epoch": 0.25,
"learning_rate": 1.7584406711387462e-05,
"loss": 0.0776,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 1.7485107481711014e-05,
"loss": 0.0751,
"step": 55
},
{
"epoch": 0.26,
"learning_rate": 1.7384100743589698e-05,
"loss": 0.0783,
"step": 56
},
{
"epoch": 0.26,
"learning_rate": 1.7281409538757886e-05,
"loss": 0.0781,
"step": 57
},
{
"epoch": 0.27,
"learning_rate": 1.7177057293211786e-05,
"loss": 0.0758,
"step": 58
},
{
"epoch": 0.27,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.0767,
"step": 59
},
{
"epoch": 0.28,
"learning_rate": 1.696346527312053e-05,
"loss": 0.078,
"step": 60
},
{
"epoch": 0.28,
"learning_rate": 1.68542742233504e-05,
"loss": 0.076,
"step": 61
},
{
"epoch": 0.29,
"learning_rate": 1.674351957130089e-05,
"loss": 0.0818,
"step": 62
},
{
"epoch": 0.29,
"learning_rate": 1.6631226582407954e-05,
"loss": 0.0754,
"step": 63
},
{
"epoch": 0.3,
"learning_rate": 1.651742087303412e-05,
"loss": 0.0762,
"step": 64
},
{
"epoch": 0.3,
"learning_rate": 1.640212840462488e-05,
"loss": 0.0741,
"step": 65
},
{
"epoch": 0.31,
"learning_rate": 1.6285375477786322e-05,
"loss": 0.0782,
"step": 66
},
{
"epoch": 0.31,
"learning_rate": 1.6167188726285433e-05,
"loss": 0.0748,
"step": 67
},
{
"epoch": 0.32,
"learning_rate": 1.6047595110974376e-05,
"loss": 0.0838,
"step": 68
},
{
"epoch": 0.32,
"learning_rate": 1.592662191364017e-05,
"loss": 0.0743,
"step": 69
},
{
"epoch": 0.32,
"learning_rate": 1.5804296730781134e-05,
"loss": 0.0781,
"step": 70
},
{
"epoch": 0.33,
"learning_rate": 1.568064746731156e-05,
"loss": 0.0769,
"step": 71
},
{
"epoch": 0.33,
"learning_rate": 1.5555702330196024e-05,
"loss": 0.0757,
"step": 72
},
{
"epoch": 0.34,
"learning_rate": 1.542948982201479e-05,
"loss": 0.079,
"step": 73
},
{
"epoch": 0.34,
"learning_rate": 1.530203873446177e-05,
"loss": 0.0787,
"step": 74
},
{
"epoch": 0.35,
"learning_rate": 1.5173378141776569e-05,
"loss": 0.0761,
"step": 75
},
{
"epoch": 0.35,
"learning_rate": 1.5043537394112008e-05,
"loss": 0.0739,
"step": 76
},
{
"epoch": 0.36,
"learning_rate": 1.4912546110838775e-05,
"loss": 0.0735,
"step": 77
},
{
"epoch": 0.36,
"learning_rate": 1.4780434173788617e-05,
"loss": 0.0774,
"step": 78
},
{
"epoch": 0.37,
"learning_rate": 1.4647231720437687e-05,
"loss": 0.0825,
"step": 79
},
{
"epoch": 0.37,
"learning_rate": 1.4512969137031538e-05,
"loss": 0.0829,
"step": 80
},
{
"epoch": 0.38,
"learning_rate": 1.4377677051653404e-05,
"loss": 0.0763,
"step": 81
},
{
"epoch": 0.38,
"learning_rate": 1.4241386327237312e-05,
"loss": 0.0754,
"step": 82
},
{
"epoch": 0.38,
"learning_rate": 1.410412805452757e-05,
"loss": 0.0769,
"step": 83
},
{
"epoch": 0.39,
"learning_rate": 1.3965933544986351e-05,
"loss": 0.0767,
"step": 84
},
{
"epoch": 0.39,
"learning_rate": 1.3826834323650899e-05,
"loss": 0.0761,
"step": 85
},
{
"epoch": 0.4,
"learning_rate": 1.368686212194199e-05,
"loss": 0.0774,
"step": 86
},
{
"epoch": 0.4,
"learning_rate": 1.3546048870425356e-05,
"loss": 0.0735,
"step": 87
},
{
"epoch": 0.41,
"learning_rate": 1.340442669152766e-05,
"loss": 0.0767,
"step": 88
},
{
"epoch": 0.41,
"learning_rate": 1.3262027892208696e-05,
"loss": 0.0778,
"step": 89
},
{
"epoch": 0.42,
"learning_rate": 1.311888495659149e-05,
"loss": 0.0752,
"step": 90
},
{
"epoch": 0.42,
"learning_rate": 1.297503053855203e-05,
"loss": 0.0729,
"step": 91
},
{
"epoch": 0.43,
"learning_rate": 1.2830497454270206e-05,
"loss": 0.0741,
"step": 92
},
{
"epoch": 0.43,
"learning_rate": 1.2685318674743769e-05,
"loss": 0.0764,
"step": 93
},
{
"epoch": 0.44,
"learning_rate": 1.2539527318266971e-05,
"loss": 0.0762,
"step": 94
},
{
"epoch": 0.44,
"learning_rate": 1.2393156642875579e-05,
"loss": 0.0804,
"step": 95
},
{
"epoch": 0.44,
"learning_rate": 1.2246240038760042e-05,
"loss": 0.0739,
"step": 96
},
{
"epoch": 0.45,
"learning_rate": 1.2098811020648475e-05,
"loss": 0.0734,
"step": 97
},
{
"epoch": 0.45,
"learning_rate": 1.1950903220161286e-05,
"loss": 0.0755,
"step": 98
},
{
"epoch": 0.46,
"learning_rate": 1.180255037813906e-05,
"loss": 0.0756,
"step": 99
},
{
"epoch": 0.46,
"learning_rate": 1.1653786336945614e-05,
"loss": 0.0763,
"step": 100
},
{
"epoch": 0.47,
"learning_rate": 1.1504645032747832e-05,
"loss": 0.0754,
"step": 101
},
{
"epoch": 0.47,
"learning_rate": 1.1355160487774119e-05,
"loss": 0.074,
"step": 102
},
{
"epoch": 0.48,
"learning_rate": 1.1205366802553231e-05,
"loss": 0.0757,
"step": 103
},
{
"epoch": 0.48,
"learning_rate": 1.1055298148135236e-05,
"loss": 0.072,
"step": 104
},
{
"epoch": 0.49,
"learning_rate": 1.090498875829638e-05,
"loss": 0.0754,
"step": 105
},
{
"epoch": 0.49,
"learning_rate": 1.0754472921729661e-05,
"loss": 0.0752,
"step": 106
},
{
"epoch": 0.5,
"learning_rate": 1.0603784974222862e-05,
"loss": 0.0753,
"step": 107
},
{
"epoch": 0.5,
"learning_rate": 1.0452959290825846e-05,
"loss": 0.0777,
"step": 108
},
{
"epoch": 0.51,
"learning_rate": 1.030203027800889e-05,
"loss": 0.0793,
"step": 109
},
{
"epoch": 0.51,
"learning_rate": 1.015103236581386e-05,
"loss": 0.0781,
"step": 110
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.0748,
"step": 111
},
{
"epoch": 0.52,
"learning_rate": 9.848967634186142e-06,
"loss": 0.0756,
"step": 112
},
{
"epoch": 0.52,
"learning_rate": 9.697969721991114e-06,
"loss": 0.0754,
"step": 113
},
{
"epoch": 0.53,
"learning_rate": 9.547040709174159e-06,
"loss": 0.0782,
"step": 114
},
{
"epoch": 0.53,
"learning_rate": 9.39621502577714e-06,
"loss": 0.0761,
"step": 115
},
{
"epoch": 0.54,
"learning_rate": 9.24552707827034e-06,
"loss": 0.0782,
"step": 116
},
{
"epoch": 0.54,
"learning_rate": 9.095011241703623e-06,
"loss": 0.0737,
"step": 117
},
{
"epoch": 0.55,
"learning_rate": 8.944701851864767e-06,
"loss": 0.0746,
"step": 118
},
{
"epoch": 0.55,
"learning_rate": 8.79463319744677e-06,
"loss": 0.074,
"step": 119
},
{
"epoch": 0.56,
"learning_rate": 8.644839512225886e-06,
"loss": 0.077,
"step": 120
},
{
"epoch": 0.56,
"learning_rate": 8.49535496725217e-06,
"loss": 0.076,
"step": 121
},
{
"epoch": 0.57,
"learning_rate": 8.346213663054388e-06,
"loss": 0.0714,
"step": 122
},
{
"epoch": 0.57,
"learning_rate": 8.197449621860944e-06,
"loss": 0.0745,
"step": 123
},
{
"epoch": 0.57,
"learning_rate": 8.04909677983872e-06,
"loss": 0.0774,
"step": 124
},
{
"epoch": 0.58,
"learning_rate": 7.901188979351527e-06,
"loss": 0.0747,
"step": 125
},
{
"epoch": 0.58,
"learning_rate": 7.753759961239965e-06,
"loss": 0.0759,
"step": 126
},
{
"epoch": 0.59,
"learning_rate": 7.606843357124426e-06,
"loss": 0.0786,
"step": 127
},
{
"epoch": 0.59,
"learning_rate": 7.460472681733031e-06,
"loss": 0.0761,
"step": 128
},
{
"epoch": 0.6,
"learning_rate": 7.314681325256232e-06,
"loss": 0.0719,
"step": 129
},
{
"epoch": 0.6,
"learning_rate": 7.169502545729798e-06,
"loss": 0.0744,
"step": 130
},
{
"epoch": 0.61,
"learning_rate": 7.024969461447973e-06,
"loss": 0.0742,
"step": 131
},
{
"epoch": 0.61,
"learning_rate": 6.881115043408512e-06,
"loss": 0.0784,
"step": 132
},
{
"epoch": 0.62,
"learning_rate": 6.7379721077913095e-06,
"loss": 0.0763,
"step": 133
},
{
"epoch": 0.62,
"learning_rate": 6.595573308472338e-06,
"loss": 0.0741,
"step": 134
},
{
"epoch": 0.63,
"learning_rate": 6.453951129574644e-06,
"loss": 0.0772,
"step": 135
},
{
"epoch": 0.63,
"learning_rate": 6.3131378780580134e-06,
"loss": 0.0762,
"step": 136
},
{
"epoch": 0.63,
"learning_rate": 6.173165676349103e-06,
"loss": 0.0762,
"step": 137
},
{
"epoch": 0.64,
"learning_rate": 6.0340664550136494e-06,
"loss": 0.0801,
"step": 138
},
{
"epoch": 0.64,
"learning_rate": 5.895871945472434e-06,
"loss": 0.0756,
"step": 139
},
{
"epoch": 0.65,
"learning_rate": 5.75861367276269e-06,
"loss": 0.0754,
"step": 140
},
{
"epoch": 0.65,
"learning_rate": 5.622322948346595e-06,
"loss": 0.0737,
"step": 141
},
{
"epoch": 0.66,
"learning_rate": 5.4870308629684675e-06,
"loss": 0.0757,
"step": 142
},
{
"epoch": 0.66,
"learning_rate": 5.352768279562315e-06,
"loss": 0.0766,
"step": 143
},
{
"epoch": 0.67,
"learning_rate": 5.219565826211382e-06,
"loss": 0.0774,
"step": 144
},
{
"epoch": 0.67,
"learning_rate": 5.087453889161229e-06,
"loss": 0.075,
"step": 145
},
{
"epoch": 0.68,
"learning_rate": 4.956462605887994e-06,
"loss": 0.0739,
"step": 146
},
{
"epoch": 0.68,
"learning_rate": 4.826621858223431e-06,
"loss": 0.0771,
"step": 147
},
{
"epoch": 0.69,
"learning_rate": 4.697961265538231e-06,
"loss": 0.0757,
"step": 148
},
{
"epoch": 0.69,
"learning_rate": 4.570510177985213e-06,
"loss": 0.0737,
"step": 149
},
{
"epoch": 0.7,
"learning_rate": 4.444297669803981e-06,
"loss": 0.0765,
"step": 150
},
{
"epoch": 0.7,
"learning_rate": 4.319352532688444e-06,
"loss": 0.0775,
"step": 151
},
{
"epoch": 0.7,
"learning_rate": 4.1957032692188685e-06,
"loss": 0.0762,
"step": 152
},
{
"epoch": 0.71,
"learning_rate": 4.073378086359834e-06,
"loss": 0.0766,
"step": 153
},
{
"epoch": 0.71,
"learning_rate": 3.952404889025626e-06,
"loss": 0.0741,
"step": 154
},
{
"epoch": 0.72,
"learning_rate": 3.832811273714569e-06,
"loss": 0.0746,
"step": 155
},
{
"epoch": 0.72,
"learning_rate": 3.714624522213681e-06,
"loss": 0.0713,
"step": 156
},
{
"epoch": 0.73,
"learning_rate": 3.5978715953751207e-06,
"loss": 0.0716,
"step": 157
},
{
"epoch": 0.73,
"learning_rate": 3.4825791269658782e-06,
"loss": 0.0754,
"step": 158
},
{
"epoch": 0.74,
"learning_rate": 3.3687734175920505e-06,
"loss": 0.0708,
"step": 159
},
{
"epoch": 0.74,
"learning_rate": 3.2564804286991137e-06,
"loss": 0.0744,
"step": 160
},
{
"epoch": 0.75,
"learning_rate": 3.145725776649602e-06,
"loss": 0.0767,
"step": 161
},
{
"epoch": 0.75,
"learning_rate": 3.036534726879473e-06,
"loss": 0.0728,
"step": 162
},
{
"epoch": 0.76,
"learning_rate": 2.9289321881345257e-06,
"loss": 0.0733,
"step": 163
},
{
"epoch": 0.76,
"learning_rate": 2.8229427067882165e-06,
"loss": 0.0742,
"step": 164
},
{
"epoch": 0.76,
"learning_rate": 2.7185904612421177e-06,
"loss": 0.0756,
"step": 165
},
{
"epoch": 0.77,
"learning_rate": 2.615899256410306e-06,
"loss": 0.0724,
"step": 166
},
{
"epoch": 0.77,
"learning_rate": 2.514892518288988e-06,
"loss": 0.0755,
"step": 167
},
{
"epoch": 0.78,
"learning_rate": 2.415593288612541e-06,
"loss": 0.0745,
"step": 168
},
{
"epoch": 0.78,
"learning_rate": 2.318024219597196e-06,
"loss": 0.0739,
"step": 169
},
{
"epoch": 0.79,
"learning_rate": 2.222207568773619e-06,
"loss": 0.0737,
"step": 170
},
{
"epoch": 0.79,
"learning_rate": 2.1281651939094996e-06,
"loss": 0.0767,
"step": 171
},
{
"epoch": 0.8,
"learning_rate": 2.03591854802333e-06,
"loss": 0.0748,
"step": 172
},
{
"epoch": 0.8,
"learning_rate": 1.94548867449054e-06,
"loss": 0.0773,
"step": 173
},
{
"epoch": 0.81,
"learning_rate": 1.8568962022430637e-06,
"loss": 0.0736,
"step": 174
},
{
"epoch": 0.81,
"learning_rate": 1.7701613410634367e-06,
"loss": 0.0743,
"step": 175
},
{
"epoch": 0.82,
"learning_rate": 1.6853038769745466e-06,
"loss": 0.0749,
"step": 176
},
{
"epoch": 0.82,
"learning_rate": 1.6023431677260215e-06,
"loss": 0.0755,
"step": 177
},
{
"epoch": 0.83,
"learning_rate": 1.5212981383783154e-06,
"loss": 0.0735,
"step": 178
},
{
"epoch": 0.83,
"learning_rate": 1.4421872769855262e-06,
"loss": 0.0776,
"step": 179
},
{
"epoch": 0.83,
"learning_rate": 1.3650286303778715e-06,
"loss": 0.0754,
"step": 180
},
{
"epoch": 0.84,
"learning_rate": 1.2898398000448441e-06,
"loss": 0.0719,
"step": 181
},
{
"epoch": 0.84,
"learning_rate": 1.2166379381199423e-06,
"loss": 0.074,
"step": 182
},
{
"epoch": 0.85,
"learning_rate": 1.1454397434679022e-06,
"loss": 0.0751,
"step": 183
},
{
"epoch": 0.85,
"learning_rate": 1.0762614578753571e-06,
"loss": 0.0743,
"step": 184
},
{
"epoch": 0.86,
"learning_rate": 1.0091188623457415e-06,
"loss": 0.0742,
"step": 185
},
{
"epoch": 0.86,
"learning_rate": 9.440272734993072e-07,
"loss": 0.0778,
"step": 186
},
{
"epoch": 0.87,
"learning_rate": 8.810015400790994e-07,
"loss": 0.0742,
"step": 187
},
{
"epoch": 0.87,
"learning_rate": 8.200560395636414e-07,
"loss": 0.0764,
"step": 188
},
{
"epoch": 0.88,
"learning_rate": 7.612046748871327e-07,
"loss": 0.0735,
"step": 189
},
{
"epoch": 0.88,
"learning_rate": 7.044608712679058e-07,
"loss": 0.0728,
"step": 190
},
{
"epoch": 0.89,
"learning_rate": 6.498375731458529e-07,
"loss": 0.0764,
"step": 191
},
{
"epoch": 0.89,
"learning_rate": 5.973472412295256e-07,
"loss": 0.0751,
"step": 192
},
{
"epoch": 0.89,
"learning_rate": 5.470018496535967e-07,
"loss": 0.0739,
"step": 193
},
{
"epoch": 0.9,
"learning_rate": 4.988128832473105e-07,
"loss": 0.0719,
"step": 194
},
{
"epoch": 0.9,
"learning_rate": 4.5279133491454406e-07,
"loss": 0.0767,
"step": 195
},
{
"epoch": 0.91,
"learning_rate": 4.089477031261113e-07,
"loss": 0.0744,
"step": 196
},
{
"epoch": 0.91,
"learning_rate": 3.6729198952483725e-07,
"loss": 0.0759,
"step": 197
},
{
"epoch": 0.92,
"learning_rate": 3.278336966439744e-07,
"loss": 0.0738,
"step": 198
},
{
"epoch": 0.92,
"learning_rate": 2.905818257394799e-07,
"loss": 0.0739,
"step": 199
},
{
"epoch": 0.93,
"learning_rate": 2.5554487473664404e-07,
"loss": 0.0777,
"step": 200
},
{
"epoch": 0.93,
"learning_rate": 2.2273083629153148e-07,
"loss": 0.0768,
"step": 201
},
{
"epoch": 0.94,
"learning_rate": 1.921471959676957e-07,
"loss": 0.0765,
"step": 202
},
{
"epoch": 0.94,
"learning_rate": 1.6380093052856482e-07,
"loss": 0.0719,
"step": 203
},
{
"epoch": 0.95,
"learning_rate": 1.3769850634589356e-07,
"loss": 0.0764,
"step": 204
},
{
"epoch": 0.95,
"learning_rate": 1.1384587792465873e-07,
"loss": 0.0738,
"step": 205
},
{
"epoch": 0.95,
"learning_rate": 9.224848654469932e-08,
"loss": 0.0769,
"step": 206
},
{
"epoch": 0.96,
"learning_rate": 7.291125901946027e-08,
"loss": 0.0734,
"step": 207
},
{
"epoch": 0.96,
"learning_rate": 5.5838606572078404e-08,
"loss": 0.0788,
"step": 208
},
{
"epoch": 0.97,
"learning_rate": 4.103442382909051e-08,
"loss": 0.075,
"step": 209
},
{
"epoch": 0.97,
"learning_rate": 2.850208793198861e-08,
"loss": 0.0735,
"step": 210
},
{
"epoch": 0.98,
"learning_rate": 1.824445776682504e-08,
"loss": 0.0709,
"step": 211
},
{
"epoch": 0.98,
"learning_rate": 1.0263873312040818e-08,
"loss": 0.0761,
"step": 212
},
{
"epoch": 0.99,
"learning_rate": 4.562155104665955e-09,
"loss": 0.0752,
"step": 213
},
{
"epoch": 0.99,
"learning_rate": 1.1406038250205699e-09,
"loss": 0.0791,
"step": 214
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.0748,
"step": 215
},
{
"epoch": 1.0,
"step": 215,
"total_flos": 119841345601536.0,
"train_loss": 0.10572562858808872,
"train_runtime": 2699.2275,
"train_samples_per_second": 10.23,
"train_steps_per_second": 0.08
}
],
"logging_steps": 1.0,
"max_steps": 215,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"total_flos": 119841345601536.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}