Undi95's picture
Upload folder using huggingface_hub
557a9c3
raw
history blame
31.3 kB
{
"best_metric": 1.60513174533844,
"best_model_checkpoint": "./lora-out/checkpoint-250",
"epoch": 0.7776049766718507,
"eval_steps": 50,
"global_step": 250,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 1.7924,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.8083,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 6e-05,
"loss": 1.8177,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 1.7595,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 1.6598,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 0.00012,
"loss": 1.6919,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.00014,
"loss": 1.6706,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.00016,
"loss": 1.6879,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 0.00018,
"loss": 1.7051,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7022,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.000199999456645141,
"loss": 1.6809,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 0.00019999782658646859,
"loss": 1.6098,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 0.0001999951098416968,
"loss": 1.7014,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 0.00019999130644034888,
"loss": 1.5885,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 0.00019998641642375657,
"loss": 1.6243,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 0.00019998043984506027,
"loss": 1.6484,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 0.00019997337676920803,
"loss": 1.6093,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 0.00019996522727295496,
"loss": 1.6173,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 0.00019995599144486247,
"loss": 1.646,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 0.00019994566938529712,
"loss": 1.6469,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 0.00019993426120642983,
"loss": 1.6564,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 0.00019992176703223432,
"loss": 1.5901,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 0.000199908186998486,
"loss": 1.664,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 0.00019989352125276047,
"loss": 1.6275,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 0.00019987776995443178,
"loss": 1.5839,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 0.00019986093327467076,
"loss": 1.5611,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 0.00019984301139644334,
"loss": 1.669,
"step": 27
},
{
"epoch": 0.09,
"learning_rate": 0.0001998240045145083,
"loss": 1.5641,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 0.00019980391283541522,
"loss": 1.6023,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 0.00019978273657750238,
"loss": 1.6309,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 0.0001997604759708942,
"loss": 1.6353,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 0.00019973713125749884,
"loss": 1.6328,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 0.00019971270269100564,
"loss": 1.5683,
"step": 33
},
{
"epoch": 0.11,
"learning_rate": 0.00019968719053688213,
"loss": 1.6217,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 0.0001996605950723714,
"loss": 1.5734,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 0.00019963291658648896,
"loss": 1.6162,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 0.00019960415538001957,
"loss": 1.5922,
"step": 37
},
{
"epoch": 0.12,
"learning_rate": 0.0001995743117655141,
"loss": 1.5806,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 0.000199543386067286,
"loss": 1.5938,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 0.00019951137862140778,
"loss": 1.6386,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 0.00019947828977570756,
"loss": 1.6476,
"step": 41
},
{
"epoch": 0.13,
"learning_rate": 0.00019944411988976496,
"loss": 1.6557,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 0.00019940886933490749,
"loss": 1.5836,
"step": 43
},
{
"epoch": 0.14,
"learning_rate": 0.00019937253849420635,
"loss": 1.6421,
"step": 44
},
{
"epoch": 0.14,
"learning_rate": 0.0001993351277624723,
"loss": 1.629,
"step": 45
},
{
"epoch": 0.14,
"learning_rate": 0.00019929663754625145,
"loss": 1.6392,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 0.00019925706826382064,
"loss": 1.5677,
"step": 47
},
{
"epoch": 0.15,
"learning_rate": 0.00019921642034518317,
"loss": 1.6144,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 0.00019917469423206389,
"loss": 1.6068,
"step": 49
},
{
"epoch": 0.16,
"learning_rate": 0.00019913189037790456,
"loss": 1.6421,
"step": 50
},
{
"epoch": 0.16,
"eval_loss": 1.621693730354309,
"eval_runtime": 233.7603,
"eval_samples_per_second": 16.354,
"eval_steps_per_second": 4.09,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 0.0001990880092478588,
"loss": 1.6172,
"step": 51
},
{
"epoch": 0.16,
"learning_rate": 0.0001990430513187871,
"loss": 1.6095,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 0.00019899701707925166,
"loss": 1.5967,
"step": 53
},
{
"epoch": 0.17,
"learning_rate": 0.00019894990702951106,
"loss": 1.617,
"step": 54
},
{
"epoch": 0.17,
"learning_rate": 0.00019890172168151473,
"loss": 1.5932,
"step": 55
},
{
"epoch": 0.17,
"learning_rate": 0.0001988524615588976,
"loss": 1.6548,
"step": 56
},
{
"epoch": 0.18,
"learning_rate": 0.00019880212719697413,
"loss": 1.6033,
"step": 57
},
{
"epoch": 0.18,
"learning_rate": 0.00019875071914273278,
"loss": 1.6063,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 0.00019869823795482986,
"loss": 1.6107,
"step": 59
},
{
"epoch": 0.19,
"learning_rate": 0.00019864468420358354,
"loss": 1.5758,
"step": 60
},
{
"epoch": 0.19,
"learning_rate": 0.00019859005847096763,
"loss": 1.5723,
"step": 61
},
{
"epoch": 0.19,
"learning_rate": 0.00019853436135060527,
"loss": 1.542,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 0.00019847759344776252,
"loss": 1.5611,
"step": 63
},
{
"epoch": 0.2,
"learning_rate": 0.00019841975537934162,
"loss": 1.6157,
"step": 64
},
{
"epoch": 0.2,
"learning_rate": 0.00019836084777387458,
"loss": 1.5589,
"step": 65
},
{
"epoch": 0.21,
"learning_rate": 0.00019830087127151598,
"loss": 1.6077,
"step": 66
},
{
"epoch": 0.21,
"learning_rate": 0.00019823982652403634,
"loss": 1.5473,
"step": 67
},
{
"epoch": 0.21,
"learning_rate": 0.00019817771419481487,
"loss": 1.6265,
"step": 68
},
{
"epoch": 0.21,
"learning_rate": 0.0001981145349588323,
"loss": 1.6074,
"step": 69
},
{
"epoch": 0.22,
"learning_rate": 0.00019805028950266348,
"loss": 1.6195,
"step": 70
},
{
"epoch": 0.22,
"learning_rate": 0.00019798497852447006,
"loss": 1.5876,
"step": 71
},
{
"epoch": 0.22,
"learning_rate": 0.0001979186027339928,
"loss": 1.5978,
"step": 72
},
{
"epoch": 0.23,
"learning_rate": 0.00019785116285254381,
"loss": 1.533,
"step": 73
},
{
"epoch": 0.23,
"learning_rate": 0.00019778265961299888,
"loss": 1.5888,
"step": 74
},
{
"epoch": 0.23,
"learning_rate": 0.0001977130937597894,
"loss": 1.6211,
"step": 75
},
{
"epoch": 0.24,
"learning_rate": 0.00019764246604889415,
"loss": 1.6091,
"step": 76
},
{
"epoch": 0.24,
"learning_rate": 0.00019757077724783147,
"loss": 1.6012,
"step": 77
},
{
"epoch": 0.24,
"learning_rate": 0.0001974980281356504,
"loss": 1.6401,
"step": 78
},
{
"epoch": 0.25,
"learning_rate": 0.0001974242195029227,
"loss": 1.6111,
"step": 79
},
{
"epoch": 0.25,
"learning_rate": 0.00019734935215173392,
"loss": 1.6208,
"step": 80
},
{
"epoch": 0.25,
"learning_rate": 0.00019727342689567482,
"loss": 1.6038,
"step": 81
},
{
"epoch": 0.26,
"learning_rate": 0.00019719644455983256,
"loss": 1.5915,
"step": 82
},
{
"epoch": 0.26,
"learning_rate": 0.0001971184059807817,
"loss": 1.5872,
"step": 83
},
{
"epoch": 0.26,
"learning_rate": 0.000197039312006575,
"loss": 1.5984,
"step": 84
},
{
"epoch": 0.26,
"learning_rate": 0.0001969591634967344,
"loss": 1.5996,
"step": 85
},
{
"epoch": 0.27,
"learning_rate": 0.00019687796132224152,
"loss": 1.6056,
"step": 86
},
{
"epoch": 0.27,
"learning_rate": 0.0001967957063655283,
"loss": 1.6099,
"step": 87
},
{
"epoch": 0.27,
"learning_rate": 0.0001967123995204674,
"loss": 1.6295,
"step": 88
},
{
"epoch": 0.28,
"learning_rate": 0.00019662804169236225,
"loss": 1.5482,
"step": 89
},
{
"epoch": 0.28,
"learning_rate": 0.00019654263379793773,
"loss": 1.5781,
"step": 90
},
{
"epoch": 0.28,
"learning_rate": 0.00019645617676532963,
"loss": 1.5954,
"step": 91
},
{
"epoch": 0.29,
"learning_rate": 0.000196368671534075,
"loss": 1.619,
"step": 92
},
{
"epoch": 0.29,
"learning_rate": 0.0001962801190551016,
"loss": 1.6153,
"step": 93
},
{
"epoch": 0.29,
"learning_rate": 0.0001961905202907179,
"loss": 1.6008,
"step": 94
},
{
"epoch": 0.3,
"learning_rate": 0.00019609987621460232,
"loss": 1.5891,
"step": 95
},
{
"epoch": 0.3,
"learning_rate": 0.0001960081878117929,
"loss": 1.6438,
"step": 96
},
{
"epoch": 0.3,
"learning_rate": 0.0001959154560786764,
"loss": 1.5576,
"step": 97
},
{
"epoch": 0.3,
"learning_rate": 0.00019582168202297758,
"loss": 1.646,
"step": 98
},
{
"epoch": 0.31,
"learning_rate": 0.00019572686666374822,
"loss": 1.6269,
"step": 99
},
{
"epoch": 0.31,
"learning_rate": 0.00019563101103135602,
"loss": 1.6288,
"step": 100
},
{
"epoch": 0.31,
"eval_loss": 1.6143836975097656,
"eval_runtime": 233.6412,
"eval_samples_per_second": 16.363,
"eval_steps_per_second": 4.092,
"step": 100
},
{
"epoch": 0.31,
"learning_rate": 0.00019553411616747348,
"loss": 1.5667,
"step": 101
},
{
"epoch": 0.32,
"learning_rate": 0.00019543618312506647,
"loss": 1.6221,
"step": 102
},
{
"epoch": 0.32,
"learning_rate": 0.0001953372129683829,
"loss": 1.5992,
"step": 103
},
{
"epoch": 0.32,
"learning_rate": 0.0001952372067729411,
"loss": 1.6138,
"step": 104
},
{
"epoch": 0.33,
"learning_rate": 0.00019513616562551807,
"loss": 1.51,
"step": 105
},
{
"epoch": 0.33,
"learning_rate": 0.00019503409062413782,
"loss": 1.6227,
"step": 106
},
{
"epoch": 0.33,
"learning_rate": 0.00019493098287805927,
"loss": 1.6014,
"step": 107
},
{
"epoch": 0.34,
"learning_rate": 0.00019482684350776434,
"loss": 1.625,
"step": 108
},
{
"epoch": 0.34,
"learning_rate": 0.0001947216736449457,
"loss": 1.6109,
"step": 109
},
{
"epoch": 0.34,
"learning_rate": 0.0001946154744324945,
"loss": 1.62,
"step": 110
},
{
"epoch": 0.35,
"learning_rate": 0.00019450824702448778,
"loss": 1.5878,
"step": 111
},
{
"epoch": 0.35,
"learning_rate": 0.0001943999925861763,
"loss": 1.6264,
"step": 112
},
{
"epoch": 0.35,
"learning_rate": 0.00019429071229397157,
"loss": 1.6186,
"step": 113
},
{
"epoch": 0.35,
"learning_rate": 0.0001941804073354331,
"loss": 1.6363,
"step": 114
},
{
"epoch": 0.36,
"learning_rate": 0.00019406907890925562,
"loss": 1.5341,
"step": 115
},
{
"epoch": 0.36,
"learning_rate": 0.00019395672822525593,
"loss": 1.5986,
"step": 116
},
{
"epoch": 0.36,
"learning_rate": 0.00019384335650435985,
"loss": 1.6181,
"step": 117
},
{
"epoch": 0.37,
"learning_rate": 0.0001937289649785889,
"loss": 1.6118,
"step": 118
},
{
"epoch": 0.37,
"learning_rate": 0.0001936135548910469,
"loss": 1.6404,
"step": 119
},
{
"epoch": 0.37,
"learning_rate": 0.00019349712749590649,
"loss": 1.583,
"step": 120
},
{
"epoch": 0.38,
"learning_rate": 0.00019337968405839547,
"loss": 1.5827,
"step": 121
},
{
"epoch": 0.38,
"learning_rate": 0.00019326122585478308,
"loss": 1.6392,
"step": 122
},
{
"epoch": 0.38,
"learning_rate": 0.00019314175417236616,
"loss": 1.5861,
"step": 123
},
{
"epoch": 0.39,
"learning_rate": 0.00019302127030945508,
"loss": 1.5738,
"step": 124
},
{
"epoch": 0.39,
"learning_rate": 0.0001928997755753597,
"loss": 1.5915,
"step": 125
},
{
"epoch": 0.39,
"learning_rate": 0.00019277727129037508,
"loss": 1.617,
"step": 126
},
{
"epoch": 0.4,
"learning_rate": 0.0001926537587857672,
"loss": 1.5582,
"step": 127
},
{
"epoch": 0.4,
"learning_rate": 0.00019252923940375844,
"loss": 1.6294,
"step": 128
},
{
"epoch": 0.4,
"learning_rate": 0.00019240371449751306,
"loss": 1.6087,
"step": 129
},
{
"epoch": 0.4,
"learning_rate": 0.00019227718543112236,
"loss": 1.5749,
"step": 130
},
{
"epoch": 0.41,
"learning_rate": 0.00019214965357959005,
"loss": 1.6041,
"step": 131
},
{
"epoch": 0.41,
"learning_rate": 0.00019202112032881715,
"loss": 1.6106,
"step": 132
},
{
"epoch": 0.41,
"learning_rate": 0.00019189158707558695,
"loss": 1.5553,
"step": 133
},
{
"epoch": 0.42,
"learning_rate": 0.00019176105522754995,
"loss": 1.5638,
"step": 134
},
{
"epoch": 0.42,
"learning_rate": 0.0001916295262032084,
"loss": 1.5921,
"step": 135
},
{
"epoch": 0.42,
"learning_rate": 0.00019149700143190096,
"loss": 1.5837,
"step": 136
},
{
"epoch": 0.43,
"learning_rate": 0.00019136348235378726,
"loss": 1.6341,
"step": 137
},
{
"epoch": 0.43,
"learning_rate": 0.00019122897041983205,
"loss": 1.5678,
"step": 138
},
{
"epoch": 0.43,
"learning_rate": 0.00019109346709178963,
"loss": 1.6137,
"step": 139
},
{
"epoch": 0.44,
"learning_rate": 0.0001909569738421878,
"loss": 1.6324,
"step": 140
},
{
"epoch": 0.44,
"learning_rate": 0.00019081949215431194,
"loss": 1.612,
"step": 141
},
{
"epoch": 0.44,
"learning_rate": 0.00019068102352218897,
"loss": 1.5908,
"step": 142
},
{
"epoch": 0.44,
"learning_rate": 0.00019054156945057097,
"loss": 1.6087,
"step": 143
},
{
"epoch": 0.45,
"learning_rate": 0.00019040113145491887,
"loss": 1.5613,
"step": 144
},
{
"epoch": 0.45,
"learning_rate": 0.000190259711061386,
"loss": 1.6072,
"step": 145
},
{
"epoch": 0.45,
"learning_rate": 0.00019011730980680156,
"loss": 1.5722,
"step": 146
},
{
"epoch": 0.46,
"learning_rate": 0.0001899739292386538,
"loss": 1.5961,
"step": 147
},
{
"epoch": 0.46,
"learning_rate": 0.00018982957091507325,
"loss": 1.5409,
"step": 148
},
{
"epoch": 0.46,
"learning_rate": 0.0001896842364048159,
"loss": 1.6557,
"step": 149
},
{
"epoch": 0.47,
"learning_rate": 0.000189537927287246,
"loss": 1.5725,
"step": 150
},
{
"epoch": 0.47,
"eval_loss": 1.6101970672607422,
"eval_runtime": 233.5313,
"eval_samples_per_second": 16.37,
"eval_steps_per_second": 4.094,
"step": 150
},
{
"epoch": 0.47,
"learning_rate": 0.00018939064515231888,
"loss": 1.5949,
"step": 151
},
{
"epoch": 0.47,
"learning_rate": 0.0001892423916005639,
"loss": 1.6191,
"step": 152
},
{
"epoch": 0.48,
"learning_rate": 0.00018909316824306674,
"loss": 1.5487,
"step": 153
},
{
"epoch": 0.48,
"learning_rate": 0.00018894297670145216,
"loss": 1.5104,
"step": 154
},
{
"epoch": 0.48,
"learning_rate": 0.00018879181860786623,
"loss": 1.6392,
"step": 155
},
{
"epoch": 0.49,
"learning_rate": 0.00018863969560495866,
"loss": 1.5932,
"step": 156
},
{
"epoch": 0.49,
"learning_rate": 0.00018848660934586491,
"loss": 1.6213,
"step": 157
},
{
"epoch": 0.49,
"learning_rate": 0.0001883325614941882,
"loss": 1.5515,
"step": 158
},
{
"epoch": 0.49,
"learning_rate": 0.00018817755372398155,
"loss": 1.6166,
"step": 159
},
{
"epoch": 0.5,
"learning_rate": 0.00018802158771972943,
"loss": 1.6552,
"step": 160
},
{
"epoch": 0.5,
"learning_rate": 0.00018786466517632956,
"loss": 1.6378,
"step": 161
},
{
"epoch": 0.5,
"learning_rate": 0.00018770678779907448,
"loss": 1.5176,
"step": 162
},
{
"epoch": 0.51,
"learning_rate": 0.00018754795730363302,
"loss": 1.5793,
"step": 163
},
{
"epoch": 0.51,
"learning_rate": 0.00018738817541603156,
"loss": 1.6616,
"step": 164
},
{
"epoch": 0.51,
"learning_rate": 0.00018722744387263544,
"loss": 1.6055,
"step": 165
},
{
"epoch": 0.52,
"learning_rate": 0.00018706576442012994,
"loss": 1.6204,
"step": 166
},
{
"epoch": 0.52,
"learning_rate": 0.00018690313881550137,
"loss": 1.5952,
"step": 167
},
{
"epoch": 0.52,
"learning_rate": 0.00018673956882601803,
"loss": 1.6271,
"step": 168
},
{
"epoch": 0.53,
"learning_rate": 0.00018657505622921082,
"loss": 1.538,
"step": 169
},
{
"epoch": 0.53,
"learning_rate": 0.00018640960281285417,
"loss": 1.5874,
"step": 170
},
{
"epoch": 0.53,
"learning_rate": 0.0001862432103749464,
"loss": 1.5694,
"step": 171
},
{
"epoch": 0.53,
"learning_rate": 0.00018607588072369033,
"loss": 1.583,
"step": 172
},
{
"epoch": 0.54,
"learning_rate": 0.00018590761567747354,
"loss": 1.5961,
"step": 173
},
{
"epoch": 0.54,
"learning_rate": 0.00018573841706484866,
"loss": 1.582,
"step": 174
},
{
"epoch": 0.54,
"learning_rate": 0.0001855682867245134,
"loss": 1.6427,
"step": 175
},
{
"epoch": 0.55,
"learning_rate": 0.00018539722650529075,
"loss": 1.604,
"step": 176
},
{
"epoch": 0.55,
"learning_rate": 0.00018522523826610868,
"loss": 1.577,
"step": 177
},
{
"epoch": 0.55,
"learning_rate": 0.00018505232387598018,
"loss": 1.6339,
"step": 178
},
{
"epoch": 0.56,
"learning_rate": 0.00018487848521398265,
"loss": 1.5993,
"step": 179
},
{
"epoch": 0.56,
"learning_rate": 0.0001847037241692378,
"loss": 1.6286,
"step": 180
},
{
"epoch": 0.56,
"learning_rate": 0.00018452804264089084,
"loss": 1.5963,
"step": 181
},
{
"epoch": 0.57,
"learning_rate": 0.00018435144253809,
"loss": 1.5856,
"step": 182
},
{
"epoch": 0.57,
"learning_rate": 0.00018417392577996578,
"loss": 1.5787,
"step": 183
},
{
"epoch": 0.57,
"learning_rate": 0.00018399549429561006,
"loss": 1.5876,
"step": 184
},
{
"epoch": 0.58,
"learning_rate": 0.00018381615002405509,
"loss": 1.5565,
"step": 185
},
{
"epoch": 0.58,
"learning_rate": 0.00018363589491425248,
"loss": 1.5897,
"step": 186
},
{
"epoch": 0.58,
"learning_rate": 0.0001834547309250521,
"loss": 1.5951,
"step": 187
},
{
"epoch": 0.58,
"learning_rate": 0.00018327266002518056,
"loss": 1.5447,
"step": 188
},
{
"epoch": 0.59,
"learning_rate": 0.00018308968419322003,
"loss": 1.6087,
"step": 189
},
{
"epoch": 0.59,
"learning_rate": 0.00018290580541758668,
"loss": 1.5946,
"step": 190
},
{
"epoch": 0.59,
"learning_rate": 0.00018272102569650905,
"loss": 1.6148,
"step": 191
},
{
"epoch": 0.6,
"learning_rate": 0.00018253534703800627,
"loss": 1.649,
"step": 192
},
{
"epoch": 0.6,
"learning_rate": 0.0001823487714598664,
"loss": 1.6312,
"step": 193
},
{
"epoch": 0.6,
"learning_rate": 0.0001821613009896244,
"loss": 1.5858,
"step": 194
},
{
"epoch": 0.61,
"learning_rate": 0.00018197293766454003,
"loss": 1.5925,
"step": 195
},
{
"epoch": 0.61,
"learning_rate": 0.0001817836835315759,
"loss": 1.5604,
"step": 196
},
{
"epoch": 0.61,
"learning_rate": 0.00018159354064737506,
"loss": 1.6125,
"step": 197
},
{
"epoch": 0.62,
"learning_rate": 0.0001814025110782387,
"loss": 1.5954,
"step": 198
},
{
"epoch": 0.62,
"learning_rate": 0.00018121059690010368,
"loss": 1.5937,
"step": 199
},
{
"epoch": 0.62,
"learning_rate": 0.00018101780019852008,
"loss": 1.5582,
"step": 200
},
{
"epoch": 0.62,
"eval_loss": 1.6065257787704468,
"eval_runtime": 233.7919,
"eval_samples_per_second": 16.352,
"eval_steps_per_second": 4.089,
"step": 200
},
{
"epoch": 0.63,
"learning_rate": 0.00018082412306862837,
"loss": 1.5628,
"step": 201
},
{
"epoch": 0.63,
"learning_rate": 0.00018062956761513675,
"loss": 1.5735,
"step": 202
},
{
"epoch": 0.63,
"learning_rate": 0.00018043413595229818,
"loss": 1.6011,
"step": 203
},
{
"epoch": 0.63,
"learning_rate": 0.00018023783020388763,
"loss": 1.5434,
"step": 204
},
{
"epoch": 0.64,
"learning_rate": 0.00018004065250317868,
"loss": 1.5533,
"step": 205
},
{
"epoch": 0.64,
"learning_rate": 0.00017984260499292058,
"loss": 1.6074,
"step": 206
},
{
"epoch": 0.64,
"learning_rate": 0.00017964368982531487,
"loss": 1.5286,
"step": 207
},
{
"epoch": 0.65,
"learning_rate": 0.00017944390916199203,
"loss": 1.5161,
"step": 208
},
{
"epoch": 0.65,
"learning_rate": 0.00017924326517398793,
"loss": 1.6024,
"step": 209
},
{
"epoch": 0.65,
"learning_rate": 0.00017904176004172027,
"loss": 1.5727,
"step": 210
},
{
"epoch": 0.66,
"learning_rate": 0.0001788393959549649,
"loss": 1.5752,
"step": 211
},
{
"epoch": 0.66,
"learning_rate": 0.00017863617511283203,
"loss": 1.5845,
"step": 212
},
{
"epoch": 0.66,
"learning_rate": 0.00017843209972374233,
"loss": 1.6082,
"step": 213
},
{
"epoch": 0.67,
"learning_rate": 0.00017822717200540283,
"loss": 1.5895,
"step": 214
},
{
"epoch": 0.67,
"learning_rate": 0.00017802139418478298,
"loss": 1.5836,
"step": 215
},
{
"epoch": 0.67,
"learning_rate": 0.00017781476849809038,
"loss": 1.5996,
"step": 216
},
{
"epoch": 0.67,
"learning_rate": 0.00017760729719074644,
"loss": 1.6256,
"step": 217
},
{
"epoch": 0.68,
"learning_rate": 0.000177398982517362,
"loss": 1.628,
"step": 218
},
{
"epoch": 0.68,
"learning_rate": 0.00017718982674171284,
"loss": 1.5543,
"step": 219
},
{
"epoch": 0.68,
"learning_rate": 0.00017697983213671515,
"loss": 1.5732,
"step": 220
},
{
"epoch": 0.69,
"learning_rate": 0.0001767690009844007,
"loss": 1.5892,
"step": 221
},
{
"epoch": 0.69,
"learning_rate": 0.0001765573355758921,
"loss": 1.6524,
"step": 222
},
{
"epoch": 0.69,
"learning_rate": 0.00017634483821137787,
"loss": 1.5694,
"step": 223
},
{
"epoch": 0.7,
"learning_rate": 0.0001761315112000876,
"loss": 1.6006,
"step": 224
},
{
"epoch": 0.7,
"learning_rate": 0.00017591735686026661,
"loss": 1.6161,
"step": 225
},
{
"epoch": 0.7,
"learning_rate": 0.00017570237751915092,
"loss": 1.595,
"step": 226
},
{
"epoch": 0.71,
"learning_rate": 0.00017548657551294192,
"loss": 1.6072,
"step": 227
},
{
"epoch": 0.71,
"learning_rate": 0.000175269953186781,
"loss": 1.5855,
"step": 228
},
{
"epoch": 0.71,
"learning_rate": 0.00017505251289472406,
"loss": 1.597,
"step": 229
},
{
"epoch": 0.72,
"learning_rate": 0.0001748342569997158,
"loss": 1.5837,
"step": 230
},
{
"epoch": 0.72,
"learning_rate": 0.00017461518787356432,
"loss": 1.5422,
"step": 231
},
{
"epoch": 0.72,
"learning_rate": 0.00017439530789691506,
"loss": 1.5837,
"step": 232
},
{
"epoch": 0.72,
"learning_rate": 0.0001741746194592251,
"loss": 1.6038,
"step": 233
},
{
"epoch": 0.73,
"learning_rate": 0.00017395312495873717,
"loss": 1.5882,
"step": 234
},
{
"epoch": 0.73,
"learning_rate": 0.00017373082680245347,
"loss": 1.5763,
"step": 235
},
{
"epoch": 0.73,
"learning_rate": 0.00017350772740610976,
"loss": 1.6046,
"step": 236
},
{
"epoch": 0.74,
"learning_rate": 0.00017328382919414877,
"loss": 1.594,
"step": 237
},
{
"epoch": 0.74,
"learning_rate": 0.00017305913459969414,
"loss": 1.5903,
"step": 238
},
{
"epoch": 0.74,
"learning_rate": 0.00017283364606452396,
"loss": 1.5704,
"step": 239
},
{
"epoch": 0.75,
"learning_rate": 0.0001726073660390439,
"loss": 1.588,
"step": 240
},
{
"epoch": 0.75,
"learning_rate": 0.00017238029698226113,
"loss": 1.6273,
"step": 241
},
{
"epoch": 0.75,
"learning_rate": 0.00017215244136175705,
"loss": 1.5166,
"step": 242
},
{
"epoch": 0.76,
"learning_rate": 0.00017192380165366092,
"loss": 1.5813,
"step": 243
},
{
"epoch": 0.76,
"learning_rate": 0.0001716943803426226,
"loss": 1.5654,
"step": 244
},
{
"epoch": 0.76,
"learning_rate": 0.0001714641799217858,
"loss": 1.5548,
"step": 245
},
{
"epoch": 0.77,
"learning_rate": 0.00017123320289276085,
"loss": 1.5491,
"step": 246
},
{
"epoch": 0.77,
"learning_rate": 0.0001710014517655976,
"loss": 1.5903,
"step": 247
},
{
"epoch": 0.77,
"learning_rate": 0.00017076892905875806,
"loss": 1.5687,
"step": 248
},
{
"epoch": 0.77,
"learning_rate": 0.00017053563729908905,
"loss": 1.5975,
"step": 249
},
{
"epoch": 0.78,
"learning_rate": 0.00017030157902179485,
"loss": 1.6055,
"step": 250
},
{
"epoch": 0.78,
"eval_loss": 1.60513174533844,
"eval_runtime": 233.7813,
"eval_samples_per_second": 16.353,
"eval_steps_per_second": 4.089,
"step": 250
}
],
"logging_steps": 1,
"max_steps": 963,
"num_train_epochs": 3,
"save_steps": 50,
"total_flos": 7.01067914379264e+17,
"trial_name": null,
"trial_params": null
}