Undi95's picture
Upload folder using huggingface_hub
557a9c3
{
"best_metric": 1.6023043394088745,
"best_model_checkpoint": "./lora-out/checkpoint-300",
"epoch": 1.7107309486780715,
"eval_steps": 50,
"global_step": 550,
"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
},
{
"epoch": 0.78,
"learning_rate": 0.00017006675677040946,
"loss": 1.4661,
"step": 251
},
{
"epoch": 0.78,
"learning_rate": 0.00016983117309676908,
"loss": 1.6071,
"step": 252
},
{
"epoch": 0.79,
"learning_rate": 0.00016959483056098445,
"loss": 1.5664,
"step": 253
},
{
"epoch": 0.79,
"learning_rate": 0.0001693577317314129,
"loss": 1.5189,
"step": 254
},
{
"epoch": 0.79,
"learning_rate": 0.00016911987918463034,
"loss": 1.5488,
"step": 255
},
{
"epoch": 0.8,
"learning_rate": 0.0001688812755054036,
"loss": 1.6153,
"step": 256
},
{
"epoch": 0.8,
"learning_rate": 0.00016864192328666202,
"loss": 1.536,
"step": 257
},
{
"epoch": 0.8,
"learning_rate": 0.00016840182512946943,
"loss": 1.624,
"step": 258
},
{
"epoch": 0.81,
"learning_rate": 0.00016816098364299582,
"loss": 1.569,
"step": 259
},
{
"epoch": 0.81,
"learning_rate": 0.00016791940144448902,
"loss": 1.588,
"step": 260
},
{
"epoch": 0.81,
"learning_rate": 0.0001676770811592463,
"loss": 1.5626,
"step": 261
},
{
"epoch": 0.81,
"learning_rate": 0.00016743402542058572,
"loss": 1.5836,
"step": 262
},
{
"epoch": 0.82,
"learning_rate": 0.00016719023686981763,
"loss": 1.5573,
"step": 263
},
{
"epoch": 0.82,
"learning_rate": 0.00016694571815621586,
"loss": 1.5815,
"step": 264
},
{
"epoch": 0.82,
"learning_rate": 0.00016670047193698912,
"loss": 1.64,
"step": 265
},
{
"epoch": 0.83,
"learning_rate": 0.0001664545008772518,
"loss": 1.6395,
"step": 266
},
{
"epoch": 0.83,
"learning_rate": 0.00016620780764999536,
"loss": 1.5927,
"step": 267
},
{
"epoch": 0.83,
"learning_rate": 0.00016596039493605913,
"loss": 1.605,
"step": 268
},
{
"epoch": 0.84,
"learning_rate": 0.000165712265424101,
"loss": 1.6219,
"step": 269
},
{
"epoch": 0.84,
"learning_rate": 0.0001654634218105686,
"loss": 1.5458,
"step": 270
},
{
"epoch": 0.84,
"learning_rate": 0.0001652138667996696,
"loss": 1.59,
"step": 271
},
{
"epoch": 0.85,
"learning_rate": 0.00016496360310334253,
"loss": 1.633,
"step": 272
},
{
"epoch": 0.85,
"learning_rate": 0.0001647126334412274,
"loss": 1.6108,
"step": 273
},
{
"epoch": 0.85,
"learning_rate": 0.0001644609605406358,
"loss": 1.5747,
"step": 274
},
{
"epoch": 0.86,
"learning_rate": 0.0001642085871365217,
"loss": 1.5393,
"step": 275
},
{
"epoch": 0.86,
"learning_rate": 0.00016395551597145133,
"loss": 1.5768,
"step": 276
},
{
"epoch": 0.86,
"learning_rate": 0.00016370174979557368,
"loss": 1.6278,
"step": 277
},
{
"epoch": 0.86,
"learning_rate": 0.0001634472913665904,
"loss": 1.5983,
"step": 278
},
{
"epoch": 0.87,
"learning_rate": 0.00016319214344972602,
"loss": 1.5701,
"step": 279
},
{
"epoch": 0.87,
"learning_rate": 0.00016293630881769773,
"loss": 1.5874,
"step": 280
},
{
"epoch": 0.87,
"learning_rate": 0.0001626797902506853,
"loss": 1.5412,
"step": 281
},
{
"epoch": 0.88,
"learning_rate": 0.000162422590536301,
"loss": 1.5733,
"step": 282
},
{
"epoch": 0.88,
"learning_rate": 0.00016216471246955906,
"loss": 1.6245,
"step": 283
},
{
"epoch": 0.88,
"learning_rate": 0.00016190615885284553,
"loss": 1.5743,
"step": 284
},
{
"epoch": 0.89,
"learning_rate": 0.00016164693249588768,
"loss": 1.5793,
"step": 285
},
{
"epoch": 0.89,
"learning_rate": 0.00016138703621572346,
"loss": 1.5672,
"step": 286
},
{
"epoch": 0.89,
"learning_rate": 0.0001611264728366711,
"loss": 1.5442,
"step": 287
},
{
"epoch": 0.9,
"learning_rate": 0.0001608652451902981,
"loss": 1.5765,
"step": 288
},
{
"epoch": 0.9,
"learning_rate": 0.00016060335611539072,
"loss": 1.6058,
"step": 289
},
{
"epoch": 0.9,
"learning_rate": 0.00016034080845792295,
"loss": 1.6156,
"step": 290
},
{
"epoch": 0.91,
"learning_rate": 0.0001600776050710257,
"loss": 1.6179,
"step": 291
},
{
"epoch": 0.91,
"learning_rate": 0.0001598137488149558,
"loss": 1.5747,
"step": 292
},
{
"epoch": 0.91,
"learning_rate": 0.00015954924255706478,
"loss": 1.5772,
"step": 293
},
{
"epoch": 0.91,
"learning_rate": 0.00015928408917176786,
"loss": 1.6064,
"step": 294
},
{
"epoch": 0.92,
"learning_rate": 0.00015901829154051265,
"loss": 1.6082,
"step": 295
},
{
"epoch": 0.92,
"learning_rate": 0.00015875185255174787,
"loss": 1.5768,
"step": 296
},
{
"epoch": 0.92,
"learning_rate": 0.0001584847751008918,
"loss": 1.5466,
"step": 297
},
{
"epoch": 0.93,
"learning_rate": 0.00015821706209030118,
"loss": 1.5127,
"step": 298
},
{
"epoch": 0.93,
"learning_rate": 0.00015794871642923927,
"loss": 1.5745,
"step": 299
},
{
"epoch": 0.93,
"learning_rate": 0.00015767974103384443,
"loss": 1.5733,
"step": 300
},
{
"epoch": 0.93,
"eval_loss": 1.6023043394088745,
"eval_runtime": 233.7298,
"eval_samples_per_second": 16.356,
"eval_steps_per_second": 4.09,
"step": 300
},
{
"epoch": 0.94,
"learning_rate": 0.0001574101388270984,
"loss": 1.6189,
"step": 301
},
{
"epoch": 0.94,
"learning_rate": 0.0001571399127387946,
"loss": 1.54,
"step": 302
},
{
"epoch": 0.94,
"learning_rate": 0.00015686906570550616,
"loss": 1.5419,
"step": 303
},
{
"epoch": 0.95,
"learning_rate": 0.00015659760067055417,
"loss": 1.576,
"step": 304
},
{
"epoch": 0.95,
"learning_rate": 0.00015632552058397544,
"loss": 1.6072,
"step": 305
},
{
"epoch": 0.95,
"learning_rate": 0.00015605282840249087,
"loss": 1.5429,
"step": 306
},
{
"epoch": 0.95,
"learning_rate": 0.00015577952708947272,
"loss": 1.5149,
"step": 307
},
{
"epoch": 0.96,
"learning_rate": 0.00015550561961491304,
"loss": 1.5744,
"step": 308
},
{
"epoch": 0.96,
"learning_rate": 0.00015523110895539097,
"loss": 1.6155,
"step": 309
},
{
"epoch": 0.96,
"learning_rate": 0.00015495599809404044,
"loss": 1.541,
"step": 310
},
{
"epoch": 0.97,
"learning_rate": 0.000154680290020518,
"loss": 1.5227,
"step": 311
},
{
"epoch": 0.97,
"learning_rate": 0.00015440398773097002,
"loss": 1.5462,
"step": 312
},
{
"epoch": 0.97,
"learning_rate": 0.00015412709422800037,
"loss": 1.56,
"step": 313
},
{
"epoch": 0.98,
"learning_rate": 0.00015384961252063763,
"loss": 1.6597,
"step": 314
},
{
"epoch": 0.98,
"learning_rate": 0.00015357154562430252,
"loss": 1.5917,
"step": 315
},
{
"epoch": 0.98,
"learning_rate": 0.000153292896560775,
"loss": 1.6058,
"step": 316
},
{
"epoch": 0.99,
"learning_rate": 0.0001530136683581615,
"loss": 1.581,
"step": 317
},
{
"epoch": 0.99,
"learning_rate": 0.00015273386405086209,
"loss": 1.592,
"step": 318
},
{
"epoch": 0.99,
"learning_rate": 0.00015245348667953726,
"loss": 1.5711,
"step": 319
},
{
"epoch": 1.0,
"learning_rate": 0.0001521725392910753,
"loss": 1.5829,
"step": 320
},
{
"epoch": 1.0,
"learning_rate": 0.00015189102493855868,
"loss": 1.5786,
"step": 321
},
{
"epoch": 1.0,
"learning_rate": 0.00015160894668123123,
"loss": 1.5848,
"step": 322
},
{
"epoch": 1.0,
"learning_rate": 0.0001513263075844648,
"loss": 1.482,
"step": 323
},
{
"epoch": 1.01,
"learning_rate": 0.000151043110719726,
"loss": 1.495,
"step": 324
},
{
"epoch": 1.01,
"learning_rate": 0.00015075935916454255,
"loss": 1.4535,
"step": 325
},
{
"epoch": 1.01,
"learning_rate": 0.00015047505600247028,
"loss": 1.5398,
"step": 326
},
{
"epoch": 1.02,
"learning_rate": 0.0001501902043230592,
"loss": 1.4649,
"step": 327
},
{
"epoch": 1.02,
"learning_rate": 0.00014990480722182022,
"loss": 1.512,
"step": 328
},
{
"epoch": 1.02,
"learning_rate": 0.0001496188678001914,
"loss": 1.4365,
"step": 329
},
{
"epoch": 1.03,
"learning_rate": 0.00014933238916550425,
"loss": 1.5408,
"step": 330
},
{
"epoch": 1.03,
"learning_rate": 0.00014904537443094986,
"loss": 1.4992,
"step": 331
},
{
"epoch": 1.03,
"learning_rate": 0.00014875782671554526,
"loss": 1.5125,
"step": 332
},
{
"epoch": 1.04,
"learning_rate": 0.00014846974914409943,
"loss": 1.4823,
"step": 333
},
{
"epoch": 1.04,
"learning_rate": 0.00014818114484717933,
"loss": 1.4985,
"step": 334
},
{
"epoch": 1.04,
"learning_rate": 0.00014789201696107594,
"loss": 1.457,
"step": 335
},
{
"epoch": 1.05,
"learning_rate": 0.00014760236862777,
"loss": 1.4623,
"step": 336
},
{
"epoch": 1.05,
"learning_rate": 0.0001473122029948982,
"loss": 1.466,
"step": 337
},
{
"epoch": 1.05,
"learning_rate": 0.0001470215232157186,
"loss": 1.4982,
"step": 338
},
{
"epoch": 1.05,
"learning_rate": 0.00014673033244907665,
"loss": 1.4369,
"step": 339
},
{
"epoch": 1.06,
"learning_rate": 0.00014643863385937076,
"loss": 1.4698,
"step": 340
},
{
"epoch": 1.06,
"learning_rate": 0.00014614643061651772,
"loss": 1.4462,
"step": 341
},
{
"epoch": 1.06,
"learning_rate": 0.0001458537258959186,
"loss": 1.4513,
"step": 342
},
{
"epoch": 1.07,
"learning_rate": 0.00014556052287842413,
"loss": 1.4304,
"step": 343
},
{
"epoch": 1.07,
"learning_rate": 0.00014526682475029994,
"loss": 1.4953,
"step": 344
},
{
"epoch": 1.07,
"learning_rate": 0.00014497263470319215,
"loss": 1.4209,
"step": 345
},
{
"epoch": 1.08,
"learning_rate": 0.00014467795593409256,
"loss": 1.4522,
"step": 346
},
{
"epoch": 1.08,
"learning_rate": 0.000144382791645304,
"loss": 1.495,
"step": 347
},
{
"epoch": 1.08,
"learning_rate": 0.0001440871450444055,
"loss": 1.4461,
"step": 348
},
{
"epoch": 1.09,
"learning_rate": 0.00014379101934421736,
"loss": 1.4592,
"step": 349
},
{
"epoch": 1.09,
"learning_rate": 0.0001434944177627664,
"loss": 1.4885,
"step": 350
},
{
"epoch": 1.09,
"eval_loss": 1.6130114793777466,
"eval_runtime": 233.7594,
"eval_samples_per_second": 16.354,
"eval_steps_per_second": 4.09,
"step": 350
},
{
"epoch": 1.09,
"learning_rate": 0.00014319734352325077,
"loss": 1.5119,
"step": 351
},
{
"epoch": 1.09,
"learning_rate": 0.00014289979985400515,
"loss": 1.4618,
"step": 352
},
{
"epoch": 1.1,
"learning_rate": 0.00014260178998846547,
"loss": 1.499,
"step": 353
},
{
"epoch": 1.1,
"learning_rate": 0.00014230331716513396,
"loss": 1.4611,
"step": 354
},
{
"epoch": 1.1,
"learning_rate": 0.00014200438462754373,
"loss": 1.4503,
"step": 355
},
{
"epoch": 1.11,
"learning_rate": 0.00014170499562422376,
"loss": 1.472,
"step": 356
},
{
"epoch": 1.11,
"learning_rate": 0.00014140515340866337,
"loss": 1.4654,
"step": 357
},
{
"epoch": 1.11,
"learning_rate": 0.00014110486123927718,
"loss": 1.4245,
"step": 358
},
{
"epoch": 1.12,
"learning_rate": 0.0001408041223793693,
"loss": 1.4944,
"step": 359
},
{
"epoch": 1.12,
"learning_rate": 0.00014050294009709813,
"loss": 1.481,
"step": 360
},
{
"epoch": 1.12,
"learning_rate": 0.00014020131766544084,
"loss": 1.4592,
"step": 361
},
{
"epoch": 1.13,
"learning_rate": 0.0001398992583621577,
"loss": 1.5189,
"step": 362
},
{
"epoch": 1.13,
"learning_rate": 0.0001395967654697565,
"loss": 1.4575,
"step": 363
},
{
"epoch": 1.13,
"learning_rate": 0.00013929384227545692,
"loss": 1.5033,
"step": 364
},
{
"epoch": 1.14,
"learning_rate": 0.0001389904920711547,
"loss": 1.5161,
"step": 365
},
{
"epoch": 1.14,
"learning_rate": 0.00013868671815338605,
"loss": 1.4703,
"step": 366
},
{
"epoch": 1.14,
"learning_rate": 0.0001383825238232916,
"loss": 1.4617,
"step": 367
},
{
"epoch": 1.14,
"learning_rate": 0.00013807791238658077,
"loss": 1.4599,
"step": 368
},
{
"epoch": 1.15,
"learning_rate": 0.00013777288715349559,
"loss": 1.4871,
"step": 369
},
{
"epoch": 1.15,
"learning_rate": 0.0001374674514387749,
"loss": 1.4825,
"step": 370
},
{
"epoch": 1.15,
"learning_rate": 0.00013716160856161834,
"loss": 1.5001,
"step": 371
},
{
"epoch": 1.16,
"learning_rate": 0.00013685536184565017,
"loss": 1.3828,
"step": 372
},
{
"epoch": 1.16,
"learning_rate": 0.00013654871461888317,
"loss": 1.4882,
"step": 373
},
{
"epoch": 1.16,
"learning_rate": 0.00013624167021368257,
"loss": 1.4426,
"step": 374
},
{
"epoch": 1.17,
"learning_rate": 0.0001359342319667298,
"loss": 1.4827,
"step": 375
},
{
"epoch": 1.17,
"learning_rate": 0.00013562640321898613,
"loss": 1.4811,
"step": 376
},
{
"epoch": 1.17,
"learning_rate": 0.00013531818731565647,
"loss": 1.4937,
"step": 377
},
{
"epoch": 1.18,
"learning_rate": 0.00013500958760615306,
"loss": 1.4668,
"step": 378
},
{
"epoch": 1.18,
"learning_rate": 0.00013470060744405883,
"loss": 1.4579,
"step": 379
},
{
"epoch": 1.18,
"learning_rate": 0.0001343912501870913,
"loss": 1.4692,
"step": 380
},
{
"epoch": 1.19,
"learning_rate": 0.00013408151919706583,
"loss": 1.4927,
"step": 381
},
{
"epoch": 1.19,
"learning_rate": 0.00013377141783985918,
"loss": 1.5073,
"step": 382
},
{
"epoch": 1.19,
"learning_rate": 0.00013346094948537296,
"loss": 1.4771,
"step": 383
},
{
"epoch": 1.19,
"learning_rate": 0.00013315011750749688,
"loss": 1.5233,
"step": 384
},
{
"epoch": 1.2,
"learning_rate": 0.00013283892528407235,
"loss": 1.4379,
"step": 385
},
{
"epoch": 1.2,
"learning_rate": 0.00013252737619685542,
"loss": 1.493,
"step": 386
},
{
"epoch": 1.2,
"learning_rate": 0.00013221547363148034,
"loss": 1.4174,
"step": 387
},
{
"epoch": 1.21,
"learning_rate": 0.00013190322097742259,
"loss": 1.4108,
"step": 388
},
{
"epoch": 1.21,
"learning_rate": 0.00013159062162796208,
"loss": 1.4713,
"step": 389
},
{
"epoch": 1.21,
"learning_rate": 0.00013127767898014637,
"loss": 1.4511,
"step": 390
},
{
"epoch": 1.22,
"learning_rate": 0.0001309643964347536,
"loss": 1.4752,
"step": 391
},
{
"epoch": 1.22,
"learning_rate": 0.00013065077739625566,
"loss": 1.4798,
"step": 392
},
{
"epoch": 1.22,
"learning_rate": 0.00013033682527278107,
"loss": 1.4372,
"step": 393
},
{
"epoch": 1.23,
"learning_rate": 0.0001300225434760781,
"loss": 1.4556,
"step": 394
},
{
"epoch": 1.23,
"learning_rate": 0.00012970793542147756,
"loss": 1.5026,
"step": 395
},
{
"epoch": 1.23,
"learning_rate": 0.00012939300452785574,
"loss": 1.4878,
"step": 396
},
{
"epoch": 1.23,
"learning_rate": 0.00012907775421759732,
"loss": 1.479,
"step": 397
},
{
"epoch": 1.24,
"learning_rate": 0.000128762187916558,
"loss": 1.4508,
"step": 398
},
{
"epoch": 1.24,
"learning_rate": 0.0001284463090540275,
"loss": 1.4923,
"step": 399
},
{
"epoch": 1.24,
"learning_rate": 0.00012813012106269208,
"loss": 1.484,
"step": 400
},
{
"epoch": 1.24,
"eval_loss": 1.616938829421997,
"eval_runtime": 233.7894,
"eval_samples_per_second": 16.352,
"eval_steps_per_second": 4.089,
"step": 400
},
{
"epoch": 1.25,
"learning_rate": 0.00012781362737859735,
"loss": 1.4867,
"step": 401
},
{
"epoch": 1.25,
"learning_rate": 0.00012749683144111095,
"loss": 1.4923,
"step": 402
},
{
"epoch": 1.25,
"learning_rate": 0.00012717973669288513,
"loss": 1.4858,
"step": 403
},
{
"epoch": 1.26,
"learning_rate": 0.00012686234657981933,
"loss": 1.4464,
"step": 404
},
{
"epoch": 1.26,
"learning_rate": 0.00012654466455102272,
"loss": 1.4598,
"step": 405
},
{
"epoch": 1.26,
"learning_rate": 0.00012622669405877685,
"loss": 1.4237,
"step": 406
},
{
"epoch": 1.27,
"learning_rate": 0.0001259084385584979,
"loss": 1.475,
"step": 407
},
{
"epoch": 1.27,
"learning_rate": 0.00012558990150869935,
"loss": 1.5201,
"step": 408
},
{
"epoch": 1.27,
"learning_rate": 0.00012527108637095427,
"loss": 1.4735,
"step": 409
},
{
"epoch": 1.28,
"learning_rate": 0.00012495199660985767,
"loss": 1.4676,
"step": 410
},
{
"epoch": 1.28,
"learning_rate": 0.00012463263569298914,
"loss": 1.4671,
"step": 411
},
{
"epoch": 1.28,
"learning_rate": 0.00012431300709087468,
"loss": 1.4724,
"step": 412
},
{
"epoch": 1.28,
"learning_rate": 0.00012399311427694945,
"loss": 1.5451,
"step": 413
},
{
"epoch": 1.29,
"learning_rate": 0.0001236729607275197,
"loss": 1.492,
"step": 414
},
{
"epoch": 1.29,
"learning_rate": 0.00012335254992172512,
"loss": 1.5186,
"step": 415
},
{
"epoch": 1.29,
"learning_rate": 0.0001230318853415012,
"loss": 1.4622,
"step": 416
},
{
"epoch": 1.3,
"learning_rate": 0.00012271097047154096,
"loss": 1.4937,
"step": 417
},
{
"epoch": 1.3,
"learning_rate": 0.00012238980879925756,
"loss": 1.4575,
"step": 418
},
{
"epoch": 1.3,
"learning_rate": 0.00012206840381474608,
"loss": 1.4801,
"step": 419
},
{
"epoch": 1.31,
"learning_rate": 0.00012174675901074577,
"loss": 1.4523,
"step": 420
},
{
"epoch": 1.31,
"learning_rate": 0.00012142487788260191,
"loss": 1.4957,
"step": 421
},
{
"epoch": 1.31,
"learning_rate": 0.00012110276392822799,
"loss": 1.4757,
"step": 422
},
{
"epoch": 1.32,
"learning_rate": 0.0001207804206480677,
"loss": 1.4769,
"step": 423
},
{
"epoch": 1.32,
"learning_rate": 0.00012045785154505676,
"loss": 1.4435,
"step": 424
},
{
"epoch": 1.32,
"learning_rate": 0.000120135060124585,
"loss": 1.5211,
"step": 425
},
{
"epoch": 1.33,
"learning_rate": 0.00011981204989445811,
"loss": 1.4248,
"step": 426
},
{
"epoch": 1.33,
"learning_rate": 0.00011948882436485969,
"loss": 1.4883,
"step": 427
},
{
"epoch": 1.33,
"learning_rate": 0.00011916538704831293,
"loss": 1.4919,
"step": 428
},
{
"epoch": 1.33,
"learning_rate": 0.00011884174145964262,
"loss": 1.4689,
"step": 429
},
{
"epoch": 1.34,
"learning_rate": 0.00011851789111593688,
"loss": 1.4071,
"step": 430
},
{
"epoch": 1.34,
"learning_rate": 0.00011819383953650874,
"loss": 1.4418,
"step": 431
},
{
"epoch": 1.34,
"learning_rate": 0.00011786959024285826,
"loss": 1.5206,
"step": 432
},
{
"epoch": 1.35,
"learning_rate": 0.00011754514675863408,
"loss": 1.446,
"step": 433
},
{
"epoch": 1.35,
"learning_rate": 0.000117220512609595,
"loss": 1.5165,
"step": 434
},
{
"epoch": 1.35,
"learning_rate": 0.0001168956913235719,
"loss": 1.4119,
"step": 435
},
{
"epoch": 1.36,
"learning_rate": 0.00011657068643042924,
"loss": 1.503,
"step": 436
},
{
"epoch": 1.36,
"learning_rate": 0.00011624550146202682,
"loss": 1.4573,
"step": 437
},
{
"epoch": 1.36,
"learning_rate": 0.00011592013995218123,
"loss": 1.4707,
"step": 438
},
{
"epoch": 1.37,
"learning_rate": 0.00011559460543662768,
"loss": 1.4304,
"step": 439
},
{
"epoch": 1.37,
"learning_rate": 0.00011526890145298137,
"loss": 1.4465,
"step": 440
},
{
"epoch": 1.37,
"learning_rate": 0.0001149430315406991,
"loss": 1.4912,
"step": 441
},
{
"epoch": 1.37,
"learning_rate": 0.0001146169992410409,
"loss": 1.4549,
"step": 442
},
{
"epoch": 1.38,
"learning_rate": 0.00011429080809703145,
"loss": 1.4528,
"step": 443
},
{
"epoch": 1.38,
"learning_rate": 0.00011396446165342165,
"loss": 1.4148,
"step": 444
},
{
"epoch": 1.38,
"learning_rate": 0.00011363796345665001,
"loss": 1.467,
"step": 445
},
{
"epoch": 1.39,
"learning_rate": 0.0001133113170548041,
"loss": 1.492,
"step": 446
},
{
"epoch": 1.39,
"learning_rate": 0.00011298452599758217,
"loss": 1.5244,
"step": 447
},
{
"epoch": 1.39,
"learning_rate": 0.00011265759383625436,
"loss": 1.4553,
"step": 448
},
{
"epoch": 1.4,
"learning_rate": 0.0001123305241236243,
"loss": 1.4764,
"step": 449
},
{
"epoch": 1.4,
"learning_rate": 0.00011200332041399027,
"loss": 1.4354,
"step": 450
},
{
"epoch": 1.4,
"eval_loss": 1.6193681955337524,
"eval_runtime": 233.6751,
"eval_samples_per_second": 16.36,
"eval_steps_per_second": 4.091,
"step": 450
},
{
"epoch": 1.4,
"learning_rate": 0.00011167598626310682,
"loss": 1.4946,
"step": 451
},
{
"epoch": 1.41,
"learning_rate": 0.00011134852522814596,
"loss": 1.4558,
"step": 452
},
{
"epoch": 1.41,
"learning_rate": 0.0001110209408676586,
"loss": 1.4549,
"step": 453
},
{
"epoch": 1.41,
"learning_rate": 0.00011069323674153585,
"loss": 1.4992,
"step": 454
},
{
"epoch": 1.42,
"learning_rate": 0.0001103654164109702,
"loss": 1.4828,
"step": 455
},
{
"epoch": 1.42,
"learning_rate": 0.00011003748343841711,
"loss": 1.4939,
"step": 456
},
{
"epoch": 1.42,
"learning_rate": 0.00010970944138755604,
"loss": 1.4761,
"step": 457
},
{
"epoch": 1.42,
"learning_rate": 0.00010938129382325184,
"loss": 1.4394,
"step": 458
},
{
"epoch": 1.43,
"learning_rate": 0.00010905304431151602,
"loss": 1.4852,
"step": 459
},
{
"epoch": 1.43,
"learning_rate": 0.00010872469641946783,
"loss": 1.4479,
"step": 460
},
{
"epoch": 1.43,
"learning_rate": 0.00010839625371529583,
"loss": 1.5161,
"step": 461
},
{
"epoch": 1.44,
"learning_rate": 0.00010806771976821872,
"loss": 1.5104,
"step": 462
},
{
"epoch": 1.44,
"learning_rate": 0.0001077390981484469,
"loss": 1.5056,
"step": 463
},
{
"epoch": 1.44,
"learning_rate": 0.00010741039242714337,
"loss": 1.4919,
"step": 464
},
{
"epoch": 1.45,
"learning_rate": 0.00010708160617638521,
"loss": 1.4605,
"step": 465
},
{
"epoch": 1.45,
"learning_rate": 0.00010675274296912452,
"loss": 1.5191,
"step": 466
},
{
"epoch": 1.45,
"learning_rate": 0.00010642380637914975,
"loss": 1.4504,
"step": 467
},
{
"epoch": 1.46,
"learning_rate": 0.00010609479998104684,
"loss": 1.4619,
"step": 468
},
{
"epoch": 1.46,
"learning_rate": 0.00010576572735016016,
"loss": 1.4619,
"step": 469
},
{
"epoch": 1.46,
"learning_rate": 0.00010543659206255409,
"loss": 1.4962,
"step": 470
},
{
"epoch": 1.47,
"learning_rate": 0.00010510739769497378,
"loss": 1.4901,
"step": 471
},
{
"epoch": 1.47,
"learning_rate": 0.0001047781478248063,
"loss": 1.4708,
"step": 472
},
{
"epoch": 1.47,
"learning_rate": 0.00010444884603004213,
"loss": 1.4756,
"step": 473
},
{
"epoch": 1.47,
"learning_rate": 0.00010411949588923577,
"loss": 1.3948,
"step": 474
},
{
"epoch": 1.48,
"learning_rate": 0.00010379010098146728,
"loss": 1.5183,
"step": 475
},
{
"epoch": 1.48,
"learning_rate": 0.00010346066488630308,
"loss": 1.4252,
"step": 476
},
{
"epoch": 1.48,
"learning_rate": 0.00010313119118375727,
"loss": 1.4686,
"step": 477
},
{
"epoch": 1.49,
"learning_rate": 0.00010280168345425256,
"loss": 1.5285,
"step": 478
},
{
"epoch": 1.49,
"learning_rate": 0.00010247214527858149,
"loss": 1.4649,
"step": 479
},
{
"epoch": 1.49,
"learning_rate": 0.0001021425802378674,
"loss": 1.4602,
"step": 480
},
{
"epoch": 1.5,
"learning_rate": 0.00010181299191352566,
"loss": 1.5102,
"step": 481
},
{
"epoch": 1.5,
"learning_rate": 0.00010148338388722465,
"loss": 1.4894,
"step": 482
},
{
"epoch": 1.5,
"learning_rate": 0.00010115375974084677,
"loss": 1.501,
"step": 483
},
{
"epoch": 1.51,
"learning_rate": 0.00010082412305644964,
"loss": 1.481,
"step": 484
},
{
"epoch": 1.51,
"learning_rate": 0.00010049447741622717,
"loss": 1.4927,
"step": 485
},
{
"epoch": 1.51,
"learning_rate": 0.00010016482640247058,
"loss": 1.512,
"step": 486
},
{
"epoch": 1.51,
"learning_rate": 9.983517359752945e-05,
"loss": 1.4622,
"step": 487
},
{
"epoch": 1.52,
"learning_rate": 9.950552258377284e-05,
"loss": 1.4956,
"step": 488
},
{
"epoch": 1.52,
"learning_rate": 9.917587694355037e-05,
"loss": 1.493,
"step": 489
},
{
"epoch": 1.52,
"learning_rate": 9.884624025915328e-05,
"loss": 1.4629,
"step": 490
},
{
"epoch": 1.53,
"learning_rate": 9.851661611277537e-05,
"loss": 1.4531,
"step": 491
},
{
"epoch": 1.53,
"learning_rate": 9.818700808647435e-05,
"loss": 1.4656,
"step": 492
},
{
"epoch": 1.53,
"learning_rate": 9.785741976213261e-05,
"loss": 1.4982,
"step": 493
},
{
"epoch": 1.54,
"learning_rate": 9.752785472141854e-05,
"loss": 1.5053,
"step": 494
},
{
"epoch": 1.54,
"learning_rate": 9.719831654574745e-05,
"loss": 1.4619,
"step": 495
},
{
"epoch": 1.54,
"learning_rate": 9.686880881624275e-05,
"loss": 1.486,
"step": 496
},
{
"epoch": 1.55,
"learning_rate": 9.653933511369696e-05,
"loss": 1.4788,
"step": 497
},
{
"epoch": 1.55,
"learning_rate": 9.620989901853275e-05,
"loss": 1.4663,
"step": 498
},
{
"epoch": 1.55,
"learning_rate": 9.588050411076424e-05,
"loss": 1.5138,
"step": 499
},
{
"epoch": 1.56,
"learning_rate": 9.555115396995788e-05,
"loss": 1.4427,
"step": 500
},
{
"epoch": 1.56,
"eval_loss": 1.6187018156051636,
"eval_runtime": 233.6591,
"eval_samples_per_second": 16.361,
"eval_steps_per_second": 4.091,
"step": 500
},
{
"epoch": 1.56,
"learning_rate": 9.522185217519371e-05,
"loss": 1.4696,
"step": 501
},
{
"epoch": 1.56,
"learning_rate": 9.489260230502626e-05,
"loss": 1.4052,
"step": 502
},
{
"epoch": 1.56,
"learning_rate": 9.45634079374459e-05,
"loss": 1.4688,
"step": 503
},
{
"epoch": 1.57,
"learning_rate": 9.423427264983986e-05,
"loss": 1.4266,
"step": 504
},
{
"epoch": 1.57,
"learning_rate": 9.390520001895321e-05,
"loss": 1.4887,
"step": 505
},
{
"epoch": 1.57,
"learning_rate": 9.357619362085027e-05,
"loss": 1.4992,
"step": 506
},
{
"epoch": 1.58,
"learning_rate": 9.32472570308755e-05,
"loss": 1.4626,
"step": 507
},
{
"epoch": 1.58,
"learning_rate": 9.291839382361481e-05,
"loss": 1.4984,
"step": 508
},
{
"epoch": 1.58,
"learning_rate": 9.258960757285664e-05,
"loss": 1.3692,
"step": 509
},
{
"epoch": 1.59,
"learning_rate": 9.226090185155314e-05,
"loss": 1.4325,
"step": 510
},
{
"epoch": 1.59,
"learning_rate": 9.19322802317813e-05,
"loss": 1.5049,
"step": 511
},
{
"epoch": 1.59,
"learning_rate": 9.160374628470421e-05,
"loss": 1.4589,
"step": 512
},
{
"epoch": 1.6,
"learning_rate": 9.127530358053218e-05,
"loss": 1.4291,
"step": 513
},
{
"epoch": 1.6,
"learning_rate": 9.094695568848402e-05,
"loss": 1.4474,
"step": 514
},
{
"epoch": 1.6,
"learning_rate": 9.061870617674817e-05,
"loss": 1.513,
"step": 515
},
{
"epoch": 1.6,
"learning_rate": 9.029055861244397e-05,
"loss": 1.4609,
"step": 516
},
{
"epoch": 1.61,
"learning_rate": 8.99625165615829e-05,
"loss": 1.5144,
"step": 517
},
{
"epoch": 1.61,
"learning_rate": 8.963458358902985e-05,
"loss": 1.4294,
"step": 518
},
{
"epoch": 1.61,
"learning_rate": 8.93067632584642e-05,
"loss": 1.4516,
"step": 519
},
{
"epoch": 1.62,
"learning_rate": 8.897905913234143e-05,
"loss": 1.4659,
"step": 520
},
{
"epoch": 1.62,
"learning_rate": 8.865147477185405e-05,
"loss": 1.4787,
"step": 521
},
{
"epoch": 1.62,
"learning_rate": 8.832401373689319e-05,
"loss": 1.4601,
"step": 522
},
{
"epoch": 1.63,
"learning_rate": 8.799667958600973e-05,
"loss": 1.4955,
"step": 523
},
{
"epoch": 1.63,
"learning_rate": 8.766947587637573e-05,
"loss": 1.4231,
"step": 524
},
{
"epoch": 1.63,
"learning_rate": 8.734240616374565e-05,
"loss": 1.4952,
"step": 525
},
{
"epoch": 1.64,
"learning_rate": 8.701547400241788e-05,
"loss": 1.4707,
"step": 526
},
{
"epoch": 1.64,
"learning_rate": 8.668868294519593e-05,
"loss": 1.5023,
"step": 527
},
{
"epoch": 1.64,
"learning_rate": 8.636203654335002e-05,
"loss": 1.4702,
"step": 528
},
{
"epoch": 1.65,
"learning_rate": 8.603553834657836e-05,
"loss": 1.4399,
"step": 529
},
{
"epoch": 1.65,
"learning_rate": 8.570919190296855e-05,
"loss": 1.5175,
"step": 530
},
{
"epoch": 1.65,
"learning_rate": 8.53830007589591e-05,
"loss": 1.4715,
"step": 531
},
{
"epoch": 1.65,
"learning_rate": 8.505696845930096e-05,
"loss": 1.5292,
"step": 532
},
{
"epoch": 1.66,
"learning_rate": 8.473109854701869e-05,
"loss": 1.5287,
"step": 533
},
{
"epoch": 1.66,
"learning_rate": 8.440539456337235e-05,
"loss": 1.4762,
"step": 534
},
{
"epoch": 1.66,
"learning_rate": 8.407986004781879e-05,
"loss": 1.4536,
"step": 535
},
{
"epoch": 1.67,
"learning_rate": 8.375449853797322e-05,
"loss": 1.5018,
"step": 536
},
{
"epoch": 1.67,
"learning_rate": 8.342931356957076e-05,
"loss": 1.4723,
"step": 537
},
{
"epoch": 1.67,
"learning_rate": 8.310430867642812e-05,
"loss": 1.4905,
"step": 538
},
{
"epoch": 1.68,
"learning_rate": 8.277948739040503e-05,
"loss": 1.4651,
"step": 539
},
{
"epoch": 1.68,
"learning_rate": 8.245485324136597e-05,
"loss": 1.4482,
"step": 540
},
{
"epoch": 1.68,
"learning_rate": 8.213040975714175e-05,
"loss": 1.3977,
"step": 541
},
{
"epoch": 1.69,
"learning_rate": 8.180616046349129e-05,
"loss": 1.5594,
"step": 542
},
{
"epoch": 1.69,
"learning_rate": 8.148210888406316e-05,
"loss": 1.4995,
"step": 543
},
{
"epoch": 1.69,
"learning_rate": 8.115825854035737e-05,
"loss": 1.5106,
"step": 544
},
{
"epoch": 1.7,
"learning_rate": 8.083461295168707e-05,
"loss": 1.4219,
"step": 545
},
{
"epoch": 1.7,
"learning_rate": 8.051117563514036e-05,
"loss": 1.4766,
"step": 546
},
{
"epoch": 1.7,
"learning_rate": 8.018795010554193e-05,
"loss": 1.5241,
"step": 547
},
{
"epoch": 1.7,
"learning_rate": 7.986493987541502e-05,
"loss": 1.4673,
"step": 548
},
{
"epoch": 1.71,
"learning_rate": 7.954214845494325e-05,
"loss": 1.4236,
"step": 549
},
{
"epoch": 1.71,
"learning_rate": 7.921957935193232e-05,
"loss": 1.4687,
"step": 550
},
{
"epoch": 1.71,
"eval_loss": 1.617763876914978,
"eval_runtime": 233.6334,
"eval_samples_per_second": 16.363,
"eval_steps_per_second": 4.092,
"step": 550
}
],
"logging_steps": 1,
"max_steps": 963,
"num_train_epochs": 3,
"save_steps": 50,
"total_flos": 1.5423494116343808e+18,
"trial_name": null,
"trial_params": null
}