2025801013_anlp_assignment1 / histories /C1_BitPairTokenizer_gelu_history.json
samvaran's picture
Upload histories/C1_BitPairTokenizer_gelu_history.json with huggingface_hub
1da8a65 verified
Raw History Blame Contribute Delete
4.74 kB
[
{
"epoch": 1,
"train_loss": 1.6858053545518354,
"val_loss": 0.595555675094053,
"train_acc": 0.5100532670454545,
"val_acc": 0.830299352750809,
"train_sec": 81.48685264587402,
"peak_gb": 1.055113216
},
{
"epoch": 2,
"train_loss": 0.4264597928388552,
"val_loss": 0.1685853291226565,
"train_acc": 0.8773850319602273,
"val_acc": 0.9523631337648328,
"train_sec": 81.06164336204529,
"peak_gb": 1.055113216
},
{
"epoch": 3,
"train_loss": 0.18242434504357252,
"val_loss": 0.0931830421459842,
"train_acc": 0.9471795099431818,
"val_acc": 0.9742651024811219,
"train_sec": 81.19477081298828,
"peak_gb": 1.055113216
},
{
"epoch": 4,
"train_loss": 0.10348158661953427,
"val_loss": 0.05390633615025167,
"train_acc": 0.9700102095170454,
"val_acc": 0.9851301240560949,
"train_sec": 81.2665605545044,
"peak_gb": 1.055113216
},
{
"epoch": 5,
"train_loss": 0.06788339015773752,
"val_loss": 0.03551092401886321,
"train_acc": 0.9802175071022727,
"val_acc": 0.9904159924487594,
"train_sec": 81.26876783370972,
"peak_gb": 1.055113216
},
{
"epoch": 6,
"train_loss": 0.04864796966483647,
"val_loss": 0.028770122571799103,
"train_acc": 0.9856431995738636,
"val_acc": 0.992138619201726,
"train_sec": 81.1808078289032,
"peak_gb": 1.055113216
},
{
"epoch": 7,
"train_loss": 0.03749366504732858,
"val_loss": 0.02504365325874238,
"train_acc": 0.9889075816761363,
"val_acc": 0.9932106256742179,
"train_sec": 81.36290311813354,
"peak_gb": 1.055113216
},
{
"epoch": 8,
"train_loss": 0.030606712804768572,
"val_loss": 0.019467452869317548,
"train_acc": 0.9909530362215909,
"val_acc": 0.9948826860841424,
"train_sec": 81.14722490310669,
"peak_gb": 1.055113216
},
{
"epoch": 9,
"train_loss": 0.024707132888619195,
"val_loss": 0.018682031109205726,
"train_acc": 0.9926242897727273,
"val_acc": 0.9950512405609493,
"train_sec": 81.24794578552246,
"peak_gb": 1.055113216
},
{
"epoch": 10,
"train_loss": 0.021113827688280833,
"val_loss": 0.01754744060964453,
"train_acc": 0.9936989524147727,
"val_acc": 0.9955872437971952,
"train_sec": 81.09005284309387,
"peak_gb": 1.055113216
},
{
"epoch": 11,
"train_loss": 0.018296120146882127,
"val_loss": 0.01451389884019618,
"train_acc": 0.9944895241477273,
"val_acc": 0.9962007820927724,
"train_sec": 81.21309995651245,
"peak_gb": 1.055113216
},
{
"epoch": 12,
"train_loss": 0.016852841912557117,
"val_loss": 0.013475285744155881,
"train_acc": 0.9949502840909091,
"val_acc": 0.9966086839266451,
"train_sec": 67.30451726913452,
"peak_gb": 1.055113216
},
{
"epoch": 13,
"train_loss": 0.014659457782241092,
"val_loss": 0.011929425490294717,
"train_acc": 0.9956312144886363,
"val_acc": 0.9970738942826322,
"train_sec": 59.35836338996887,
"peak_gb": 1.055113216
},
{
"epoch": 14,
"train_loss": 0.012817100407767363,
"val_loss": 0.01192405523236001,
"train_acc": 0.9961412464488636,
"val_acc": 0.9970671521035599,
"train_sec": 59.80900430679321,
"peak_gb": 1.055113216
},
{
"epoch": 15,
"train_loss": 0.013028379491191696,
"val_loss": 0.01350981789242231,
"train_acc": 0.9960915305397727,
"val_acc": 0.9966895900755124,
"train_sec": 59.59719109535217,
"peak_gb": 1.055113216
},
{
"epoch": 16,
"train_loss": 0.010513839054514062,
"val_loss": 0.011061671787135487,
"train_acc": 0.9968745561079545,
"val_acc": 0.997242448759439,
"train_sec": 59.66454243659973,
"peak_gb": 1.055113216
},
{
"epoch": 17,
"train_loss": 0.009302293939346618,
"val_loss": 0.010829877125213832,
"train_acc": 0.9971852805397727,
"val_acc": 0.997411003236246,
"train_sec": 59.57374978065491,
"peak_gb": 1.055113216
},
{
"epoch": 18,
"train_loss": 0.010293126639232717,
"val_loss": 0.010242077265690284,
"train_acc": 0.9969464666193182,
"val_acc": 0.9975896709816613,
"train_sec": 59.457746267318726,
"peak_gb": 1.055113216
},
{
"epoch": 19,
"train_loss": 0.008228028477063741,
"val_loss": 0.011714679767511295,
"train_acc": 0.9975310724431818,
"val_acc": 0.997242448759439,
"train_sec": 59.34623575210571,
"peak_gb": 1.055113216
},
{
"epoch": 20,
"train_loss": 0.00952310803304003,
"val_loss": 0.010139969648128253,
"train_acc": 0.9971937144886364,
"val_acc": 0.9975458468176914,
"train_sec": 59.374980449676514,
"peak_gb": 1.055113216
}
]