2025801013_anlp_assignment1 / histories /C2_BytePairTokenizer_gelu_history.json
samvaran's picture
Upload histories/C2_BytePairTokenizer_gelu_history.json with huggingface_hub
73c0c83 verified
Raw History Blame Contribute Delete
4.75 kB
[
{
"epoch": 1,
"train_loss": 1.7624475087902762,
"val_loss": 1.1151122884842957,
"train_acc": 0.4803972833806818,
"val_acc": 0.6656418554476807,
"train_sec": 58.75240993499756,
"peak_gb": 0.944777728
},
{
"epoch": 2,
"train_loss": 0.5108237018097531,
"val_loss": 0.1522014513595719,
"train_acc": 0.8382568359375,
"val_acc": 0.9471514293419633,
"train_sec": 58.77429413795471,
"peak_gb": 0.944777728
},
{
"epoch": 3,
"train_loss": 0.11274288888343356,
"val_loss": 0.051911772089932987,
"train_acc": 0.962689541903409,
"val_acc": 0.9846615426105717,
"train_sec": 57.8922758102417,
"peak_gb": 0.944777728
},
{
"epoch": 4,
"train_loss": 0.0385091987201436,
"val_loss": 0.013644262950991993,
"train_acc": 0.9884419389204545,
"val_acc": 0.9961771844660194,
"train_sec": 58.206791400909424,
"peak_gb": 0.944777728
},
{
"epoch": 5,
"train_loss": 0.020106018228583378,
"val_loss": 0.009553470273884947,
"train_acc": 0.994150390625,
"val_acc": 0.9972761596548004,
"train_sec": 58.04266905784607,
"peak_gb": 0.944777728
},
{
"epoch": 6,
"train_loss": 0.013522688390221447,
"val_loss": 0.006664294412735339,
"train_acc": 0.9960284978693181,
"val_acc": 0.9981425296655879,
"train_sec": 57.91779971122742,
"peak_gb": 0.944777728
},
{
"epoch": 7,
"train_loss": 0.010302849772005258,
"val_loss": 0.005835580717603462,
"train_acc": 0.9970348011363637,
"val_acc": 0.9984155879180151,
"train_sec": 59.05021333694458,
"peak_gb": 0.944777728
},
{
"epoch": 8,
"train_loss": 0.008762956866253675,
"val_loss": 0.005082864396474018,
"train_acc": 0.997529296875,
"val_acc": 0.9986212243797196,
"train_sec": 59.73148488998413,
"peak_gb": 0.944777728
},
{
"epoch": 9,
"train_loss": 0.007837512882595713,
"val_loss": 0.002842013011339895,
"train_acc": 0.9978173828125,
"val_acc": 0.9993055555555556,
"train_sec": 57.72091603279114,
"peak_gb": 0.944777728
},
{
"epoch": 10,
"train_loss": 0.005858481948380358,
"val_loss": 0.012970390834844598,
"train_acc": 0.998343838778409,
"val_acc": 0.9970974919093851,
"train_sec": 57.91335153579712,
"peak_gb": 0.944777728
},
{
"epoch": 11,
"train_loss": 0.0055208700603212825,
"val_loss": 0.0028324383224070295,
"train_acc": 0.9984592507102272,
"val_acc": 0.9993358953613808,
"train_sec": 58.04611110687256,
"peak_gb": 0.944777728
},
{
"epoch": 12,
"train_loss": 0.005396796792470427,
"val_loss": 0.0024209556266757888,
"train_acc": 0.9985258345170455,
"val_acc": 0.9994403991370011,
"train_sec": 58.18194007873535,
"peak_gb": 0.944777728
},
{
"epoch": 13,
"train_loss": 0.0042736622006420725,
"val_loss": 0.0029658884202866556,
"train_acc": 0.9988432173295455,
"val_acc": 0.9992482470334412,
"train_sec": 59.30978345870972,
"peak_gb": 0.944777728
},
{
"epoch": 14,
"train_loss": 0.003965111205735328,
"val_loss": 0.0027619202999097214,
"train_acc": 0.9989000355113636,
"val_acc": 0.9993864617044229,
"train_sec": 58.864203691482544,
"peak_gb": 0.944777728
},
{
"epoch": 15,
"train_loss": 0.0035830637618015646,
"val_loss": 0.001652343539179701,
"train_acc": 0.9990287642045454,
"val_acc": 0.9995685005393743,
"train_sec": 58.31713509559631,
"peak_gb": 0.944777728
},
{
"epoch": 16,
"train_loss": 0.003869527549885044,
"val_loss": 0.0025518046446875975,
"train_acc": 0.9989417613636363,
"val_acc": 0.9994977076591154,
"train_sec": 59.23481750488281,
"peak_gb": 0.944777728
},
{
"epoch": 17,
"train_loss": 0.003034974182453218,
"val_loss": 0.002608602105912641,
"train_acc": 0.99919921875,
"val_acc": 0.9993561218985976,
"train_sec": 59.45095705986023,
"peak_gb": 0.944777728
},
{
"epoch": 18,
"train_loss": 0.0029995176076508044,
"val_loss": 0.003107864049538576,
"train_acc": 0.9991916725852272,
"val_acc": 0.9993628640776699,
"train_sec": 59.402247190475464,
"peak_gb": 0.944777728
},
{
"epoch": 19,
"train_loss": 0.0031176625257119833,
"val_loss": 0.0019467750582050334,
"train_acc": 0.9991366299715909,
"val_acc": 0.999558387270766,
"train_sec": 59.30274057388306,
"peak_gb": 0.944777728
},
{
"epoch": 20,
"train_loss": 0.002729102304438129,
"val_loss": 0.001676761161761023,
"train_acc": 0.9992857776988636,
"val_acc": 0.9995887270765912,
"train_sec": 59.69143867492676,
"peak_gb": 0.944777728
}
]