MixtureofRecursionwithRouter / ultra_fast_results .json
Girinath11's picture
Rename ultra_fast_results (1).json to ultra_fast_results .json
9b51037 verified
[
{
"epoch": 1,
"train_loss": 5.904081931531553,
"train_ppl": 366.5305711150301,
"epoch_time_min": 3.736004670461019
},
{
"epoch": 2,
"train_loss": 4.782037754045692,
"train_ppl": 119.34730287095881,
"epoch_time_min": 3.8931448221206666
},
{
"epoch": 3,
"train_loss": 4.346468383242228,
"train_ppl": 77.20532128691357,
"epoch_time_min": 3.921374297142029
},
{
"epoch": 4,
"train_loss": 4.018676786895952,
"train_ppl": 55.627450135490534,
"epoch_time_min": 3.985279401143392
},
{
"epoch": 5,
"train_loss": 3.7450198261266245,
"train_ppl": 42.30984605088766,
"epoch_time_min": 3.9397004723548887
},
{
"epoch": 6,
"train_loss": 3.489572767386512,
"train_ppl": 32.77194347185351,
"epoch_time_min": 3.9274261832237243
},
{
"epoch": 7,
"train_loss": 3.2404102570923503,
"train_ppl": 25.54419928688797,
"epoch_time_min": 3.9699341615041095
},
{
"epoch": 8,
"train_loss": 3.02185961955338,
"train_ppl": 20.529433144193597,
"epoch_time_min": 3.9765639464060465
},
{
"epoch": 9,
"train_loss": 2.8062185044949173,
"train_ppl": 16.54722649664141,
"epoch_time_min": 4.011128667990366
},
{
"epoch": 10,
"train_loss": 2.614807206790748,
"train_ppl": 13.664581685370322,
"epoch_time_min": 4.025792515277862
},
{
"epoch": 11,
"train_loss": 2.449191606102279,
"train_ppl": 11.578982555927084,
"epoch_time_min": 4.044950878620147
},
{
"epoch": 12,
"train_loss": 2.286392891267347,
"train_ppl": 9.83938187261486,
"epoch_time_min": 4.032349860668182
},
{
"epoch": 13,
"train_loss": 2.1751735476606227,
"train_ppl": 8.803712853387184,
"epoch_time_min": 4.048110489050547
},
{
"epoch": 14,
"train_loss": 2.1039459013593844,
"train_ppl": 8.198456471422684,
"epoch_time_min": 4.049738196531932
},
{
"epoch": 15,
"train_loss": 2.0712672462141324,
"train_ppl": 7.934872185920158,
"epoch_time_min": 4.0435048540433245
}
]