josecannete's picture
adding model distilled on mlqa
7f7ea9e
[
{
"kd_train_loss": 1.0966327536640577,
"ce_train_loss": 2.425135554602736,
"epoch": 1
},
{
"kd_train_loss": 0.6028298882045011,
"ce_train_loss": 1.9218363381268686,
"epoch": 2
},
{
"kd_train_loss": 0.39284729567332805,
"ce_train_loss": 1.6968178288281313,
"epoch": 3
},
{
"kd_train_loss": 0.29444230084124134,
"ce_train_loss": 1.5832153033327174,
"epoch": 4
},
{
"kd_train_loss": 0.24880144547881672,
"ce_train_loss": 1.5273258323557892,
"epoch": 5
},
{
"kd_train_loss": 0.21199501323682524,
"ce_train_loss": 1.4846864300629317,
"epoch": 6
},
{
"kd_train_loss": 0.1898589454692939,
"ce_train_loss": 1.4565552937008484,
"epoch": 7
},
{
"kd_train_loss": 0.1697300156698241,
"ce_train_loss": 1.4315641443515614,
"epoch": 8
},
{
"kd_train_loss": 0.15527293716373963,
"ce_train_loss": 1.4157921907265052,
"epoch": 9
},
{
"kd_train_loss": 0.1427187800618001,
"ce_train_loss": 1.3990895473469072,
"epoch": 10
},
{
"kd_train_loss": 0.1320027018899051,
"ce_train_loss": 1.3857538908720017,
"epoch": 11
},
{
"kd_train_loss": 0.12207950383540947,
"ce_train_loss": 1.3733008942873621,
"epoch": 12
},
{
"kd_train_loss": 0.11346291012873194,
"ce_train_loss": 1.3636816531245473,
"epoch": 13
},
{
"kd_train_loss": 0.1070231559143545,
"ce_train_loss": 1.354241604501741,
"epoch": 14
},
{
"kd_train_loss": 0.10077550309486905,
"ce_train_loss": 1.3487564541907804,
"epoch": 15
},
{
"kd_train_loss": 0.09470034228314665,
"ce_train_loss": 1.3389324404807583,
"epoch": 16
},
{
"kd_train_loss": 0.08925495943595559,
"ce_train_loss": 1.3356766930274797,
"epoch": 17
},
{
"kd_train_loss": 0.08508727698937261,
"ce_train_loss": 1.3269488129583251,
"epoch": 18
},
{
"kd_train_loss": 0.08035293568586513,
"ce_train_loss": 1.323597615748121,
"epoch": 19
},
{
"kd_train_loss": 0.07568324804596502,
"ce_train_loss": 1.3158395546570159,
"epoch": 20
},
{
"kd_train_loss": 0.07179850485633339,
"ce_train_loss": 1.312317049288378,
"epoch": 21
},
{
"kd_train_loss": 0.06885896269522505,
"ce_train_loss": 1.3089465946598127,
"epoch": 22
},
{
"kd_train_loss": 0.06520364823992605,
"ce_train_loss": 1.3044240581129494,
"epoch": 23
},
{
"kd_train_loss": 0.06174703795157852,
"ce_train_loss": 1.29910074816345,
"epoch": 24
},
{
"kd_train_loss": 0.05913372104352097,
"ce_train_loss": 1.2973454949800034,
"epoch": 25
},
{
"kd_train_loss": 0.05681754786296082,
"ce_train_loss": 1.2934590654647373,
"epoch": 26
},
{
"kd_train_loss": 0.05374109216731543,
"ce_train_loss": 1.2900665794025388,
"epoch": 27
},
{
"kd_train_loss": 0.05149607109577625,
"ce_train_loss": 1.2879741225791024,
"epoch": 28
},
{
"kd_train_loss": 0.04957827115050185,
"ce_train_loss": 1.2851160877164576,
"epoch": 29
},
{
"kd_train_loss": 0.04695611311663777,
"ce_train_loss": 1.2812810770949425,
"epoch": 30
},
{
"kd_train_loss": 0.04501556584912899,
"ce_train_loss": 1.2805869066401532,
"epoch": 31
},
{
"kd_train_loss": 0.04319381927762754,
"ce_train_loss": 1.277856232774885,
"epoch": 32
},
{
"kd_train_loss": 0.04138699650953272,
"ce_train_loss": 1.2751395187531298,
"epoch": 33
},
{
"kd_train_loss": 0.039558702625232596,
"ce_train_loss": 1.273521645282909,
"epoch": 34
}
]