31 lines
1.4 KiB
Plaintext
31 lines
1.4 KiB
Plaintext
[jev] device=cuda base=/tmp/base
|
|
Some weights of XLMRobertaForSequenceClassification were not initialized from the model checkpoint at /tmp/base and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']
|
|
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
|
[jev] train=35848 calib=5291
|
|
[jev] ep0 step100/3360 loss=0.4371
|
|
[jev] ep0 step200/3360 loss=0.2559
|
|
[jev] ep0 step300/3360 loss=0.2655
|
|
[jev] ep0 step400/3360 loss=0.2031
|
|
[jev] ep0 step500/3360 loss=0.5181
|
|
[jev] ep0 step600/3360 loss=0.3475
|
|
[jev] ep0 step700/3360 loss=0.2018
|
|
[jev] ep0 step800/3360 loss=0.2473
|
|
[jev] ep0 step900/3360 loss=0.2586
|
|
[jev] ep0 step1000/3360 loss=0.2817
|
|
[jev] ep0 step1100/3360 loss=0.2758
|
|
[jev] epoch 0 calibration: {'auc': 0.9869, 'ece': 0.0203, 'n': 5291}
|
|
[jev] ep1 step1200/3360 loss=0.1937
|
|
[jev] ep1 step1300/3360 loss=0.2044
|
|
[jev] ep1 step1400/3360 loss=0.4326
|
|
[jev] ep1 step1500/3360 loss=0.4071
|
|
[jev] ep1 step1600/3360 loss=0.1805
|
|
[jev] ep1 step1700/3360 loss=0.3103
|
|
[jev] ep1 step1800/3360 loss=0.2555
|
|
[jev] ep1 step1900/3360 loss=0.1615
|
|
[jev] ep1 step2000/3360 loss=0.2714
|
|
[jev] ep1 step2100/3360 loss=0.3809
|
|
[jev] ep1 step2200/3360 loss=0.1102
|
|
[jev] epoch 1 calibration: {'auc': 0.9912, 'ece': 0.0176, 'n': 5291}
|
|
[jev] ep2 step2300/3360 loss=0.1976
|
|
[jev] ep2 step2400/3360 loss=0.3304
|