diff --git a/logs/train-progress.log b/logs/train-progress.log index 01ea196..5ea84c4 100644 --- a/logs/train-progress.log +++ b/logs/train-progress.log @@ -32,3 +32,6 @@ You should probably TRAIN this model on a down-stream task to be able to use it [jev] ep2 step2600/3360 loss=0.0973 [jev] ep2 step2700/3360 loss=0.2210 [jev] ep2 step2800/3360 loss=0.1071 +[jev] ep2 step2900/3360 loss=0.1232 +[jev] ep2 step3000/3360 loss=0.0794 +[jev] ep2 step3100/3360 loss=0.1606