Bryan Marcus McCann
|
2c837eaf6e
|
ptr-gen mem efficient dist; only trainable params
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
38ce8ac161
|
mv save out of val; add arg for no tensorboard logging
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
80408b9e23
|
val loss item
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
2bcd810957
|
update devices
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
fb0dcaab35
|
mv to cpu for save; multinli.in.out regression
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
e958d2d35c
|
using torch 0.4 style device
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
ab4f39de72
|
pytorch > 0.4 for MQAN training
|
2018-10-25 16:02:48 -07:00 |
|
Bryan Marcus McCann
|
8e85a13c87
|
Contextualized Word Vectors (CoVe; McCann et al. 2017)
|
2018-08-28 03:14:41 +00:00 |
|
Bryan Marcus McCann
|
97181e99e9
|
default gpus
|
2018-06-27 21:38:53 +00:00 |
|
Bryan Marcus McCann
|
e0e04702cc
|
rm dependency on .git; multi-gpu WIP; fine-grained time
|
2018-06-27 21:18:45 +00:00 |
|
Bryan Marcus McCann
|
faa1ad382e
|
change start iteration for resume
|
2018-06-24 14:40:52 +00:00 |
|
Bryan Marcus McCann
|
8997039aec
|
Initial commit
|
2018-06-20 12:36:21 +00:00 |