Christian Risi
|
76345f8d4f
|
Fixed a visual bug
|
2025-10-12 16:42:59 +02:00 |
|
GassiGiuseppe
|
2ccec9efb8
|
typo
|
2025-10-12 16:41:06 +02:00 |
|
GassiGiuseppe
|
e2231eb3b9
|
Merge branch 'dev.train' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.train
|
2025-10-12 16:36:09 +02:00 |
|
GassiGiuseppe
|
144f8724d6
|
Update of the batcher to resolve a bug in the 4th construction
|
2025-10-12 16:35:42 +02:00 |
|
Christian Risi
|
07130ff489
|
Fixed several bugs for task 4
|
2025-10-12 16:30:30 +02:00 |
|
Christian Risi
|
e0f8a36aa5
|
Added support for fast resuming
|
2025-10-12 13:53:07 +02:00 |
|
Christian Risi
|
37a2501a79
|
Added a way to load checkpoints
|
2025-10-12 12:28:24 +02:00 |
|
Christian Risi
|
4ca1d0a189
|
Activated Dropout to avoid overfitting
|
2025-10-12 12:28:06 +02:00 |
|
Christian Risi
|
f463f699cf
|
Fixed a bug over task 4
|
2025-10-12 12:22:38 +02:00 |
|
Christian Risi
|
ab3d68bc13
|
fixed patience not quitting
|
2025-10-12 01:41:34 +02:00 |
|
Christian Risi
|
79438e3d30
|
Fixed Patience system
|
2025-10-12 01:22:06 +02:00 |
|
Christian Risi
|
f98f5a2611
|
Fixed misprint in task 3
|
2025-10-12 01:16:09 +02:00 |
|
Christian Risi
|
4281f8724b
|
Fixed Validation loss
|
2025-10-12 00:57:24 +02:00 |
|
Christian Risi
|
71d602e36e
|
Fixed a memory bug
|
2025-10-12 00:47:20 +02:00 |
|
Christian Risi
|
46ee6055ec
|
Added Colab default values
|
2025-10-12 00:15:54 +02:00 |
|
Christian Risi
|
e579e1c88b
|
fixed verbosity
|
2025-10-12 00:15:15 +02:00 |
|
Christian Risi
|
f51ada866f
|
Added verbosity level
|
2025-10-12 00:13:03 +02:00 |
|
Christian Risi
|
acd978cbc5
|
Merge branch 'dev.train' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.train
|
2025-10-12 00:05:36 +02:00 |
|
Christian Risi
|
56fbadd55e
|
Fixed training
|
2025-10-12 00:05:30 +02:00 |
|
GassiGiuseppe
|
14f1c574e7
|
typo batch size
|
2025-10-11 22:11:53 +02:00 |
|
Christian Risi
|
d8e65bfb8a
|
Fixed a bug about mismatched batch sizes
|
2025-10-11 22:09:46 +02:00 |
|
Christian Risi
|
bcc2fe7368
|
Fixed bugs and added visibility
|
2025-10-11 21:49:29 +02:00 |
|
Christian Risi
|
160b7dbfc0
|
V0.0.1 Athene
|
2025-10-11 19:35:43 +02:00 |
|
GassiGiuseppe
|
49946727d8
|
updated decoder_input to work without embedder
|
2025-10-11 16:53:36 +02:00 |
|
GassiGiuseppe
|
1649cd7768
|
added decoder_input method to build the batch tensor to give in input to the deocder
|
2025-10-11 16:18:43 +02:00 |
|
GassiGiuseppe
|
443f54fffd
|
WIP decoder with prefix mask
|
2025-10-11 15:31:43 +02:00 |
|
GassiGiuseppe
|
ff721107b9
|
typo
|
2025-10-11 15:26:58 +02:00 |
|
GassiGiuseppe
|
f1886e5be1
|
added builder for prefix mask
|
2025-10-11 15:19:09 +02:00 |
|
GassiGiuseppe
|
5e3878ea17
|
Merge branch 'dev' into dev.train
|
2025-10-11 11:51:58 +02:00 |
|
GassiGiuseppe
|
79d3fb9ff8
|
Merge branch 'dev' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev
|
2025-10-11 11:51:19 +02:00 |
|
GassiGiuseppe
|
586f021276
|
Merge branch 'dev.train' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.train
|
2025-10-11 11:28:35 +02:00 |
|
GassiGiuseppe
|
82462078f8
|
WIP for the new prefix mask
|
2025-10-11 11:28:15 +02:00 |
|
Christian Risi
|
625f79f7c3
|
Fixed imports
|
2025-10-11 11:18:44 +02:00 |
|
GassiGiuseppe
|
3446870291
|
typo
|
2025-10-10 22:27:01 +02:00 |
|
GassiGiuseppe
|
e76dbeb9a7
|
typo
|
2025-10-10 22:26:06 +02:00 |
|
GassiGiuseppe
|
96610612fe
|
Batcher added
|
2025-10-10 20:10:08 +02:00 |
|
Christian Risi
|
92ae40013d
|
Added a way to detach models and create them standalone
|
2025-10-10 18:43:20 +02:00 |
|
Christian Risi
|
15f203cad5
|
Added boe 16k tokens vocabulary
|
2025-10-10 18:43:02 +02:00 |
|
Christian Risi
|
31c8541dfb
|
Co-authored-by: GassiGiuseppe <GassiGiuseppe@users.noreply.github.com>
|
2025-10-10 16:28:09 +02:00 |
|
Christian Risi
|
bed9718f27
|
Added BPE small vocabulary
|
2025-10-10 11:40:39 +02:00 |
|
GassiGiuseppe
|
93865bee8a
|
typo
|
2025-10-09 22:26:17 +02:00 |
|
Christian Risi
|
1c0ddb8753
|
Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder
|
2025-10-09 22:23:36 +02:00 |
|
Christian Risi
|
51399f9dc9
|
commit of toy dataset with whole batch
|
2025-10-09 22:22:42 +02:00 |
|
GassiGiuseppe
|
d1ba4ae026
|
last update for collab
( we are gonna run it on a 100 yey)
|
2025-10-09 21:57:05 +02:00 |
|
Christian Risi
|
db0090981c
|
Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder
|
2025-10-09 21:53:45 +02:00 |
|
Christian Risi
|
e1c5649d67
|
updated to overfit over toy dataset
|
2025-10-09 21:53:42 +02:00 |
|
GassiGiuseppe
|
0bca241662
|
update environment yaml
|
2025-10-09 20:53:45 +02:00 |
|
GassiGiuseppe
|
005d7af6a0
|
lil update of requirements
|
2025-10-09 20:30:06 +02:00 |
|
GassiGiuseppe
|
9068db550e
|
Merge branch 'dev.embedder' of https://repositories.communitynotfound.work/PoliBa-DeepLearning/NanoSocrates into dev.embedder
|
2025-10-09 19:44:46 +02:00 |
|
GassiGiuseppe
|
d8f81e1a47
|
that god can have mercy upon us
|
2025-10-09 19:43:50 +02:00 |
|