Jake Poznanski
|
d9b6978499
|
Some scripts
|
2025-08-25 18:44:18 +00:00 |
|
Jake Poznanski
|
2415cdcfda
|
Adding support for a blank page output check
|
2025-08-25 17:20:47 +00:00 |
|
Jake Poznanski
|
33ecc2316c
|
Startng miner for blank pages, we want to make sure we don't hallucinate
|
2025-08-25 16:54:23 +00:00 |
|
Jake Poznanski
|
55b7101d7e
|
Add some new rotation tests to a branch of the bench
|
2025-08-25 16:25:00 +00:00 |
|
Jake Poznanski
|
59321af018
|
Merge pull request #319 from haydn-jones/main
External vLLM instance
|
2025-08-25 08:43:25 -07:00 |
|
Haydn Jones
|
2c63836648
|
Black and mock
|
2025-08-23 20:07:05 -04:00 |
|
Jake Poznanski
|
5c6225b227
|
Fix for some math equations stuff
|
2025-08-22 20:52:41 +00:00 |
|
Jake Poznanski
|
d36357f3db
|
Some fixes to validating math which was not working otherwise
|
2025-08-22 20:40:14 +00:00 |
|
Jake Poznanski
|
f3ea1527ef
|
Local path supported
|
2025-08-22 20:11:35 +00:00 |
|
Jake Poznanski
|
5cbe331259
|
Async mode
|
2025-08-22 19:51:51 +00:00 |
|
Jake Poznanski
|
0df56e958e
|
Even more test cleanup
|
2025-08-22 18:56:56 +00:00 |
|
Jake Poznanski
|
9831e65161
|
Fixing some logs, verifying 100% self test accuracy
|
2025-08-22 18:39:39 +00:00 |
|
Jake Poznanski
|
c1c83fd86c
|
Better quality synth data from both sides
|
2025-08-22 18:37:59 +00:00 |
|
Jake Poznanski
|
d9789947d5
|
Refactoring of loading tests
|
2025-08-22 18:31:37 +00:00 |
|
Jake Poznanski
|
afac12b839
|
Cleaning up test cases
|
2025-08-22 18:24:39 +00:00 |
|
Jake Poznanski
|
7ea692198b
|
Spaces for newlines in markdown is better
|
2025-08-22 17:27:47 +00:00 |
|
Jake Poznanski
|
dcc932dc2c
|
Markdown cleanup
|
2025-08-22 17:21:13 +00:00 |
|
Jake Poznanski
|
aed755de38
|
Image alt tags
|
2025-08-22 16:52:52 +00:00 |
|
Jake Poznanski
|
d2bec31595
|
Markdown front matter corrector
|
2025-08-22 16:43:36 +00:00 |
|
Jake Poznanski
|
b1101c1a2f
|
Adding front matter to markdown, still debugging a bit
|
2025-08-22 16:36:03 +00:00 |
|
Jake Poznanski
|
dc3aba9891
|
Sorting keys in dataset to repro nicely
|
2025-08-21 22:18:48 +00:00 |
|
Jake Poznanski
|
c0aee06c8f
|
grpo startup script works
|
2025-08-21 22:15:21 +00:00 |
|
Haydn Jones
|
261c722f56
|
Update README + arg name
|
2025-08-21 17:49:07 -04:00 |
|
Jake Poznanski
|
6e3e2d8abc
|
Type checks better
|
2025-08-21 18:51:05 +00:00 |
|
Jake Poznanski
|
33d889c748
|
Fixing for conv format
|
2025-08-21 18:47:53 +00:00 |
|
Jake Poznanski
|
0f8d515d8c
|
Logging
|
2025-08-21 18:42:04 +00:00 |
|
Jake Poznanski
|
0fd7d07e73
|
GRPO reward fixups
|
2025-08-21 18:33:11 +00:00 |
|
Jake Poznanski
|
55b705ce50
|
Log completions
|
2025-08-21 18:20:26 +00:00 |
|
Jake Poznanski
|
1dd6ff9b03
|
Olmocr bench grpo stuff
|
2025-08-21 18:17:07 +00:00 |
|
Jake Poznanski
|
6184c94c3c
|
Vllm enable
|
2025-08-21 17:33:56 +00:00 |
|
Jake Poznanski
|
6fb136deee
|
Random func
|
2025-08-21 17:23:26 +00:00 |
|
Jake Poznanski
|
5556e204cf
|
Testing
|
2025-08-21 17:17:43 +00:00 |
|
Jake Poznanski
|
892429965a
|
Hmm
|
2025-08-21 17:14:14 +00:00 |
|
Jake Poznanski
|
de719edf49
|
Logs
|
2025-08-21 17:11:33 +00:00 |
|
Jake Poznanski
|
6fe630516a
|
Score longer
|
2025-08-21 17:09:09 +00:00 |
|
Jake Poznanski
|
7f2dd85e5b
|
More configs
|
2025-08-21 17:06:18 +00:00 |
|
Jake Poznanski
|
dc4c0864ac
|
Dont default to tensorboard
|
2025-08-21 17:03:01 +00:00 |
|
Jake Poznanski
|
a443b89854
|
Cleanup
|
2025-08-21 17:01:40 +00:00 |
|
Jake Poznanski
|
d08068218c
|
Setting some defaults
|
2025-08-21 16:59:16 +00:00 |
|
Jake Poznanski
|
f865e49624
|
Options
|
2025-08-21 16:55:24 +00:00 |
|
Jake Poznanski
|
3c8410f22c
|
fix
|
2025-08-21 16:51:51 +00:00 |
|
Jake Poznanski
|
1dbb4332c0
|
FIxing up
|
2025-08-21 16:50:56 +00:00 |
|
Haydn Jones
|
b34c3611e1
|
oopsy woopsy
|
2025-08-20 19:22:48 -04:00 |
|
Haydn Jones
|
b8a2b92174
|
External vLLM
|
2025-08-20 19:21:38 -04:00 |
|
Jake Poznanski
|
7c446e1679
|
Trying to fix script
|
2025-08-20 22:44:10 +00:00 |
|
Jake Poznanski
|
a2ee4d46c0
|
gpro trainer test 1
|
2025-08-20 22:35:19 +00:00 |
|
Jake Poznanski
|
77164e909f
|
Decent grpo script
|
2025-08-20 22:25:26 +00:00 |
|
Jake Poznanski
|
cc918ca03e
|
Setting up GRPO trainer
|
2025-08-20 22:18:38 +00:00 |
|
Jake Poznanski
|
d046ba554a
|
Mining math tests too
|
2025-08-20 21:05:56 +00:00 |
|
Jake Poznanski
|
c32dced59c
|
More fixes to data gen script
|
2025-08-20 20:24:38 +00:00 |
|