1749 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Jake Poznanski	f3cdc78b4f	Pushing new version	2025-08-31 03:12:30 +00:00
Jake Poznanski	72fcfafde7	Fixed up national archives script	2025-08-29 16:36:18 +00:00
Jake Poznanski	7e09a02f7c	Better NA extractor	2025-08-28 20:48:51 +00:00
Jake Poznanski	22626a512c	Describing national archives project	2025-08-28 18:44:24 +00:00
Jake Poznanski	f426826850	Clean downloads	2025-08-28 18:03:52 +00:00
Jake Poznanski	3d3d184f25	Fixes	2025-08-28 17:56:27 +00:00
Jake Poznanski	ed3820c0c7	LOC downloader	2025-08-28 17:38:20 +00:00
Jake Poznanski	6123d4452b	Reorganizing files	2025-08-28 17:04:26 +00:00
Jake Poznanski	0710debf75	Cleaner front matter reward	2025-08-27 19:49:42 +00:00
Jake Poznanski	09036b07d9	Verifying bench loading	2025-08-27 19:00:29 +00:00
Jake Poznanski	edd098093b	Reverting version changes that broke, vllm 0.10.1 is not good	2025-08-27 18:55:26 +00:00
Jake Poznanski	14f19e5d58	Some cost tracking	2025-08-27 18:53:42 +00:00
Jake Poznanski	d70208d98a	Moving test code around, adding format reward since some runs stop outputting the front matter thing in grpo training	2025-08-27 18:22:05 +00:00
Jake Poznanski	8383865392	Fixing up subscripts and superscripts in synth data	2025-08-27 18:15:36 +00:00
Jake Poznanski	27792664bf	Transformers version bump needed also	2025-08-27 16:35:51 +00:00
Jake Poznanski	03c7479a17	VLLM version bump	2025-08-27 16:33:37 +00:00
Jake Poznanski	cf479d1d29	Fixing reward weights stuff	2025-08-26 22:04:45 +00:00
Jake Poznanski	c86b413d3e	Adding additional rewards and weights	2025-08-26 21:49:35 +00:00
Jake Poznanski	9c520498dd	Adding some losses	2025-08-26 21:18:24 +00:00
Jake Poznanski	3be381b375	Adding some params	2025-08-26 20:46:06 +00:00
Jake Poznanski	4b3660debd	Quieting some messages	2025-08-26 20:15:39 +00:00
Jake Poznanski	8327da2415	Fix	2025-08-26 20:06:52 +00:00
Jake Poznanski	98f4d62d1e	Fixing data check	2025-08-26 19:51:54 +00:00
Jake Poznanski	3433c8f5f2	Adding more cmd line args	2025-08-26 18:28:41 +00:00
Jake Poznanski	9671f6847c	Parallel rewards	2025-08-26 18:16:21 +00:00
Jake Poznanski	3eec58012c	Docker ignore	2025-08-26 17:52:50 +00:00
Jake Poznanski	2588f911dc	Docker ignore	2025-08-26 17:52:30 +00:00
Jake Poznanski	82fd50263f	Launcher for grpo training	2025-08-26 16:28:38 +00:00
Jake Poznanski	6be12c2e06	Baseline tests for blanks	2025-08-25 22:01:24 +00:00
Jake Poznanski	ad33672781	fix	2025-08-25 21:04:53 +00:00
Jake Poznanski	ba226cc1d5	Saving url metadata	2025-08-25 20:47:54 +00:00
Jake Poznanski	90a7443b2b	Working to cleanup miner script	2025-08-25 20:41:04 +00:00
Jake Poznanski	ed6f483074	Fixing run_benchmark	2025-08-25 20:28:40 +00:00
Jake Poznanski	d84eb95ba2	Saving some extra data mixes	2025-08-25 20:26:29 +00:00
Jake Poznanski	c7aa217281	Scripts to run benchmarks better	2025-08-25 20:12:10 +00:00
Jake Poznanski	b16e4051f6	Saving bench results to s3	2025-08-25 19:53:55 +00:00
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