balyan.sid@gmail.com
|
6a27e88023
|
use managed server
|
2026-01-14 17:09:01 +05:30 |
|
balyan.sid@gmail.com
|
32320512e8
|
update verifiers_server to use tokenizer_for_trainer
|
2026-01-13 15:00:54 +05:30 |
|
balyan.sid@gmail.com
|
a1d1e7d7fe
|
fix env_args, dataset/prompt loading
|
2026-01-12 10:39:43 +05:30 |
|
pre-commit-ci[bot]
|
7907ffd0ad
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-01-12 05:05:11 +00:00 |
|
balyan.sid@gmail.com
|
9db6c0d1ed
|
added better wandb logging
|
2026-01-12 10:34:05 +05:30 |
|
balyan.sid@gmail.com
|
dceb1d8fd8
|
parallelize verifiers_server: use generate() for SFT, parallel
ManagedServer contexts for RL
|
2026-01-12 10:34:05 +05:30 |
|
balyan.sid@gmail.com
|
24b4488c60
|
clean up eval, pin verifiers version
|
2026-01-12 10:34:05 +05:30 |
|
pre-commit-ci[bot]
|
d98bc6d9fc
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-01-12 10:34:05 +05:30 |
|
balyan.sid@gmail.com
|
cf636595d2
|
rework server and eval for rl rollout. add in asyncmanagedserver for
verifiers
|
2026-01-12 10:34:05 +05:30 |
|
pre-commit-ci[bot]
|
3449a4c23d
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-01-12 10:34:05 +05:30 |
|
balyan.sid@gmail.com
|
5b09ad86f4
|
update readme, add sft-datagen to verifiers_server
|
2026-01-09 19:20:41 +05:30 |
|
balyan.sid@gmail.com
|
636715bb08
|
add wandb to eval
|
2026-01-09 16:51:19 +05:30 |
|
balyan.sid@gmail.com
|
dda85430da
|
fix docstrings
|
2026-01-09 16:25:44 +05:30 |
|
balyan.sid@gmail.com
|
9d5cd2b593
|
fix: improve verifiers environments consistency and correctness
- verifiers_server.py: consistent dataset column selection for train/test,
remove redundant comments, preserve float precision for scores
- verifiers_eval.py: add env_config_cls, fix constructor signature to match
BaseEnv (slurm bool), make stub methods raise NotImplementedError
|
2026-01-09 16:21:12 +05:30 |
|
balyan.sid@gmail.com
|
ed826de724
|
wip: verifiers integration
|
2026-01-09 14:21:03 +05:30 |
|
PLippmann
|
5a130a3a5b
|
Quote fix
|
2026-01-06 15:14:26 +01:00 |
|
PLippmann
|
7d8123a526
|
Missing initialization
|
2026-01-06 15:14:26 +01:00 |
|
PLippmann
|
c927794248
|
Add SQL Query Generation Environment
|
2026-01-06 15:14:26 +01:00 |
|
Teknium
|
11ebecd93f
|
Merge branch 'main' into add-eval-runner
|
2026-01-05 15:46:39 -08:00 |
|
teknium
|
cb6bf37e68
|
update name of eval example
|
2026-01-05 23:46:27 +00:00 |
|
teknium
|
1fa5c3eee4
|
lint it
|
2026-01-05 23:37:37 +00:00 |
|
Teknium
|
3ef206e013
|
Merge branch 'main' into reverse-text-env
|
2026-01-05 15:33:43 -08:00 |
|
Teknium
|
46beb71e4b
|
Merge branch 'main' into gsm8k-fix
|
2026-01-03 03:58:51 -08:00 |
|
Teknium
|
ab75ce6e03
|
Merge branch 'main' into feat/tool_use_mtgrpo
|
2026-01-03 03:08:21 -08:00 |
|
teknium
|
00ab64a0f4
|
lint it
|
2026-01-02 14:17:56 +00:00 |
|
pre-commit-ci[bot]
|
f71873b0ea
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2026-01-02 14:14:11 +00:00 |
|
teknium
|
0bb38e79ef
|
big update for letter counting
|
2026-01-02 14:10:02 +00:00 |
|
pre-commit-ci[bot]
|
3cb09259df
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-31 21:05:45 +00:00 |
|
teknium
|
b9dac318ee
|
fix lintings
|
2025-12-31 21:04:40 +00:00 |
|
Teknium
|
c980157a5a
|
Merge branch 'main' into joe-public-branch
|
2025-12-31 12:41:24 -08:00 |
|
Teknium
|
1c306d3b17
|
Merge pull request #294 from NousResearch/port_many_evals
Port many benchmarks into atropos
|
2025-12-28 04:34:46 -08:00 |
|
pre-commit-ci[bot]
|
f7fe9d612b
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-28 12:32:56 +00:00 |
|
teknium
|
b912983e5e
|
Merge branch 'port_many_evals' of https://github.com/NousResearch/atropos into port_many_evals
|
2025-12-28 12:32:14 +00:00 |
|
teknium
|
c3f7c8dea6
|
final
|
2025-12-28 12:32:12 +00:00 |
|
pre-commit-ci[bot]
|
55e50f5782
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-28 12:29:37 +00:00 |
|
teknium
|
b975a315fe
|
linters
|
2025-12-28 12:28:52 +00:00 |
|
pre-commit-ci[bot]
|
1d4275d441
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-28 04:12:17 +00:00 |
|
teknium
|
ea6db6fe92
|
Merge branch 'port_many_evals' of https://github.com/NousResearch/atropos into port_many_evals
|
2025-12-28 04:11:32 +00:00 |
|
teknium
|
bcfbd647e3
|
fix some bugs
|
2025-12-28 04:09:34 +00:00 |
|
pre-commit-ci[bot]
|
52110f3fb4
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-28 01:45:06 +00:00 |
|
teknium
|
830a129655
|
add phybench eval
|
2025-12-28 01:44:20 +00:00 |
|
pre-commit-ci[bot]
|
cd733d4285
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-26 16:50:26 +00:00 |
|
interstellarninja
|
6e2bdd2a39
|
refactoring mtgrpo turn level advantage server
|
2025-12-26 22:33:35 +05:45 |
|
pre-commit-ci[bot]
|
60188d07d3
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-26 17:06:20 +05:45 |
|
interstellarninja
|
fa26c32cde
|
implmenting scenarios modes: single, multistep, multiturn
|
2025-12-26 17:04:12 +05:45 |
|
interstellarninja
|
eabb91d254
|
config for sequential tools & normalizing python literals
|
2025-12-26 17:04:12 +05:45 |
|
interstellarninja
|
a4cdf80e4a
|
BaseEnvConfig subclass for experimental vars
|
2025-12-26 17:04:12 +05:45 |
|
interstellarninja
|
2aa950a5a8
|
Add MT-GRPO turn-level advantage environment
- Implement turn-level credit assignment following MT-GRPO paper
- Custom reward computation: turn-level + outcome-level rewards
- Per-token advantage assignment compatible with existing GRPO trainer
- Configurable lambda parameter for turn/outcome advantage weighting
|
2025-12-26 17:04:12 +05:45 |
|
pre-commit-ci[bot]
|
d04f8c0ae7
|
[pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
|
2025-12-25 09:54:56 +00:00 |
|
teknium
|
8435371d80
|
linty
|
2025-12-25 09:54:11 +00:00 |
|