Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +10 -0
- ckpt/1shot_gae/global_step_400/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_gae/global_step_400/actor/huggingface/tokenizer.json +3 -0
- ckpt/1shot_gae/global_step_400/critic/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_gae/global_step_400/critic/huggingface/tokenizer.json +3 -0
- ckpt/1shot_gae/global_step_400/data.pt +3 -0
- ckpt/1shot_graphrpo/global_step_700/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_graphrpo/global_step_700/actor/huggingface/tokenizer.json +3 -0
- ckpt/1shot_graphrpo/global_step_700/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_graphrpo/global_step_700/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_graphrpo/global_step_700/data.pt +3 -0
- ckpt/1shot_grpo/global_step_1200/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_grpo/global_step_1200/actor/huggingface/tokenizer.json +3 -0
- ckpt/1shot_grpo/global_step_1200/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_grpo/global_step_1200/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_grpo/global_step_1200/data.pt +3 -0
- ckpt/1shot_grpo_lan/global_step_800/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_grpo_lan/global_step_800/actor/huggingface/tokenizer.json +3 -0
- ckpt/1shot_grpo_lan/global_step_800/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_grpo_lan/global_step_800/data.pt +3 -0
- ckpt/1shot_rankrpo/global_step_1000/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_rankrpo/global_step_1000/actor/huggingface/tokenizer.json +3 -0
- ckpt/1shot_rankrpo/global_step_1000/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_rankrpo/global_step_1000/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/1shot_rankrpo/global_step_1000/data.pt +3 -0
- ckpt/fullmath_graphrpo/global_step_200/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_graphrpo/global_step_200/actor/huggingface/tokenizer.json +3 -0
- ckpt/fullmath_graphrpo/global_step_200/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_graphrpo/global_step_200/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_graphrpo/global_step_200/data.pt +3 -0
- ckpt/fullmath_grpo_gspo_base/global_step_200/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_grpo_gspo_base/global_step_200/actor/huggingface/tokenizer.json +3 -0
- ckpt/fullmath_grpo_gspo_base/global_step_200/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_grpo_gspo_base/global_step_200/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_grpo_gspo_base/global_step_200/data.pt +3 -0
- ckpt/fullmath_gspo_exact/global_step_200/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_gspo_exact/global_step_200/actor/huggingface/tokenizer.json +3 -0
- ckpt/fullmath_gspo_exact/global_step_200/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_gspo_exact/global_step_200/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/fullmath_gspo_exact/global_step_200/data.pt +3 -0
- ckpt/pilot_passk_graphrpo/global_step_100/actor/extra_state_world_size_1_rank_0.pt +3 -0
- ckpt/pilot_passk_graphrpo/global_step_100/actor/huggingface/tokenizer.json +3 -0
- ckpt/pilot_passk_graphrpo/global_step_100/actor/model_world_size_1_rank_0.pt +3 -0
- ckpt/pilot_passk_graphrpo/global_step_100/actor/optim_world_size_1_rank_0.pt +3 -0
- ckpt/pilot_passk_graphrpo/global_step_100/data.pt +3 -0
- data/1shot_dsr_sub/dsr_sub_released.parquet +3 -0
- data/1shot_dsr_sub/train.parquet +3 -0
- data/_simplerl_raw/simplelr_qwen_level3to5/test.parquet +3 -0
- data/_simplerl_raw/simplelr_qwen_level3to5/train.parquet +3 -0
- data/aime24/test.parquet +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
ckpt/pilot_passk_graphrpo/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
ckpt/fullmath_graphrpo/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
ckpt/fullmath_grpo_gspo_base/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
ckpt/fullmath_gspo_exact/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
ckpt/1shot_grpo/global_step_1200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
ckpt/1shot_rankrpo/global_step_1000/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
ckpt/1shot_graphrpo/global_step_700/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
ckpt/1shot_grpo_lan/global_step_800/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
ckpt/1shot_gae/global_step_400/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
ckpt/1shot_gae/global_step_400/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
ckpt/1shot_gae/global_step_400/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99e6b6d8a105a0661ac2940bd6ececca0094f68851cb07b86d40a2f30b3c5b2f
|
| 3 |
+
size 15141
|
ckpt/1shot_gae/global_step_400/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_gae/global_step_400/critic/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:312613644d1d31420a70808a2fe05ec6d94f7b7bd4fea91f3bebb0dbb07346e2
|
| 3 |
+
size 15141
|
ckpt/1shot_gae/global_step_400/critic/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_gae/global_step_400/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35258f6cf21d43269fe07648a6b49fe95ad626b8f3fcba3cf28659e33266dbae
|
| 3 |
+
size 7316
|
ckpt/1shot_graphrpo/global_step_700/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b22bb5b151a2bcdfd99dddd651924126ded3f766fbc831ef0c29dc19e6784bb
|
| 3 |
+
size 15141
|
ckpt/1shot_graphrpo/global_step_700/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_graphrpo/global_step_700/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c31b7a2209e3ff58a75c6de12b85ed8540d501b8a9e4cedfdc579296bfb10acf
|
| 3 |
+
size 7108515723
|
ckpt/1shot_graphrpo/global_step_700/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62b9305d5535bc0e796121fbc5119165fc08619659ec272064ec4de8583e6217
|
| 3 |
+
size 12349741064
|
ckpt/1shot_graphrpo/global_step_700/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d87652a46cb3242cda5951027ba619f8adf598a8a180a925d002fb93c9de8bd8
|
| 3 |
+
size 7316
|
ckpt/1shot_grpo/global_step_1200/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d64e0327d0d5c3bada0ac1512f7039a3c4baafcb8e49fad5ab374cbc193c1bcf
|
| 3 |
+
size 15141
|
ckpt/1shot_grpo/global_step_1200/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_grpo/global_step_1200/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fe4f871640a36be242d2f75268a7a7af5293fa234586c087e16a83c1795f0a7
|
| 3 |
+
size 7108515723
|
ckpt/1shot_grpo/global_step_1200/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5d24e29a927286e083e7bd8ba7d4007dda7788fcdd67d1edb046da82fb775b1
|
| 3 |
+
size 12349741896
|
ckpt/1shot_grpo/global_step_1200/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf288edf3a48ea838dafe8b1d732f5d6c383d223218068a31a085722c69aa13a
|
| 3 |
+
size 7316
|
ckpt/1shot_grpo_lan/global_step_800/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ca3a48be1e0f5e061c12b9c31189d0a898b9bfdfab125f8f90316cce4640a2c
|
| 3 |
+
size 15141
|
ckpt/1shot_grpo_lan/global_step_800/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_grpo_lan/global_step_800/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c77558fd10b9612de3f490ef285760f70c8dd7aa5ffb8a3a1c60049254ab2f81
|
| 3 |
+
size 7108515723
|
ckpt/1shot_grpo_lan/global_step_800/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a69f2d301b4809cf8f7395727c8c61b301f4de1a383c5eeb38183a7e0243fc31
|
| 3 |
+
size 7316
|
ckpt/1shot_rankrpo/global_step_1000/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd7be71dde8f5a8e5ea15431087dfc7c998543868a0cf1b6a30dd33ba25431d
|
| 3 |
+
size 15077
|
ckpt/1shot_rankrpo/global_step_1000/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/1shot_rankrpo/global_step_1000/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:915dda63c419efbdef3f78cdd9b26350ed667b316487b46f57d9a53899bdc087
|
| 3 |
+
size 7108515723
|
ckpt/1shot_rankrpo/global_step_1000/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dfb8b77afbcb40bd9247082773b026298304472f78ee39ecd45b1cc11b62211
|
| 3 |
+
size 12349741064
|
ckpt/1shot_rankrpo/global_step_1000/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4edcf8aea2b93d918641ecb0e44623880740a763b019ad2a9cc8dd4c13aff82
|
| 3 |
+
size 7316
|
ckpt/fullmath_graphrpo/global_step_200/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94a41ec48252e3c6f881733255af9e3eac38c38079c8c83a2a7ead72c7c9776f
|
| 3 |
+
size 15077
|
ckpt/fullmath_graphrpo/global_step_200/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/fullmath_graphrpo/global_step_200/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f995a7e8232637e6ceecfaa88d5e5b6e7782c299feb6ef841ff62c101ef99b5f
|
| 3 |
+
size 7108515723
|
ckpt/fullmath_graphrpo/global_step_200/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ba83324ce771c476f58833874570a353cf4b201d12db39c981270d020ac332c
|
| 3 |
+
size 12349741896
|
ckpt/fullmath_graphrpo/global_step_200/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bece1a482694a18f0531c112c88a496a3261e8348990d210a03ef499382e8d4
|
| 3 |
+
size 7316
|
ckpt/fullmath_grpo_gspo_base/global_step_200/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3acbabb1f75a384e984a046b64b3610f5c57335da981b6da1c003c74c543197
|
| 3 |
+
size 15141
|
ckpt/fullmath_grpo_gspo_base/global_step_200/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/fullmath_grpo_gspo_base/global_step_200/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc564c0fbb4941c7bbdbfbc57d318d15f63cb466caf61d84c98b81f037504b5e
|
| 3 |
+
size 7108515723
|
ckpt/fullmath_grpo_gspo_base/global_step_200/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f2afc6ab5dbf7838ce83b7bd44dd9400f0e8b54182a40de2aa9a4287156bdd7
|
| 3 |
+
size 12349741896
|
ckpt/fullmath_grpo_gspo_base/global_step_200/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1185927ec030a199bdaaa744f8532b8aaa5562baa5472928d2243d457d720cdc
|
| 3 |
+
size 7316
|
ckpt/fullmath_gspo_exact/global_step_200/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6df68c47a972a8a23329fc4002fdc36fbd06a082a012026df4f2fff0ace6fbd7
|
| 3 |
+
size 15141
|
ckpt/fullmath_gspo_exact/global_step_200/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/fullmath_gspo_exact/global_step_200/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2df8b89f88d1c8707a123fdbb37e6d0c5be2398a3bffe10a560dbdd5904d66b
|
| 3 |
+
size 7108515723
|
ckpt/fullmath_gspo_exact/global_step_200/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e52f0aa3a6e18fb95fe8b0ce7221bd2952f3a7c4c54b58e26ca0617e3087b77b
|
| 3 |
+
size 12349741896
|
ckpt/fullmath_gspo_exact/global_step_200/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:271c0317bd98e580cd41f709879099ae017a6f01428b53223564201da1d28e03
|
| 3 |
+
size 7316
|
ckpt/pilot_passk_graphrpo/global_step_100/actor/extra_state_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac897c94971d573e667326a5fb01199df71271b9b478ab8ff55632bd97f1144
|
| 3 |
+
size 15141
|
ckpt/pilot_passk_graphrpo/global_step_100/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
ckpt/pilot_passk_graphrpo/global_step_100/actor/model_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e0b114f81a4f38b899bab03812998e0d5e7441f84d3ba2ee693c52e7a5afa3
|
| 3 |
+
size 7108515723
|
ckpt/pilot_passk_graphrpo/global_step_100/actor/optim_world_size_1_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73a7a1ff30413741f2dca197555493fab5094c336b956e5e8b4a16bf58e80168
|
| 3 |
+
size 12349741896
|
ckpt/pilot_passk_graphrpo/global_step_100/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01a8910a27ff2706137f7cd244c2f678834fbe5d5636fef5b0a434676227690f
|
| 3 |
+
size 7316
|
data/1shot_dsr_sub/dsr_sub_released.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bce5945e5666d5b82f1554b0a18203a88a0209f82fa724e5bfdfc17cc9a1aea6
|
| 3 |
+
size 208112
|
data/1shot_dsr_sub/train.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b969951dcf5c10405e83516370498d96716ecd67dc971fb319587824ca1398c
|
| 3 |
+
size 206141
|
data/_simplerl_raw/simplelr_qwen_level3to5/test.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:127daa21c7ecf85aa9a04c9acf9e1420246d8b4f458885a00805d50994304b3a
|
| 3 |
+
size 285226
|
data/_simplerl_raw/simplelr_qwen_level3to5/train.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6ce0b30da9d3be80b0bd8b2925c8707aec6f627af3628c5439241a3b22e7c13
|
| 3 |
+
size 3805836
|
data/aime24/test.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91a4e4bd347868bb70c8052b7485cb8fff6db5a7a512780bb8b46e047fb43c8
|
| 3 |
+
size 12771
|