Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-07-14T12-41-17.800843/details_lighteval|gpqa:diamond|0_2025-07-14T12-41-17.800843.parquet +3 -0
- eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-07-17T15-29-55.092392/details_extended|ifeval|0_2025-07-17T15-29-55.092392.parquet +3 -0
- eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-07-14T12-45-55.307385/details_lighteval|gpqa:diamond|0_2025-07-14T12-45-55.307385.parquet +3 -0
- eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-07-17T15-27-34.486497/details_extended|ifeval|0_2025-07-17T15-27-34.486497.parquet +3 -0
- eval_results_ood/global_step_100/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-07-14T12-58-50.192486/details_lighteval|gpqa:diamond|0_2025-07-14T12-58-50.192486.parquet +3 -0
- eval_results_ood/global_step_100/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-07-17T15-57-23.838956/details_extended|ifeval|0_2025-07-17T15-57-23.838956.parquet +3 -0
- eval_results_ood/global_step_110/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_110_actor_huggingface/2025-07-14T13-00-52.252218/details_lighteval|gpqa:diamond|0_2025-07-14T13-00-52.252218.parquet +3 -0
- eval_results_ood/global_step_110/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_110_actor_huggingface/2025-07-17T15-52-51.610154/details_extended|ifeval|0_2025-07-17T15-52-51.610154.parquet +3 -0
- eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-07-14T12-46-08.302506/details_lighteval|gpqa:diamond|0_2025-07-14T12-46-08.302506.parquet +3 -0
- eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-07-17T15-33-20.611749/details_extended|ifeval|0_2025-07-17T15-33-20.611749.parquet +3 -0
- eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-07-14T12-41-43.868511/details_lighteval|gpqa:diamond|0_2025-07-14T12-41-43.868511.parquet +3 -0
- eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-07-17T15-22-22.924052/details_extended|ifeval|0_2025-07-17T15-22-22.924052.parquet +3 -0
- eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-07-14T12-49-47.596528/details_lighteval|gpqa:diamond|0_2025-07-14T12-49-47.596528.parquet +3 -0
- eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-07-17T15-23-49.905332/details_extended|ifeval|0_2025-07-17T15-23-49.905332.parquet +3 -0
- eval_results_ood/global_step_50/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-07-14T12-55-00.091779/details_lighteval|gpqa:diamond|0_2025-07-14T12-55-00.091779.parquet +3 -0
- eval_results_ood/global_step_50/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-07-17T15-24-59.219716/details_extended|ifeval|0_2025-07-17T15-24-59.219716.parquet +3 -0
- eval_results_ood/global_step_60/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-07-14T12-55-24.416815/details_lighteval|gpqa:diamond|0_2025-07-14T12-55-24.416815.parquet +3 -0
- eval_results_ood/global_step_60/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-07-17T15-57-48.158439/details_extended|ifeval|0_2025-07-17T15-57-48.158439.parquet +3 -0
- eval_results_ood/global_step_70/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-07-14T12-53-57.983091/details_lighteval|gpqa:diamond|0_2025-07-14T12-53-57.983091.parquet +3 -0
- eval_results_ood/global_step_70/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-07-17T15-56-25.432877/details_extended|ifeval|0_2025-07-17T15-56-25.432877.parquet +3 -0
- eval_results_ood/global_step_90/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_90_actor_huggingface/2025-07-14T13-03-46.159408/details_lighteval|gpqa:diamond|0_2025-07-14T13-03-46.159408.parquet +3 -0
- eval_results_ood/global_step_90/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_90_actor_huggingface/2025-07-17T16-05-07.289841/details_extended|ifeval|0_2025-07-17T16-05-07.289841.parquet +3 -0
- global_step_0/actor/huggingface/model-00001-of-00005.safetensors +3 -0
- global_step_0/actor/huggingface/model-00002-of-00005.safetensors +3 -0
- global_step_0/actor/huggingface/model-00003-of-00005.safetensors +3 -0
- global_step_0/actor/huggingface/model-00004-of-00005.safetensors +3 -0
- global_step_100/actor/huggingface/model-00004-of-00004.safetensors +3 -0
- global_step_20/actor/huggingface/model-00002-of-00004.safetensors +3 -0
- global_step_20/actor/huggingface/model-00003-of-00004.safetensors +3 -0
- global_step_40/actor/huggingface/tokenizer.json +3 -0
- global_step_40/data.pt +3 -0
.gitattributes
CHANGED
|
@@ -81,3 +81,4 @@ eval_results_avg32/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jso
|
|
| 81 |
eval_results_avg32/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 82 |
eval_results_avg32/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 83 |
global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 81 |
eval_results_avg32/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 82 |
eval_results_avg32/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 83 |
global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-07-14T12-41-17.800843/details_lighteval|gpqa:diamond|0_2025-07-14T12-41-17.800843.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a1915de718386eb93f9109d57afac0b7d5ff0bdd1ec8bc0b4f44ad76cde13d
|
| 3 |
+
size 624267
|
eval_results_ood/global_step_0/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-07-17T15-29-55.092392/details_extended|ifeval|0_2025-07-17T15-29-55.092392.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d152bbd0c8c5d14e7d394de666f1bc52cdb7f00a793dd2278366336778ff39
|
| 3 |
+
size 2953542
|
eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-07-14T12-45-55.307385/details_lighteval|gpqa:diamond|0_2025-07-14T12-45-55.307385.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:320961462ba17af043ade1891b65f72d467d64476ee7e51341ddf9574baa57b5
|
| 3 |
+
size 677713
|
eval_results_ood/global_step_10/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-07-17T15-27-34.486497/details_extended|ifeval|0_2025-07-17T15-27-34.486497.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8df1bc0ac624fb8f42ec1b9c66735a8bd458e37c299abcbfc4075bc4caf72a41
|
| 3 |
+
size 2510545
|
eval_results_ood/global_step_100/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-07-14T12-58-50.192486/details_lighteval|gpqa:diamond|0_2025-07-14T12-58-50.192486.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea41d1ce0e05fa03dbd2950b0488bba7a1de28e73806a0acdcf7bd7005dc8bd3
|
| 3 |
+
size 778539
|
eval_results_ood/global_step_100/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-07-17T15-57-23.838956/details_extended|ifeval|0_2025-07-17T15-57-23.838956.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ec088651b025747a1301bf285794b1221cc54f0a9c0631e27ab949fbc448fa8
|
| 3 |
+
size 2501925
|
eval_results_ood/global_step_110/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_110_actor_huggingface/2025-07-14T13-00-52.252218/details_lighteval|gpqa:diamond|0_2025-07-14T13-00-52.252218.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98f1f6783aeb7a40214264e63329f19aefc62395336b2c7c3d7f4e463b67e361
|
| 3 |
+
size 775262
|
eval_results_ood/global_step_110/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_110_actor_huggingface/2025-07-17T15-52-51.610154/details_extended|ifeval|0_2025-07-17T15-52-51.610154.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c9d62676f48c18ea14bd4e62f8917531cf3fd3908055b77a1e3b64da26f132
|
| 3 |
+
size 2208051
|
eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-07-14T12-46-08.302506/details_lighteval|gpqa:diamond|0_2025-07-14T12-46-08.302506.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f28bfdd5e4093c5da51a0a3af9db74820b45b15dc77b59e63ffc70cd29f9632
|
| 3 |
+
size 700090
|
eval_results_ood/global_step_20/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-07-17T15-33-20.611749/details_extended|ifeval|0_2025-07-17T15-33-20.611749.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6034daf92d601ae497f08cedddf6716c06b9cbe0f0dd9e2a65a1767f62158b50
|
| 3 |
+
size 2770805
|
eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-07-14T12-41-43.868511/details_lighteval|gpqa:diamond|0_2025-07-14T12-41-43.868511.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32497912b73c37179ed849368ec95d3f06026ffd2289d61a914a731fcba2a5e6
|
| 3 |
+
size 760073
|
eval_results_ood/global_step_30/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-07-17T15-22-22.924052/details_extended|ifeval|0_2025-07-17T15-22-22.924052.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0cbbc39a1cf44487f69e953be0d994696fc7c70b90bd4216d666b25bf64f17
|
| 3 |
+
size 2127646
|
eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-07-14T12-49-47.596528/details_lighteval|gpqa:diamond|0_2025-07-14T12-49-47.596528.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79c03a19771231ead919f1c3ed0510f5fc0e4a68993a729e3982151543e4dfaa
|
| 3 |
+
size 748579
|
eval_results_ood/global_step_40/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-07-17T15-23-49.905332/details_extended|ifeval|0_2025-07-17T15-23-49.905332.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:155be8871d3a8721a7a99a0d0d44eb217468318cbd2b0d115e09f68c866a4836
|
| 3 |
+
size 2277837
|
eval_results_ood/global_step_50/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-07-14T12-55-00.091779/details_lighteval|gpqa:diamond|0_2025-07-14T12-55-00.091779.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b170faa021109064af96570d425f52b2f914042c2dd5be52028532cdf4bc9177
|
| 3 |
+
size 897818
|
eval_results_ood/global_step_50/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-07-17T15-24-59.219716/details_extended|ifeval|0_2025-07-17T15-24-59.219716.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab46915f17d74479fc502c8b0a36d5b94f81aa1d61223001124677e77ec6df35
|
| 3 |
+
size 2557848
|
eval_results_ood/global_step_60/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-07-14T12-55-24.416815/details_lighteval|gpqa:diamond|0_2025-07-14T12-55-24.416815.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cf25e5634f19085a2f2ceca8674f34c5156ea00920cf5a5f3e3ee8e332b3ae8
|
| 3 |
+
size 835584
|
eval_results_ood/global_step_60/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-07-17T15-57-48.158439/details_extended|ifeval|0_2025-07-17T15-57-48.158439.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6fddd1cb5a85d133e43087570fbf1a33dd2d068acad44ab0d7de6df6fa74004
|
| 3 |
+
size 2476123
|
eval_results_ood/global_step_70/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-07-14T12-53-57.983091/details_lighteval|gpqa:diamond|0_2025-07-14T12-53-57.983091.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da1e518fb39613e542d70f3fe0f6dfe2da8724cc00db24cd82df42907b6b6cf4
|
| 3 |
+
size 765405
|
eval_results_ood/global_step_70/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-07-17T15-56-25.432877/details_extended|ifeval|0_2025-07-17T15-56-25.432877.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb23ac20692f2d707e093172a6599c4af26308d797d7c240f5eaa3ec9669778
|
| 3 |
+
size 2010755
|
eval_results_ood/global_step_90/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_90_actor_huggingface/2025-07-14T13-03-46.159408/details_lighteval|gpqa:diamond|0_2025-07-14T13-03-46.159408.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91cff3bcf8ebed270024ea19963aad728adab4e0578e5e9c37b89ec05839cb68
|
| 3 |
+
size 815731
|
eval_results_ood/global_step_90/details/_home_work_minzijun_rl_output_checkpoints_verl_0.4_grpo_simplelr_math_35_train_Qwen3-8B-base_max_response4096_batch1024_rollout8_vllm_global_step_90_actor_huggingface/2025-07-17T16-05-07.289841/details_extended|ifeval|0_2025-07-17T16-05-07.289841.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:174b7e956eebf67822ad7fe526250a3e25a2893fcedb707ed291b83ac5831997
|
| 3 |
+
size 2793847
|
global_step_0/actor/huggingface/model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9983f1b9ef2f60e7c3730d9bc11ada914e6ec630639b5b020a89bd158cd0446b
|
| 3 |
+
size 3996250744
|
global_step_0/actor/huggingface/model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa12339835bf7a093d3d0b0a0d2d77f8538301cfc7f8e7ec7a585858ebf7a1f
|
| 3 |
+
size 3993160032
|
global_step_0/actor/huggingface/model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7dd5a191c8da555def0714550375b3c0117751add408fcdda0c2a79ac0186bc
|
| 3 |
+
size 3959604768
|
global_step_0/actor/huggingface/model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad8b708792105133e03fe19e2d56c89c709f677f01285f8b3ede8947d59fd9fe
|
| 3 |
+
size 3187841392
|
global_step_100/actor/huggingface/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b7d5f62d121dfd48b41896f6c3f1fe4a3988f5f6169b1c30687eaa4702df541
|
| 3 |
+
size 1484803888
|
global_step_20/actor/huggingface/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d5be56bbf71c6379254d0f98e362dda9c884a1ffb4bcca206808800fbcd5bba
|
| 3 |
+
size 4999870640
|
global_step_20/actor/huggingface/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55c71ec84a1e6ffa7db6a1e524dae5d6ec34226102d9281c31e41a11b48ff190
|
| 3 |
+
size 4994516936
|
global_step_40/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
global_step_40/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c6863fda78cbb172d070750da10a8aaea503c62d00f1445b55fbe558771bb27
|
| 3 |
+
size 1492
|