Hugging Face's logo

bensondccnqwc
/
tmp-cdcnqwi71

Safetensors
Model card Files
xet
 Community
bensondccnqwc commited on
Commit
8f9caed
·
verified ·
1 Parent(s): 548f51e

Add files using upload-large-folder tool

Browse files
Files changed (29) hide show
  1. .gitattributes +10 -0
  2. eval_results_ood/global_step_80/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_80_actor_huggingface/2025-08-20T21-48-46.935565/details_extended|ifeval|0_2025-08-20T21-48-46.935565.parquet +3 -0
  3. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T18-03-43.749603/details_extended|ifeval|0_2025-08-20T18-03-43.749603.parquet +3 -0
  4. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T18-03-43.749603/details_lighteval|gpqa:diamond|0_2025-08-20T18-03-43.749603.parquet +3 -0
  5. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T20-28-04.073795/details_extended|ifeval|0_2025-08-20T20-28-04.073795.parquet +3 -0
  6. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T20-28-04.073795/details_lighteval|gpqa:diamond|0_2025-08-20T20-28-04.073795.parquet +3 -0
  7. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T21-43-47.552890/details_extended|ifeval|0_2025-08-20T21-43-47.552890.parquet +3 -0
  8. eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T21-43-47.552890/details_lighteval|gpqa:diamond|0_2025-08-20T21-43-47.552890.parquet +3 -0
  9. global_step_10/actor/huggingface/model.safetensors +3 -0
  10. global_step_10/actor/huggingface/tokenizer.json +3 -0
  11. global_step_10/data.pt +3 -0
  12. global_step_100/actor/huggingface/tokenizer.json +3 -0
  13. global_step_100/data.pt +3 -0
  14. global_step_20/actor/huggingface/tokenizer.json +3 -0
  15. global_step_20/data.pt +3 -0
  16. global_step_30/actor/huggingface/tokenizer.json +3 -0
  17. global_step_30/data.pt +3 -0
  18. global_step_40/actor/huggingface/tokenizer.json +3 -0
  19. global_step_40/data.pt +3 -0
  20. global_step_50/actor/huggingface/tokenizer.json +3 -0
  21. global_step_50/data.pt +3 -0
  22. global_step_60/actor/huggingface/tokenizer.json +3 -0
  23. global_step_60/data.pt +3 -0
  24. global_step_70/actor/huggingface/tokenizer.json +3 -0
  25. global_step_70/data.pt +3 -0
  26. global_step_80/actor/huggingface/tokenizer.json +3 -0
  27. global_step_80/data.pt +3 -0
  28. global_step_90/actor/huggingface/tokenizer.json +3 -0
  29. global_step_90/data.pt +3 -0
.gitattributes CHANGED
@@ -62,3 +62,13 @@ eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_c
62
  eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_0_actor_huggingface/2025-08-20T21-36-38.816189/details_extended|ifeval|0_2025-08-20T21-36-38.816189.csv filter=lfs diff=lfs merge=lfs -text
63
  eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_10_actor_huggingface/2025-08-20T20-20-53.516588/details_extended|ifeval|0_2025-08-20T20-20-53.516588.csv filter=lfs diff=lfs merge=lfs -text
64
  eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_10_actor_huggingface/2025-08-20T21-30-26.010784/details_extended|ifeval|0_2025-08-20T21-30-26.010784.csv filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
62
  eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_0_actor_huggingface/2025-08-20T21-36-38.816189/details_extended|ifeval|0_2025-08-20T21-36-38.816189.csv filter=lfs diff=lfs merge=lfs -text
63
  eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_10_actor_huggingface/2025-08-20T20-20-53.516588/details_extended|ifeval|0_2025-08-20T20-20-53.516588.csv filter=lfs diff=lfs merge=lfs -text
64
  eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_10_actor_huggingface/2025-08-20T21-30-26.010784/details_extended|ifeval|0_2025-08-20T21-30-26.010784.csv filter=lfs diff=lfs merge=lfs -text
65
+ global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
eval_results_ood/global_step_80/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_80_actor_huggingface/2025-08-20T21-48-46.935565/details_extended|ifeval|0_2025-08-20T21-48-46.935565.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2203ee878c41394f24d9515efd9c5b6d07284195ce9006c27c55bdbe318145
3
+ size 1286597
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T18-03-43.749603/details_extended|ifeval|0_2025-08-20T18-03-43.749603.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb715b76416500380f7fa14665c44dfbaf722122420565724c1e78439cc101b9
3
+ size 1287943
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T18-03-43.749603/details_lighteval|gpqa:diamond|0_2025-08-20T18-03-43.749603.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cba75e84dcba95cf3200c4a92e5a311a5919183e86fd926b9f103bdaedf995
3
+ size 740664
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T20-28-04.073795/details_extended|ifeval|0_2025-08-20T20-28-04.073795.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86576718eaf5298ced10f680d659e147ee28fd2ec0bab2f6dc6d0c442a0a609c
3
+ size 1230970
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T20-28-04.073795/details_lighteval|gpqa:diamond|0_2025-08-20T20-28-04.073795.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f161a40db9f0f113736301987f6e7c131e7a88aaded9654a75749f9def9d9e86
3
+ size 711359
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T21-43-47.552890/details_extended|ifeval|0_2025-08-20T21-43-47.552890.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da60cba5dce1305d35e892f29faeb7fd0596825d51c6717b6d721de79706fb64
3
+ size 1230970
eval_results_ood/global_step_90/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_True_bias1.5_global_step_90_actor_huggingface/2025-08-20T21-43-47.552890/details_lighteval|gpqa:diamond|0_2025-08-20T21-43-47.552890.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f161a40db9f0f113736301987f6e7c131e7a88aaded9654a75749f9def9d9e86
3
+ size 711359
global_step_10/actor/huggingface/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9131f8ee80a57cb7c3db3a77f2be329eb04c6baa95094a17cd51c6753d09bb
3
+ size 4063515640
global_step_10/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_10/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae9cac0f48798a4167cb59dc3be01018f3b002fa92413d0d684d6aab802248c
3
+ size 1947
global_step_100/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_100/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc54cc54a2ae27bcb749f03791d68574003beaeac89e301216cd08481afb0166
3
+ size 1947
global_step_20/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_20/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec3eef973f024013ff9e53830cf1ec34af7e525911b64ab819235c7976f7d0d
3
+ size 1947
global_step_30/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_30/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e24cf7e13052deb8f18db6c09cb86b369fe04864ae21ed87dc42829ad10a9e5a
3
+ size 1947
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 sha256:37f844bd43d239b679f610c60d464ce1d2f071bb27f66867de02d17db6a772ba
3
+ size 1947
global_step_50/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_50/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a9191ddeece333cb9640bc2f326b62e3eee0e127c70deca1ea6cce70e81fff
3
+ size 1947
global_step_60/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_60/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbbb2217cd9d765107abc2e5227e1243b259be52cc2d672b7b30676a24b23c6
3
+ size 1947
global_step_70/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_70/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87b7d97b67ae821087ff43fb7fbebd7fce80d386b85214b53949b5f6bfa1ece
3
+ size 1947
global_step_80/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_80/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50640094f4ad1fd03a7afc9526e3a0c5d87c34d5e9c227c66bda96072c84df70
3
+ size 1947
global_step_90/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_90/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e950e65d778d1d88512086d9d16dab084a2da6c68cc2f1a55963580303f2b00e
3
+ size 1947