Hugging Face's logo

DatPySci
/
RLVR-SGDM-Gap

Safetensors
Model card Files
xet
Community
DatPySci commited on
Commit
736fe9c
·
verified ·
1 Parent(s): 10c9d5a

upload lora

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_0.pt +3 -0
  2. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_1.pt +3 -0
  3. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_2.pt +3 -0
  4. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_3.pt +3 -0
  5. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_0.pt +3 -0
  6. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_1.pt +3 -0
  7. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_2.pt +3 -0
  8. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_3.pt +3 -0
  9. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_0.pt +3 -0
  10. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_1.pt +3 -0
  11. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_2.pt +3 -0
  12. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_3.pt +3 -0
  13. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_0.pt +3 -0
  14. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_1.pt +3 -0
  15. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_2.pt +3 -0
  16. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_3.pt +3 -0
  17. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_0.pt +3 -0
  18. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_1.pt +3 -0
  19. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_2.pt +3 -0
  20. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_3.pt +3 -0
  21. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_0.pt +3 -0
  22. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_1.pt +3 -0
  23. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_2.pt +3 -0
  24. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_3.pt +3 -0
  25. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_0.pt +3 -0
  26. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_1.pt +3 -0
  27. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_2.pt +3 -0
  28. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_3.pt +3 -0
  29. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_0.pt +3 -0
  30. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_1.pt +3 -0
  31. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_2.pt +3 -0
  32. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_3.pt +3 -0
  33. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_0.pt +3 -0
  34. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_1.pt +3 -0
  35. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_2.pt +3 -0
  36. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_3.pt +3 -0
  37. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_0.pt +3 -0
  38. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_1.pt +3 -0
  39. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_2.pt +3 -0
  40. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_3.pt +3 -0
  41. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_0.pt +3 -0
  42. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_1.pt +3 -0
  43. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_2.pt +3 -0
  44. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_3.pt +3 -0
  45. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_0.pt +3 -0
  46. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_1.pt +3 -0
  47. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_2.pt +3 -0
  48. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_3.pt +3 -0
  49. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_384/actor/optim_world_size_4_rank_0.pt +3 -0
  50. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_384/actor/optim_world_size_4_rank_1.pt +3 -0
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48aa5e8ed4b2f6a4e8e6edaeb92a31eebe7d69a2cda8c60df06ea94097590c4f
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba42986e6d80b4361bfffc2181825ba6685c455f6231b3a1836673271889260a
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc8ad56c134b057a3e0d4a6b5ec32d412efb85a113f5414f83c3e0e5e846e39
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_128/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdf46c4012fa38fb25060153c71cb258f8f815ee3763fe9f7702c87f08d07d2
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55061c3027843c09b9a081304b40a3808c27e15486a201fffbb3019a86cb00ee
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65038fb659e62b80c297884c7ce8589c5c8575c34d5413456f6046fd358a886b
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ba96461284acb608e69954576c5ddc9c383f7cbcd3fd91e60a939e18b5b9f1
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_192/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b39aa87552d590887d7db1f7a9589896d60cfd6aac74cd386e158436871cc53
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b21a85c857ea936ab2d50092e4525bd22d85c50788f9833aa546ab9c9766807
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375d3f599ec1fdeca7a1b575418dc273dd46475d662389d67a5e0e8ceb5f6ad5
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38218bcd6d2f47f0f4005ef28067dc52af779d3b9c99a17678d5eb5b44ae8341
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_256/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791b0bdb15379c161eab0d2540a4cd123449317cadafdb19d2d9987381e350c5
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3638338acdc0a53a53f6d84e09ea1c2d87ff9818537adac032accfecdb27ce6
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8913d5adc2f1fb08122e411bbe3ec09149adb5b97c5a3148475651cce71c2f
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0446525a4dc05beb6e7e1b4f37552e6bfe7856095c1af2b4051d4ffd0b59f7
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_320/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b54f1c72edc7aa5044b5515c4bea342e076b2dc48e5db919e435297a8a7c9fe
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd05df70478c3f1d2dc4c875234382fefa77be324a9c92cad423a716a125ec6
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b75a9eb020eddcb56a49298d5804317f8b58618137ae1fa4b90f45e1865be84
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e50bb514aa21e34c23102a1ce5a4369d65fd1bd36c039e0a7782f65845a9d3
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_384/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946399c4b23a5b18f1c710f3b70c977760dac2d7e5dd42edcf67901628805c63
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2420848b2b409e1bed521d63c969a73dbc3a6d74633539d64dd6d0bcf47386a2
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc42032f2150475e35ecc08cd101efd92e16a18a95ed38fb396070deb5794ed
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f2c764eb51b66c31ab3bc221db12e2e7abd8721db2db4b9b9e8758435dd125
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_448/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e408b7dc8730b83ebee93159848b41cde9484ca11be09d9571a4108f1a4b952
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d7f474d7205966134325f63f492989a2ae4a796dcfb5a9bc169ee925cbef13
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec0c209a5fb678ca6c1d5b30787742bf1979bd14cbd9f0a604d627755d59e084
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d66d2e780f48fe3b965980f5c5064bca7462bdeac7750279cfdd094e96fd6c
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_512/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db804060a738ea83a2ff13a2f2a7caa961e4b1692bdcc84c5d45e933074d5673
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0693cb6c51a8bb3806e57e110b732d87e56dbcf98d07e8a0b1c5ecf23b1d955
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8073d7a36a2ddcd9c45ce1d70847603546ccdb46a02d3b4b34fbd3bd9d26891b
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8a32a081da9079beeedd874cec1f1ef0c3102f146d1edb201f6915ea6655d8
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank16/global_step_64/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b010932a3dca26532c3c4251f17bc47de879bee59f6bbf7a8933f660139b5299
3
+ size 60527100
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd71d559cf12ad081a4b593acb207ee2aec523d36a144f74aeb2a71919f655f
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf43081dd8a6dd77bc7e2f1da0dcffef9fee67ae9f6893405f47cb347980445
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfe9fe9b8fc89b4f44bf5252176d8c3c67fb66ad48a30c0b068471d4d3d5b05
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_128/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f1f7ffcc681155bb3817515a4738588079f47b574b657b7ab4076b3469b9be
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837ed09d8198bc4ce137faaa688d3e4e18112a8864b92b9a29362f0a2d3cc7c9
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9332ac7512ee20ebb7576d93ed0e96db4a45135e3752a6df46ccb4ede6d9efe
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f516bd806950c0332346534b62c5a2e69129c163f56291a14516685058452af6
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_192/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca08e39f61bc4c85c2cb1544251a1b67f41d9bca10798a6cbb831f9aa64d52b7
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09730b37fc1f025d67e89f4b54dae467d8cd14a3fef1aed6fae2e5629d531bb6
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09324c798b0480653a83191ffeca5096efb71c95d72221eed34b3b8d34df22b
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b52827fe180df8139bfd8e0144f34eef8e56daac996dd52aab0c0706b546fa
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_256/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2387a31a3bbc508b7a030214266bb7e199f49f64933b353d427d1d624c9419a
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a1cea69bad38b32f078ea47e5475464d19a9d8741a5d497e3bd287787f2a25
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acd092f24d6d42a804e8a2d5a0889c3135b7fc13d35b336bd577f9dd91ff65e
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444e9e52217b8ae761263353f535102cef429ea4c44954d37e1726bb3280e9fd
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_320/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c946ae3620b45159a27427bd31e7c4bab3dd4efceb87dbfd844e86178b20f2
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_384/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd54ddef40c1c076dad7e52bbd5d810c1368fbaa7257c5e18f08c8ea875993fd
3
+ size 120394620
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-LoRA-rank32/global_step_384/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495839099d15f3e0647bbedeb5ef913b937bc67a54a2bdadd9c06b639c7dc6b1
3
+ size 120394620