Hugging Face's logo

DatPySci
/
RLVR-SGDM-Gap

Safetensors
Model card Files
xet
 Community
DatPySci commited on
Commit
6eb2cb0
·
verified ·
1 Parent(s): 25fe78d

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-SGD-1e-2/global_step_128/actor/optim_world_size_4_rank_0.pt +3 -0
  2. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_128/actor/optim_world_size_4_rank_1.pt +3 -0
  3. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_128/actor/optim_world_size_4_rank_2.pt +3 -0
  4. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_128/actor/optim_world_size_4_rank_3.pt +3 -0
  5. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_192/actor/optim_world_size_4_rank_0.pt +3 -0
  6. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_192/actor/optim_world_size_4_rank_1.pt +3 -0
  7. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_192/actor/optim_world_size_4_rank_2.pt +3 -0
  8. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_192/actor/optim_world_size_4_rank_3.pt +3 -0
  9. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_256/actor/optim_world_size_4_rank_0.pt +3 -0
  10. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_256/actor/optim_world_size_4_rank_1.pt +3 -0
  11. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_256/actor/optim_world_size_4_rank_2.pt +3 -0
  12. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_256/actor/optim_world_size_4_rank_3.pt +3 -0
  13. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_320/actor/optim_world_size_4_rank_0.pt +3 -0
  14. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_320/actor/optim_world_size_4_rank_1.pt +3 -0
  15. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_320/actor/optim_world_size_4_rank_2.pt +3 -0
  16. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_320/actor/optim_world_size_4_rank_3.pt +3 -0
  17. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_384/actor/optim_world_size_4_rank_0.pt +3 -0
  18. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_384/actor/optim_world_size_4_rank_1.pt +3 -0
  19. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_384/actor/optim_world_size_4_rank_2.pt +3 -0
  20. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_384/actor/optim_world_size_4_rank_3.pt +3 -0
  21. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_448/actor/optim_world_size_4_rank_0.pt +3 -0
  22. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_448/actor/optim_world_size_4_rank_1.pt +3 -0
  23. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_448/actor/optim_world_size_4_rank_2.pt +3 -0
  24. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_448/actor/optim_world_size_4_rank_3.pt +3 -0
  25. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_512/actor/optim_world_size_4_rank_0.pt +3 -0
  26. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_512/actor/optim_world_size_4_rank_1.pt +3 -0
  27. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_512/actor/optim_world_size_4_rank_2.pt +3 -0
  28. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_512/actor/optim_world_size_4_rank_3.pt +3 -0
  29. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_64/actor/optim_world_size_4_rank_0.pt +3 -0
  30. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_64/actor/optim_world_size_4_rank_1.pt +3 -0
  31. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_64/actor/optim_world_size_4_rank_2.pt +3 -0
  32. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/global_step_64/actor/optim_world_size_4_rank_3.pt +3 -0
  33. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_128/actor/optim_world_size_4_rank_0.pt +3 -0
  34. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_128/actor/optim_world_size_4_rank_1.pt +3 -0
  35. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_128/actor/optim_world_size_4_rank_2.pt +3 -0
  36. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_128/actor/optim_world_size_4_rank_3.pt +3 -0
  37. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_192/actor/optim_world_size_4_rank_0.pt +3 -0
  38. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_192/actor/optim_world_size_4_rank_1.pt +3 -0
  39. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_192/actor/optim_world_size_4_rank_2.pt +3 -0
  40. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_192/actor/optim_world_size_4_rank_3.pt +3 -0
  41. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_256/actor/optim_world_size_4_rank_0.pt +3 -0
  42. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_256/actor/optim_world_size_4_rank_1.pt +3 -0
  43. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_256/actor/optim_world_size_4_rank_2.pt +3 -0
  44. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_256/actor/optim_world_size_4_rank_3.pt +3 -0
  45. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_320/actor/optim_world_size_4_rank_0.pt +3 -0
  46. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_320/actor/optim_world_size_4_rank_1.pt +3 -0
  47. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_320/actor/optim_world_size_4_rank_2.pt +3 -0
  48. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_320/actor/optim_world_size_4_rank_3.pt +3 -0
  49. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_384/actor/optim_world_size_4_rank_0.pt +3 -0
  50. qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/global_step_384/actor/optim_world_size_4_rank_1.pt +3 -0
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:3ae6f2f953a2e0134afe27549123ddbea7e47be8e3fed951e1a1b18caeb97309
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:64bd024d93301f49cca52194ec8c6edba3e14fbbdeb5091be6443686ccd7275b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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 sha256:15c4b82048832400d48c27fc1e4a4b13c873a18f840f97b885d9762606cb166b
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-2/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:aeb3efd8564ab67a6fbe332a9161406e64249a6abf96f6a9ef33057368ade6c2
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9cd6963468df4eb3950191ce3358d33a869d48c424dc07f8f3da843b1e547073
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9031c7954e9f03c66619337bd6770ff6e86afc214bc7d501266ef8d32acf8ef7
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9572c8e08b60b7db34074772c2584142e9797a6f6aa356102b4eb671df33a4ad
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:90d3b8b8d60ea1c4d3436c336914c04cc633181ea7a2113437b71332e160f3bb
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9cd6963468df4eb3950191ce3358d33a869d48c424dc07f8f3da843b1e547073
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9031c7954e9f03c66619337bd6770ff6e86afc214bc7d501266ef8d32acf8ef7
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9572c8e08b60b7db34074772c2584142e9797a6f6aa356102b4eb671df33a4ad
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:90d3b8b8d60ea1c4d3436c336914c04cc633181ea7a2113437b71332e160f3bb
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9cd6963468df4eb3950191ce3358d33a869d48c424dc07f8f3da843b1e547073
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9031c7954e9f03c66619337bd6770ff6e86afc214bc7d501266ef8d32acf8ef7
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9572c8e08b60b7db34074772c2584142e9797a6f6aa356102b4eb671df33a4ad
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:90d3b8b8d60ea1c4d3436c336914c04cc633181ea7a2113437b71332e160f3bb
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9cd6963468df4eb3950191ce3358d33a869d48c424dc07f8f3da843b1e547073
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9031c7954e9f03c66619337bd6770ff6e86afc214bc7d501266ef8d32acf8ef7
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9572c8e08b60b7db34074772c2584142e9797a6f6aa356102b4eb671df33a4ad
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:90d3b8b8d60ea1c4d3436c336914c04cc633181ea7a2113437b71332e160f3bb
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9cd6963468df4eb3950191ce3358d33a869d48c424dc07f8f3da843b1e547073
3
+ size 2713
qwen-3b-lora/Qwen/Qwen2.5-3B-Instruct-math-GRPO-SGD-1e-3/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 sha256:9031c7954e9f03c66619337bd6770ff6e86afc214bc7d501266ef8d32acf8ef7
3
+ size 2713