Hugging Face's logo

tyzhu
/
hf_model_math

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
f91c837
·
verified ·
1 Parent(s): 3e01154

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. mathhard2-grpo-qwen3-1.7b-4k-step-50/model.safetensors +3 -0
  3. mathhard2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json +3 -0
  4. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/model-00001-of-00002.safetensors +3 -0
  5. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/model-00002-of-00002.safetensors +3 -0
  6. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/tokenizer.json +3 -0
  7. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_0.pt +3 -0
  8. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_0.pt +3 -0
  9. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_0.pt +3 -0
  10. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_1.pt +3 -0
  11. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_2.pt +3 -0
  12. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_3.pt +3 -0
  13. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_4.pt +3 -0
  14. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_5.pt +3 -0
  15. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_6.pt +3 -0
  16. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_7.pt +3 -0
  17. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  18. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  19. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  20. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json +3 -0
  21. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_0.pt +3 -0
  22. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_1.pt +3 -0
  23. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_2.pt +3 -0
  24. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_3.pt +3 -0
  25. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_4.pt +3 -0
  26. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_5.pt +3 -0
  27. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_6.pt +3 -0
  28. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_7.pt +3 -0
  29. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_0.pt +3 -0
  30. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_1.pt +3 -0
  31. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_2.pt +3 -0
  32. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_3.pt +3 -0
  33. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_4.pt +3 -0
  34. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_5.pt +3 -0
  35. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_6.pt +3 -0
  36. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_7.pt +3 -0
  37. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/data.pt +3 -0
  38. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_1.pt +3 -0
  39. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_6.pt +3 -0
  40. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_3.pt +3 -0
  41. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_4.pt +3 -0
  42. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_4.pt +3 -0
  43. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/data.pt +3 -0
  44. mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00001-of-00003.safetensors +3 -0
  45. mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00002-of-00003.safetensors +3 -0
  46. mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00003-of-00003.safetensors +3 -0
  47. mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/tokenizer.json +3 -0
  48. mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/random_state.pkl +3 -0
  49. mathmedium2-mutualposclip0.2-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00001-of-00003.safetensors +3 -0
  50. mathmedium2-mutualposclip0.2-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00002-of-00003.safetensors +3 -0
.gitattributes CHANGED
@@ -68,3 +68,7 @@ pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/c
68
  pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  mathhard2-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
68
  pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  mathhard2-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ mathhard2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathhard2-grpo-qwen3-1.7b-4k-step-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201d2bec3dc923f60caaec94fe334383e895f8c5ab011c3bf88090ca05d6dceb
3
+ size 4063515640
mathhard2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bdd113738213bdd1c9618a4add96abc3fe9023b650239eea0e73331874de541
3
+ size 4969539560
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/huggingface/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cee00cb3293986e460fdd18604d1bc37a9e34a83097ecf531563895688f95db
3
+ size 3157455608
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/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
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661b7c6ed04bab3b10756192e11ca61dd600b126480212ec410f36513142d342
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64f62437460a18fae7c22d276ce9994a636635e28e50b0e5b16b2ae72c73fa43
3
+ size 1720600311
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3ee5de802e18a6c464c668cbdea573f3a0762277f1da014fc4de56061b19ae
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:919a2fa7656698779da0467195200081bea59e9188d28ba480928d2c640b236c
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3af5db6866f4159722e3292cdd17a0eaf592558b03b04d5b8d1a4519eb9c33
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af942cccf3e655acb5044223ed1e67480b3ea44abc0dcec8e766a10f10bf0e4a
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542616d296554beeb26e2c0e3ca00bf39476ab873ce590bd527f6259c67eddd5
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4e97adb81cdd7a88915021119adbca638cb20fb5354c3b7e38da09ebe3011f
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5142697a3fac0fad6a9ce7a2385c9ae7643c8c5fbb7d9dc767c93589cf184b99
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a6569381d581fbc1f645ce86beb08209de562214cf5167c2a7f864edd16b7f
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7edb3bd529ed3cc91699fc1911492ee661cfc8d403c2ee5b34aac7cfe9f9e2
3
+ size 4998767360
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99292ee13e5ce09eb8c68625fbeeb0aceef1e4e099be808c37ca85a9df71a26d
3
+ size 4932808968
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8ca9cf9a3aac680cd265ee5db91e8123ef3c5269c701e552969894f4cd12c5
3
+ size 4495462048
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776e3b83eec99fc34e9ffa051db20ea8cf43e81f2fcdf60b071780ee7b6ea0f9
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb80609cd4649a51fd6abbb9b33342554c3ccdb62fd3a288f136e199956d4358
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9164126dcdddd1f12db8c276306f51ac50f6f817f032c39da72218227bad712b
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76266f3980106a3b4c8a0f979a9f05279c609e8fd71d77943133d2b8ddc5162a
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe94a244ad4b96e7520bd9179730874387554c5a089aee7279ff5ff86d68e59c
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3e07897a2d7b441470e128e692e600836c4711acfba4e641ee827ae4fa58ad
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e2d59e00a2357a44806d289bf6735e93325daebb3eb5e83cede0a5f49cf09d
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ad4377e255291ba3e2421547ac1570aa4005ca155fbf636cdbfcc3d77fe8ea
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df773d6ac160dc515224ad0a6a187ab2d5724912c2b9b1aad255d66070128c75
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e794d73c57ed52a05e41c8eb029e2cac1cca5573ff6fd4f816a17ab9b3320c61
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f713aa48f6c41790255bff1f68c4e9cad1b6d2138a21fb90c5f826b16de7bf38
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379b52b90e6987680e507caeb6c55ebd5d38e7505956ab374e7a70cd5dfd38f6
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd818ec95ce43bda97e4caa6787b22af6ac0a7e9b1ae36d213cc9188ac462af1
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a887a315dc209983280795925b5bae6891e2d7855c15192e8713f59d87d1c44
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275296354734ab1b1e62950747a7fbb48780fb7f82af4c6f0922df72f7675dc3
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e31b687c6e1ee4c73ab3bff001886f37a987e30cdea71d85aa52d89f5bd62c
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3304d4f734e7f6ea306229510c87cdf58c788bd687887718acec32e8b6e4303
3
+ size 1492
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc4ef2e6ee8f7092508c4792b5bd4090cea7760a7568a0aaf7c5ca806aa1bd4
3
+ size 14696
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6765e06801fe60b69e69b6327e50f0d3c492ecb2ba9630507afc8dff28ba7a
3
+ size 14632
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0d0064f02965b08cde553ccc3bed62e6a14f4e1fe80221569bf55b78184b1a
3
+ size 1803528186
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea4272ed9b7cb127f75ebfed022e62247270fdbff1bfe2a837406ef70a0bb09
3
+ size 1803528186
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651861073270d2d71e6e1e58b61abbd44a96ba42fa1e05c289581cc4c3d51859
3
+ size 3212775159
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a0f167e052fb597b6af95e4ecfebbe88f35785da9c87cc7f29d19611a690a6
3
+ size 1492
mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af812c5ddca6be843496c3b89acff79eaecfdee98e1fdbf01bccc4f22f28af2
3
+ size 4982131536
mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831f7f81c6ca14bd93c1a2f36c818cf20f0989a0ac71463e79840f14d62f86a2
3
+ size 4932949336
mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003c2b9476d9c8fdf38c6a797d883a7e774bb0b082bea8627e33723435952089
3
+ size 3673383040
mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
mathmedium2-mutualposclip0.0-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/random_state.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e913a22d2ca9468b044b25ecc554f48e1d83cb32a3c18a1cb17c449ffeec734
3
+ size 12846
mathmedium2-mutualposclip0.2-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae2eb5bb3bfef872fba0056668901b27728e72a33f9b98e8690609f103bcaf5
3
+ size 4982131536
mathmedium2-mutualposclip0.2-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/actor/global_step_100/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b1d3d07f0955603ea2dc9f8700b583a634fc4103a39273a732cddc8408abcd
3
+ size 4932949336