Hugging Face's logo

tyzhu
/
hf_model_math

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
a2c4937
·
verified ·
1 Parent(s): 653634f

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. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  11. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  12. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  13. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json +3 -0
  14. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  15. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt +3 -0
  16. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_2.pt +3 -0
  17. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_3.pt +3 -0
  18. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_4.pt +3 -0
  19. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt +3 -0
  20. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt +3 -0
  21. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  22. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt +3 -0
  23. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  24. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  25. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  26. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/tokenizer.json +3 -0
  27. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/data.pt +3 -0
  28. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/extra_state_world_size_8_rank_0.pt +3 -0
  29. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/extra_state_world_size_8_rank_2.pt +3 -0
  30. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/extra_state_world_size_8_rank_4.pt +3 -0
  31. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/extra_state_world_size_8_rank_5.pt +3 -0
  32. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/extra_state_world_size_8_rank_7.pt +3 -0
  33. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  34. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  35. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  36. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/tokenizer.json +3 -0
  37. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_0.pt +3 -0
  38. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_1.pt +3 -0
  39. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_2.pt +3 -0
  40. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_5.pt +3 -0
  41. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_6.pt +3 -0
  42. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_7.pt +3 -0
  43. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_0.pt +3 -0
  44. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_1.pt +3 -0
  45. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_2.pt +3 -0
  46. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_5.pt +3 -0
  47. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_6.pt +3 -0
  48. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_7.pt +3 -0
  49. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/model-00001-of-00002.safetensors +3 -0
  50. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -41,3 +41,7 @@ pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge7-temperature-1.0/c
41
  pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
41
  pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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:bda746bab51495c1fd50c0a53c381ddf10d75429a0297c183f6f8c4a6ed372b9
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/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:e7276b975a6ffc96397e410e554bca17350dd3c2600a24e74b5b578efa2af6e5
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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:ab1811d0066a64a8c1b8f3363d93b48821e0fe09e742779f068e22318fb26c9c
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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 sha256:22757ffb05725478b1c1dbeee4e78ae6f669111c6f91c613698170530fa56ce4
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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 sha256:59b5f9fe02c2c43f9d4a8245eccd5bc9c548dff3646929ba39d201a2d89b90b9
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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 sha256:5d227687d673a6d4cddcce2eadf63e665740371ea76ed050757c0eed4293b654
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/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 sha256:2279557e6c239e3075d6478b60f1d1800daaba9caa478b96fed8533e21c76a18
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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:a1390deeccdee907893134bdab17cccbbfe5f2a3a3afebf94da6d2b2af263993
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec842ae48b943f09d19bda9f63b33d9e1fdc4cdef1593ef74cde9f17ae8c28b
3
+ size 4998767360
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3ba43a8a43233c94cb213a46092b52f3dfc04e1eeda1b8a673c977d20fe62a
3
+ size 4932808968
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8d95a55079c5bc11fe90f3664d216db24e49b71fc9170ba5cd9a6de276f3b4
3
+ size 4495462048
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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:fca5f21ad2fa64864bdd73f250f24ab488575646cfd5c22cbbd06098ebd40324
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6859aace96b3fce39f18906a82ef19185628eed81525c5b24aa0aa965bd338bf
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/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:c2e44209deb3fabb668c0cbf17d596d244678cce68f5fe6e703e0ff6fd2123cc
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/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 sha256:6679899f49cdb4869b4acfd4d77fb915f578bc9f1a791a7ff9a64c8528825644
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/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 sha256:7d7e52926f1bacc948a26c695d5b37748a7e7eded2dce2e72b4730de774d0c22
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97432940cc3ce780040397de634f494471b2a9612a6cd116a780d3c2820abaa5
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4fa93cac4b0145b65619801dc7e854517cd781d43d83e92a2549bfe59d6fcb
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398cdadbc08509505e2622e803826723690d7d9e02d965525ff24af89c175686
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64ddf6dce72bb8a8f54bb44d9e987375e973f8d6c4d6095af9d1f64f7be30c5
3
+ size 1492
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09438a0f5a631f830b690bca793c0f28df2c586bc2c833f343c7e24f8088f673
3
+ size 4998767360
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c85656564025722d77e8144d4b6ad20b411cd76beeb4151896d34a8737f09b
3
+ size 4932808968
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b4996012450d861121e2bc24f1bd03b12f5414448b5d1a92ce49e35adef604
3
+ size 4495462048
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/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-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e367aa4e4921b1598c0b062d8d887d4797836b6b0be8b7f6bd8bf99a39edb5c5
3
+ size 1492
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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 sha256:3d4fab691cdfa4d6eb38580815e64c37bf4dc5252d8310f12fbfbd0c94be2ddb
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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:fec2b2d82bc1d805abee2e501422874d269d1f615103e9ee9423335b54ecd7f2
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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 sha256:3629bfd10723cbdf0b98b704ac0dcb42fec1cb705b4f832b74dc6d3bbbb21f50
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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 sha256:88eefb71372d9824891a294659b776f4d5a5dd043269ebce180818a7ee176a0f
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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 sha256:4d8dcfab32b481bec0d7e30f47041adc700bcfc68f3657c9a94c0d74e78261b6
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7114c732b04a4a6e6adb25ced9c1f88c08b952ee4f8316158729312f980dadab
3
+ size 4998767360
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5565261aca4dfd41cb59aa5c61101964649ae78f24b5722c18143c6d144559c
3
+ size 4932808968
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7dc19388c83663136e8b7f925cf83eac8632718aa2a57a5ffaadff68ea99c98
3
+ size 4495462048
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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:ad39bb288a7a18789636d697338ef830a67907fb69973062c4b6eea463061f2e
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d13dbc3220c84b43f3f53ee17727af5c3b54e87e5edf7245377176da37432c5
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661c51a8aad9c9eeb2505d4fdef8a1185fd2bdc8f9e7d4c56f84ce3ee4e51abb
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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:a5ca4eb78ea880666fb2ceba1da80601b0e933a384080f8c53b291dd0f7c81b0
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aede43b5d8623710b4fc252881ac0f6d7a0770873778a7db624bfe6b2ecf78c
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7875231710cca2abfee985b8853bb1e18cf933a1ac3777d43a1afaedfca9dbd1
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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:a0c4b436659ca449ad94016dd718d42137f546ca0753ae794d4c6a392617979a
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfb6efbf51755a996b2c92a665ed87fa673d5e989c02beeabe1b3076b48e70f
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d301e26b08b29b3205010bd4441cd5c4e1e28009c956fba634a1117d2290de6
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f58f2dce372ab11ca58cbe0fbe09a5d5e5f754f70854d7bc135a65b4efb38bf
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/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:dfc75ccf429bc18d8348d17953c31cdc92b1951c3012c5a2b35177d6e0e80c8d
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_301/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2980341f34c1da32d64c89e65b074b17402a6714634a0f8f5f8ce124a0421d82
3
+ size 3212775159
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58c7b596f3cede5b114a84a2348659decc6c20ead506be71adb29b276180679
3
+ size 4996670464
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/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