Hugging Face's logo

tyzhu
/
hf_model_math

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
4d43abd
·
verified ·
1 Parent(s): 5483784

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 +3 -0
  2. mathmedium2-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  11. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  12. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  13. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json +3 -0
  14. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  15. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt +3 -0
  16. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_2.pt +3 -0
  17. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_3.pt +3 -0
  18. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_4.pt +3 -0
  19. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt +3 -0
  20. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt +3 -0
  21. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  22. mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt +3 -0
  23. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_0.pt +3 -0
  24. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_1.pt +3 -0
  25. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_3.pt +3 -0
  26. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_4.pt +3 -0
  27. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_6.pt +3 -0
  28. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_7.pt +3 -0
  29. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_1.pt +3 -0
  30. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_2.pt +3 -0
  31. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_3.pt +3 -0
  32. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_4.pt +3 -0
  33. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_5.pt +3 -0
  34. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_6.pt +3 -0
  35. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_1.pt +3 -0
  36. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_2.pt +3 -0
  37. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_3.pt +3 -0
  38. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_4.pt +3 -0
  39. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_5.pt +3 -0
  40. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_6.pt +3 -0
  41. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/data.pt +3 -0
  42. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt +3 -0
  43. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  44. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json +3 -0
  45. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  46. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  47. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  48. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  49. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  50. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -55,3 +55,6 @@ pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/a
55
  mathhard2-grpo-qwen3-1.7b-4k-step-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
55
  mathhard2-grpo-qwen3-1.7b-4k-step-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathmedium2-mutualposclip0.0-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:bd8f5a411aa84528c462cdc9bf780af3ec80c0d75d02b0ebfff14708be96dd60
3
+ size 14632
mathmedium2-mutualposclip0.0-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 sha256:6b899618a6dd15c98582a3f43803ff5263150c3a53d760ff1737cf56c3d4f349
3
+ size 14632
mathmedium2-mutualposclip0.0-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:bfc6e5c51ca52405eb41f433f5860a57ee0e494ff2f63cc931e1139b45c5fd73
3
+ size 14696
mathmedium2-mutualposclip0.0-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 sha256:9bbb8a4521e0df155cb957ddb4fc856f50aa8667b0b00c77ac5e9245f0f4276d
3
+ size 14696
mathmedium2-mutualposclip0.0-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:bb9f004dac7d65378dead9e59e1324a6e0f86e1b59b2092eba2429a2a4560957
3
+ size 14696
mathmedium2-mutualposclip0.0-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 sha256:1200d4db318d80aad29adeb8c23d6e4b70841947e4f992f319dd74c09a5755e6
3
+ size 14632
mathmedium2-mutualposclip0.0-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:d9bcbbcfd1e9ebf27018d7c089da7289ccc98a5a179d954d281b8e5373daed71
3
+ size 14696
mathmedium2-mutualposclip0.0-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:e2b5213d4a025f32f16434f08c66132fda8a4968b3cd81240cce644de39f4786
3
+ size 14632
mathmedium2-mutualposclip0.0-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 sha256:118ee7a55b2a3830e006ab60ce653768b6b567509359e28a5ea0be44199d3b7f
3
+ size 4998767360
mathmedium2-mutualposclip0.0-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 sha256:2e55a57dc8ff391091a7077c793d94af9aa55ac96df23cbd658fc3209ed3cfe9
3
+ size 4932808968
mathmedium2-mutualposclip0.0-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:c07dfd34aa0ce2b32acdcf8d7913d8f43e07c10c3f95863fdfdb12338c2aaeb1
3
+ size 4495462048
mathmedium2-mutualposclip0.0-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-mutualposclip0.0-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 sha256:56d511c388d7dc5a2acf15d21f3c4d76a0040706d4dc2862c571e7fec6f8a23d
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:916590835c04ed2b3ec7ada1ed2860d0912d542038f344bb10450fdca5e86f90
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:653055c9bdf6a62c11add323dc0a3adee3cc16f1434e5981b99dacf2e375ea43
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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:df9bf4d8678d0af984761368af50fd694f9b2e5f0de0c2c058bf24c857fa083f
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:66d3ec5dceda230afd25c5a9412b454a9e4faa67fd8ac7b6445f3ecef23a92b6
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:93e938ac17dd0cf9e294cd42e5e2531088f8630e4f59e6fe0fc6b7db4f5bcbeb
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:77857569c076fb5833efb064a6db4fcb3757f30421433ab78eb791264665ac5c
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:806d12365be15b4fe16802c8c1c2df0904b0baeafe4be61cbb456bb74ef7b8e3
3
+ size 1803528186
mathmedium2-mutualposclip0.0-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 sha256:15b242e0cab009584e039e858f3bf59994ae92005796749b56637c2ae169fcbc
3
+ size 1492
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:ad4ff68a4636e4f82e39b1c89fb9b949d72e2f0d457553c0a7032b8bad6b6d5b
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:89ab908272cc540d166cc9a0a85934e95eca9706861716830900bb3f841a5b38
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:98cc3e1bf35a40bbde5dec700b3c579dce5d3f21513e5e8208fd9c9bc8fb50c0
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:9d5a0915d15cc09669207efaf319517ca754160bcc182366955b49cecfed55a3
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:d625dfdbdb8f3ce770badd80c04cf765bca257c423b00b20c1ebacbf1ed728f8
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:859406df4d8e3644116625e1887170e15bfba5f922e4f75c2fcb6489a565ee75
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:207f5f08ab63e9f997c0df7e4ec9c0eec84cddaf466b2913628138b040dcd65b
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:1f8376a2d87e1d46630a2eff109e611c75bcbd302dca9c8e057a6ce27caa0743
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:5626ce21e9974c596009e5ab8a51fc7beeec797464541fb40a444b2f745ddf5e
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:86dca4cd95e18caf39d94cd25babb403dc6bed032218d8e8ff5867a16d6fe48d
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:ae3a02b0dd74e2c7bbfa831be2bd20d8367f3ecc443d20bda96312b2a0b606ce
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:b5f1c8186cc08260cf96f1468c3997c41e299c6675c6c373bcdd98e2f67f4e68
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:aa9600758654403d87c4498f8fef0afe721e09454120b9d488ba8f0c31f21f62
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:683f83dcbe2cc068c756aebc695a251f9b2671a41d73b5cd37887c020a4209da
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:ef8a16893015639b999f27d08f605d0c1d3c0c08c115c7b3bd90615dde860600
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:8f4be49a40ae908f39530e25ba3325a4bfa3a8bee5a0b06a6f64ab654ee91526
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:dbbea0137010e3b26e8b5c1d30e275f8e6c364b3697adaf3bca2f8c822e3a0c0
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:83c0d300dbaec48394b709b895bf4bd318b0f10a56248536ed63dfcdd95f322d
3
+ size 3212775159
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c25d7d77721c6320caad8e4f0c25df3062a6ab7f8d897c6ce1449346fbdb93
3
+ size 1492
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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:ed8fb1e600d034a08fb1ae21b80934417c4acdeef1ee903a24ae20c909ccfefc
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:2da2bb4041178a72945c9ae703901ad3e7b621bc3ccf39ea187bc2df092bf5b0
3
+ size 4769980416
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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-0.2/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:c5fa51df74c7d5d0245826e47194536f487b0a002510bcd387802b77b98a00fe
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:5596f63296f4c6fbe3767609f53d9d33e761a9ea717734e99738bdceac22d910
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:8b1893e0b0906a4ba5f4073467256dae53285b75c4160801dc27075d8afefe27
3
+ size 4998767360
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:6e4ce210a5f58ba403c5095d27689439e6a7f3eb23e61df9f7feeff5c1b2e34e
3
+ size 4932808968
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:2614b0804ff4ec7ce9dcfa457d6fc3f24b78b2cbca025fb18fc36b6e6a959aff
3
+ size 4495462048
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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