Hugging Face's logo

tyzhu
/
hf_model_math

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
e60d134
·
verified ·
1 Parent(s): a2c4937

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 +8 -0
  2. mathhard2-grpo-qwen3-1.7b-4k-step-100/model.safetensors +3 -0
  3. mathhard2-grpo-qwen3-1.7b-4k-step-100/tokenizer.json +3 -0
  4. mathmedium2-mutualposclip-0.0-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-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt +3 -0
  6. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  7. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  8. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  9. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json +3 -0
  10. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  11. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt +3 -0
  12. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  13. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  14. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  15. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  16. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/tokenizer.json +3 -0
  17. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/data.pt +3 -0
  18. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_1.pt +3 -0
  19. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_3.pt +3 -0
  20. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_4.pt +3 -0
  21. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/extra_state_world_size_8_rank_6.pt +3 -0
  22. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_1.pt +3 -0
  23. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_3.pt +3 -0
  24. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_4.pt +3 -0
  25. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/model_world_size_8_rank_6.pt +3 -0
  26. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_1.pt +3 -0
  27. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_3.pt +3 -0
  28. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_4.pt +3 -0
  29. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/optim_world_size_8_rank_6.pt +3 -0
  30. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/data.pt +3 -0
  31. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/model-00002-of-00002.safetensors +3 -0
  32. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/model-00001-of-00002.safetensors +3 -0
  33. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/model-00002-of-00002.safetensors +3 -0
  34. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/tokenizer.json +3 -0
  35. mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/random_state.pkl +3 -0
  36. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors +3 -0
  37. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors +3 -0
  38. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors +3 -0
  39. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/tokenizer.json +3 -0
  40. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors +3 -0
  41. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors +3 -0
  42. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors +3 -0
  43. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/tokenizer.json +3 -0
  44. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors +3 -0
  45. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors +3 -0
  46. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors +3 -0
  47. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/tokenizer.json +3 -0
  48. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors +3 -0
  49. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors +3 -0
  50. pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors +3 -0
.gitattributes CHANGED
@@ -45,3 +45,11 @@ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step
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
 
 
 
 
 
 
 
 
 
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
48
+ mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/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
mathhard2-grpo-qwen3-1.7b-4k-step-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91010ca819070628c7bc2f2f608035f1501ba529461bce09f4582cdb9db79320
3
+ size 4063515640
mathhard2-grpo-qwen3-1.7b-4k-step-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
mathmedium2-mutualposclip-0.0-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 sha256:992867e9821a253236805cfdcfb0704e579adc0703438bc32a8013b9e3435bc6
3
+ size 14632
mathmedium2-mutualposclip-0.0-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 sha256:9bb138fd25171ad6d128037d07be43c57f8165e36cb6140da796e3d707705e5e
3
+ size 14632
mathmedium2-mutualposclip-0.0-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 sha256:743148d0a518bcbc54292c698e5f9e4ce8027722e14cf452471cb33bd79d49a4
3
+ size 4998767360
mathmedium2-mutualposclip-0.0-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:bf908dacf6705d257d03b1f61bb8bb0e09baf99f01d1443dd63484892004e129
3
+ size 4932808968
mathmedium2-mutualposclip-0.0-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 sha256:6ed581ad516b279565981378d7ee7ee7b79171c1d5f9759a5674cba7ebb083c3
3
+ size 4495462048
mathmedium2-mutualposclip-0.0-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-mutualposclip-0.0-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 sha256:3259d7f911b83c67a5275b68f453a78c1d2212c56083817e4527983cce67a853
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-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 sha256:980857611402274d9bae2c62c166224fd7c51a7a06e01de16e06af1d7554ee94
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-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:f9bed3a6ee6c40fae451cd3c7824447748646191950873f1597a1dfb080100b1
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-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:c3747dc4d48f10d3247cd1c6d185bdf9c6d5fbaeaa482502a55a7fc20bc02665
3
+ size 4998767360
mathmedium2-mutualposclip-0.0-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 sha256:66266fe16262dbbded13f1aeec593f266fd0033cdc919454eb05a155700c29ba
3
+ size 4932808968
mathmedium2-mutualposclip-0.0-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:da5dffd3991c8f414d8afe3e447599121865b7496f31a461d7a5393ca9525b97
3
+ size 4495462048
mathmedium2-mutualposclip-0.0-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-mutualposclip-0.0-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 sha256:80905c80177b8dac7924e4499bb593196cba24fee0013f6f28089c0e28a55eb9
3
+ size 1492
mathmedium2-mutualposclip0.5-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:e4a434f32f69e38311bd68c37d840f6734f925181dab3e88e786e79af4c36f1e
3
+ size 14760
mathmedium2-mutualposclip0.5-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 sha256:9ce2963ff99c06d4610f89af7431bc4c53bc8d2a9af981561f90a854796bbb19
3
+ size 14696
mathmedium2-mutualposclip0.5-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 sha256:3b601ee254c3732d86b5e9ad5e5fb165927c31d0b1fcaf2d6f5e7ec625c23b53
3
+ size 14696
mathmedium2-mutualposclip0.5-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:a62afb11bc86fce9c8b0d999d970bb9c6298fb1d33f0752a581f25d825deec65
3
+ size 14760
mathmedium2-mutualposclip0.5-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 sha256:8e03e4be48abde3073aa84752897980cf036f8204818ce9077105b863f3fc151
3
+ size 1803528186
mathmedium2-mutualposclip0.5-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 sha256:64c0ccd4fb21c80cae54d53b08b7f2ea9e8f60b8f5d87f0cd5c2f69119893f29
3
+ size 1803528186
mathmedium2-mutualposclip0.5-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 sha256:66aabf9822550b7861dffdfaf0ded777b4a067b24a263b8207a83eba48cac63a
3
+ size 1803528186
mathmedium2-mutualposclip0.5-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 sha256:584e43bb61bd591ad02a47a4bf21f634216a0d0532634ce8853bdca9060c59b0
3
+ size 1803528186
mathmedium2-mutualposclip0.5-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 sha256:826173794c1462c11c88eb4a9ce817dfd1546797d5940c2a6b34159d1f96e1d0
3
+ size 3212775159
mathmedium2-mutualposclip0.5-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:fb2727ab149b180075f74af075723ec2d0b465c9bfa8a798f80fdb992bb99037
3
+ size 3212775159
mathmedium2-mutualposclip0.5-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 sha256:98162afec6722951303c3fc1ce68eea96e7299372449ee6338360c7d2ce87a0d
3
+ size 3212775159
mathmedium2-mutualposclip0.5-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:f0a2efc1e702d818f1380f672012ef1fd4b99e5515814b709241f20b0659dc9c
3
+ size 3212775159
mathmedium2-mutualposclip0.5-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 sha256:0a9a5343c05377b06534adffd6adb01f34763c07ccf76276b2090629a5523063
3
+ size 1492
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_100/actor/global_step_100/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086158b5538eca111e7bfb6200f1a9692229371ce559c991cb2515ba53b748db
3
+ size 2111719976
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90cd2b52e6af87e7c21f5e3cd1b04850eaf362a4424530444cfde9de231cf6ca
3
+ size 4996670464
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ef2a764aaf15213949fa3000966dc7fcf75b7c4481c75791e2527f974f0b50
3
+ size 2111719976
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/actor/global_step_200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
mathmedium2-mutualposclip0.5-qwen2.5-math-1.5b-oldreward-corrupt_delete-0.8/global_step_200/random_state.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa16f5bd60a1e1c60b5150671b96e30d4d670310cbe4a6e5eb00f2b0b387205
3
+ size 12846
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e556a6861d3168ce979ea9ef70c191eb01991b4a3b17156c009b580a32db176
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec715f9b572ee7e4978bd7f4531f441f671fbfcf6890975a658a68f73b30b65
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48272d722876908736addd29a1a62b381edd76eece05e236f0dbb3018e678234
3
+ size 4495462048
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd104338c78196f3f1d5ad85ba4b88cefc0b80e18a12b24ab3d910a5c93775a
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7e7275609977c9a1ff8fd7b96044bce00d27600a7fc855be768a5258cae819
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a8ce7d103edc3c38337ac87a63afb8b3824d74833ee97a7a304a7a250b82c4
3
+ size 2919464628
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463b39ebb21b685c68f9e3d7ea11d87d508a1919ecd6b5d7c5d63dc406ed98c9
3
+ size 4998767360
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5bcc96c231573edf69ae62f5388527982228a8824b9bdea23f9ad00886960e
3
+ size 4932808968
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d2938b4787359ce9e4a21e3d407813141ed1c7c50b7198c4db32a0ad1ac7e53
3
+ size 4495462048
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/actor/global_step_300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2882c27152cc79b3f7949c172f6cda1a2b5b692ce13c03e3884afe0434afa8
3
+ size 4998767360
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606f1a9d5eb1df6a6e038aa04aa983a5e498f270008910f0639459623fc4fb15
3
+ size 4932808968
pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20eaf8c3bb3c13fda4eb25152cbaf86cf745b6dfadddf69708e91cb48c6430b
3
+ size 2919464628