Hugging Face's logo

tyzhu
/
hf_model_math

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
3e01154
·
verified ·
1 Parent(s): da15303

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-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/model.safetensors +3 -0
  3. mathhard2-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json +3 -0
  4. mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/model.safetensors +3 -0
  5. mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json +3 -0
  6. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_0.pt +3 -0
  7. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_1.pt +3 -0
  8. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_2.pt +3 -0
  9. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_3.pt +3 -0
  10. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_4.pt +3 -0
  11. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_5.pt +3 -0
  12. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_6.pt +3 -0
  13. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/extra_state_world_size_8_rank_7.pt +3 -0
  14. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_1.pt +3 -0
  15. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_2.pt +3 -0
  16. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_3.pt +3 -0
  17. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_4.pt +3 -0
  18. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_5.pt +3 -0
  19. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_6.pt +3 -0
  20. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/model_world_size_8_rank_7.pt +3 -0
  21. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_1.pt +3 -0
  22. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_2.pt +3 -0
  23. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_3.pt +3 -0
  24. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_4.pt +3 -0
  25. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_5.pt +3 -0
  26. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_6.pt +3 -0
  27. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/actor/optim_world_size_8_rank_7.pt +3 -0
  28. mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/data.pt +3 -0
  29. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  30. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/tokenizer.json +3 -0
  31. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  32. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  33. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  34. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/tokenizer.json +3 -0
  35. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/data.pt +3 -0
  36. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors +3 -0
  37. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors +3 -0
  38. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors +3 -0
  39. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/tokenizer.json +3 -0
  40. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors +3 -0
  41. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors +3 -0
  42. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors +3 -0
  43. pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/critic/global_step_300/tokenizer.json +3 -0
  44. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors +3 -0
  45. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors +3 -0
  46. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors +3 -0
  47. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json +3 -0
  48. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/model-00001-of-00003.safetensors +3 -0
  49. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/model-00002-of-00003.safetensors +3 -0
  50. pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/model-00003-of-00003.safetensors +3 -0
.gitattributes CHANGED
@@ -60,3 +60,11 @@ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step
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
61
  mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
  mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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
61
  mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
  mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/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
mathhard2-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ea16b12eebddf2473be9c997adcb716220c0cd58aa566f461460189c4f9b5b
3
+ size 4063515640
mathhard2-mutualposclip0.0-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48130a7669f533aef4cb0e243d22968f3b818a495131b43282920b36a19401dc
3
+ size 4063515640
mathhard2-mutualposclip0.2-qwen3-1.7b-oldreward-4k-corrupt-0.2-step-250/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/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5cbef050241cc58be4305c0b7a6811861e4d4c9f6ea35533d2ae4485d4a180
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:3393a565ce5bf8e8a74875d003a0d1b6c32eace87e742a522af1afbde72dba54
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:9708ed0f6034ca6315d54f4bf5652ac35f692b344535884605474b8fec3d7364
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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:ddd0ae1e79ef0376767ce85e784a5bd7794ca47e3dc51ab67d31fb554607f740
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:184916ee9877fb3b00b03dfe6225617fd5daf19311af081b73819d733246a50d
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:221e913ab4b7193c41c7e820e49c4e47c43c7dae087bc771efcccfc6f21a4f9a
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:03fc9f4bc4fd8db8c932e599e5795b93e23cef610f73dbc2b0016f7747ddbd2f
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:476446d582f98cc0c4f84c02ac0feead8d749ff12c5aa8c2ff564200691cbaf0
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b-4k/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:a919122215f4ac0628eeb139dcddd4cd1384cf568e2fa03d37e433762e953ac5
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:9bb9410b4ae6247316ca0e4e62b67ab786e6bfb41df2be18dabf47da9e219c4f
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:6696779968ecc484570516f3e6147be7b547db9ef50622c15c69b4582edd90cc
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:84f8158a93d07842052a75315f1036f00cf0199159030db4cd33af373a45a144
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:3d99ad08eb7454a321ed98f750bbf6fbec8fd809ef48e53e2e88ce04c2cfbad5
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:0a77317e54650e111e885f3f532780308c4d43276b67d7b3667a3543d6ebffef
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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:f39d253268669a11f57da89dcbc14ec4d8c0437e5169df43a4b4416ab4ecf377
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:3af4b6d5095605167b8122f2f38eb6279314cc9b5e40f0be6e5d333dec398c26
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:7ab5d47e81f85297e667c8d636025d4b2d9743ab3c3b87b57bdc4f3ac23f21ca
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:5f214f1c48f7bdf14dbac4c2256c7fee548a8a65c4e0062d60b92c3732784c1c
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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:d65b96c00a019fab264b155a77ded801a74de1c9c5bf3de34203a7f78bd8c664
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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:ea37774dfd31861e6af31f6e4d6cb8cca0102c5127ab66a407d2d1212744a41a
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:80b0212e0b4d72d3ef9fed0f81c5fcf2357cdac882aacc57f980787d3b19cd72
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/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 sha256:903b636792f0395efd91e1a0ca32c7c065632089a9d2c7179fe6e8c58a30a78f
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b-4k/global_step_300/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312d70eb30c6b3a1f6108f7c10d6172a17fd44920565cd983631939c4024504c
3
+ size 1492
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:7d9125b5189fa7a01da8c3721f6cdfc440c3fc9b1bc8f326774887a78184eaf1
3
+ size 4495462048
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:608e6e455d018229013244596a38715d4df98a2eef3933824a6c21d1aef996dc
3
+ size 4998767360
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:71f85d948f8ac074d6949bd0b5e0114e5e058bf2d63cb8ba42e4051b60e898da
3
+ size 4932808968
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:3de9916c5ab2d2c55ae6631e5ba601c5ea0142e30a53717457fd703b4beb1e2c
3
+ size 4495462048
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf123f178a85ef6d50972faef86705bf783bcb2ee7b289af10a0b6c2180f9bf
3
+ size 1492
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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:e4c3ae512f78eda87cf649bd7c783a06d3255ab5c6caded768043e32771ecdbb
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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 sha256:61bb19e2687109b0328d7b950817e7493e49a427322611f7c3e84b35ff98ea1c
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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 sha256:86cd49984db16819f43f8ae0302082dfd0822b88c5aa0d0e67738816d15b16fb
3
+ size 4495462048
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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-em-warmup-0.05-rouge-rouge7-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:e8a45ca86971cc62bcd6be05f49a6fb44ed2bfbf5fefce89f7056af4bec871de
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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:bd401b3e25bc432b2c3d3bdcda7a1a031fbe7dc1b107abfd4ba7374b6697f11b
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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:bc1f0c28855b2da546143765d71be80f8fc98073cbf7ad6b17abacc6a73b6a7b
3
+ size 2919464628
pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge7-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_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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:bb1e944bbc9ad3730bc0fae46d770eeeff7c739b1322e6738b6b6a86a13c534c
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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 sha256:29fbb644322cd2a44bd52ae8f6ccee2bb8ff8fc80bb72047fec8cbe4a998cf08
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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 sha256:4ec16a4c8bf5338a491c9aacf11f3a1593d6c199a6b707e51eb2e501726569fc
3
+ size 4495462048
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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-rouge5-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:a9ad4422230ca25238231df51c7c6d19a71b7a87dd807f0728f49267237b1448
3
+ size 4998767360
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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 sha256:9458276bbeb2a8d530d62bcd3a209c51be00caeb89b33c08f3fd57f01e105855
3
+ size 4932808968
pilecc_cont1-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rouge5-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:c9c4f79caf1f8626ce705f0d95fb0f81dc1abb4c55b76d87f92f58f9bc668f69
3
+ size 2919464628