Hugging Face's logo

TheBlackCat22
/
cache_models

Model card Files
xet
 Community
TheBlackCat22 commited on
Commit
5306ce7
·
verified ·
1 Parent(s): 57d3fa8

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 +40 -0
  2. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_1.pt +3 -0
  11. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_2.pt +3 -0
  12. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_3.pt +3 -0
  13. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_4.pt +3 -0
  14. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_5.pt +3 -0
  15. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_6.pt +3 -0
  16. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_7.pt +3 -0
  17. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_1.pt +3 -0
  18. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_6.pt +3 -0
  19. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_7.pt +3 -0
  20. atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json +3 -0
  21. atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl +3 -0
  22. atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl +3 -0
  23. atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl +3 -0
  24. atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl +3 -0
  25. atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl +3 -0
  26. atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl +3 -0
  27. atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl +3 -0
  28. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_0.pt +3 -0
  29. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_1.pt +3 -0
  30. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_3.pt +3 -0
  31. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_4.pt +3 -0
  32. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_5.pt +3 -0
  33. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_7.pt +3 -0
  34. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_1.pt +3 -0
  35. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_3.pt +3 -0
  36. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_5.pt +3 -0
  37. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_7.pt +3 -0
  38. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_1.pt +3 -0
  39. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_6.pt +3 -0
  40. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json +3 -0
  41. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl +3 -0
  42. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/107.jsonl +3 -0
  43. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/108.jsonl +3 -0
  44. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl +3 -0
  45. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl +3 -0
  46. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl +3 -0
  47. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/12.jsonl +3 -0
  48. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl +3 -0
  49. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl +3 -0
  50. cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl +3 -0
.gitattributes CHANGED
@@ -1093,3 +1093,43 @@ atpo_hotpotqa_qwen8b/20260506_124901/rollout/217.jsonl filter=lfs diff=lfs merge
1093
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/212.jsonl filter=lfs diff=lfs merge=lfs -text
1094
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/181.jsonl filter=lfs diff=lfs merge=lfs -text
1095
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/146.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1093
  atpo_hotpotqa_qwen8b/20260506_124901/rollout/212.jsonl filter=lfs diff=lfs merge=lfs -text
1094
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/181.jsonl filter=lfs diff=lfs merge=lfs -text
1095
  cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/146.jsonl filter=lfs diff=lfs merge=lfs -text
1096
+ atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1097
+ atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl filter=lfs diff=lfs merge=lfs -text
1098
+ atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl filter=lfs diff=lfs merge=lfs -text
1099
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/238.jsonl filter=lfs diff=lfs merge=lfs -text
1100
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/134.jsonl filter=lfs diff=lfs merge=lfs -text
1101
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/179.jsonl filter=lfs diff=lfs merge=lfs -text
1102
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/162.jsonl filter=lfs diff=lfs merge=lfs -text
1103
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/182.jsonl filter=lfs diff=lfs merge=lfs -text
1104
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl filter=lfs diff=lfs merge=lfs -text
1105
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl filter=lfs diff=lfs merge=lfs -text
1106
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl filter=lfs diff=lfs merge=lfs -text
1107
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl filter=lfs diff=lfs merge=lfs -text
1108
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1109
+ atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl filter=lfs diff=lfs merge=lfs -text
1110
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/170.jsonl filter=lfs diff=lfs merge=lfs -text
1111
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/168.jsonl filter=lfs diff=lfs merge=lfs -text
1112
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/186.jsonl filter=lfs diff=lfs merge=lfs -text
1113
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl filter=lfs diff=lfs merge=lfs -text
1114
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/171.jsonl filter=lfs diff=lfs merge=lfs -text
1115
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/132.jsonl filter=lfs diff=lfs merge=lfs -text
1116
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/135.jsonl filter=lfs diff=lfs merge=lfs -text
1117
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/223.jsonl filter=lfs diff=lfs merge=lfs -text
1118
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/180.jsonl filter=lfs diff=lfs merge=lfs -text
1119
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/142.jsonl filter=lfs diff=lfs merge=lfs -text
1120
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl filter=lfs diff=lfs merge=lfs -text
1121
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/197.jsonl filter=lfs diff=lfs merge=lfs -text
1122
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl filter=lfs diff=lfs merge=lfs -text
1123
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/204.jsonl filter=lfs diff=lfs merge=lfs -text
1124
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/235.jsonl filter=lfs diff=lfs merge=lfs -text
1125
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/172.jsonl filter=lfs diff=lfs merge=lfs -text
1126
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/210.jsonl filter=lfs diff=lfs merge=lfs -text
1127
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/175.jsonl filter=lfs diff=lfs merge=lfs -text
1128
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/191.jsonl filter=lfs diff=lfs merge=lfs -text
1129
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/133.jsonl filter=lfs diff=lfs merge=lfs -text
1130
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/164.jsonl filter=lfs diff=lfs merge=lfs -text
1131
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/193.jsonl filter=lfs diff=lfs merge=lfs -text
1132
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/173.jsonl filter=lfs diff=lfs merge=lfs -text
1133
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/188.jsonl filter=lfs diff=lfs merge=lfs -text
1134
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/224.jsonl filter=lfs diff=lfs merge=lfs -text
1135
+ cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/231.jsonl filter=lfs diff=lfs merge=lfs -text
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:9887fb9855e05264d3c726eb65eddeab7e18c53d7fde3a3e97f15512533653af
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:ed16a8eeb716045b1d5e340e5b092cb348c4130394c58f5028089ecf4ce98e1f
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:781b66d00559c781b19ee3e78b0eed2285359f085089841d5981fd2e983f2711
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:1b559e560a1144b0b5ab5c95afcbe202fcdf640230dba332b359e0066b7632af
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:f83c10449771e26072bede3d467713ecd7e70bab52e7b394ecab4ff0abf46dce
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:9555d4f192660933e164807d87641992b0d03cf16ee5c29ee322a96332d100a3
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:2cc792dcebd6e1928afb4b332ebf0f56adc55764695699fa6ebb9df3b4007612
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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 sha256:211415a6bbaf94c6b73e6ea260de303b2f6e2715a6385d4016867e56203bdde6
3
+ size 14632
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:a645461944defd14762f11318a2dccdffec4658187315eae67eaf64c2342e99c
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d61612ebaf332f00ed18f49159bcb0df6f499b56294313822f3c1bc480ebf9b
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:e74f601054e94607eb051ccf147865af74858bcee8ffc2a71ddb1956a474cacd
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c857268e687a609ead7e57810f8d25237a364da8e8f7e97d07894975fa4fd28
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1ca6ed56d60dfcdd620ee80a0e1758c2b3df5d5ce3ced87173ac743a10dc79
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:caa3e21e20643bfd6b6f28c2a9851a6f1f9c650ebf953d322860113f40278bb6
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511beced1ce2464294a293ca53c04dc8cd3cf8a01b9c25d068964601449aaa81
3
+ size 2205945402
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7653b8d348cd77305493e160300abf5febeff18c2a0d9704fef840e894d1c9b5
3
+ size 4022501290
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/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:a0762d44b21a63bf9301094fbe06d55c08d7e577db7f9ae9ee6ea3a9c895bccc
3
+ size 4022501290
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7beaf3b7da1d2ad5971cd524d9b47101da83009cb78deb703b9005c1e12989
3
+ size 4022501290
atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84dbcef0aecef645dfb4e94e1ffd2908c9ad9d867942a8a0f7b2e91d7852dede
3
+ size 13025576
atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b6c77312795ee2924cd1bc32daa1ac004b2a58ea93e98a4367f9245b48572f
3
+ size 14556140
atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039ab2bd03c8c27616dd48be698cb3e5785ae6d52074564c17438e86faa203a0
3
+ size 16199491
atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a49f82d45ac8313322012a509e1ec4a97c55c724e6c3e5f4b6bc3637041486
3
+ size 14373320
atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc81b02cbade55a7eb5fbbeb7892655ff497ad6195f81b36c5f59eb96b1d2a21
3
+ size 15577226
atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e21fbdba6b8e0526751d2586c1578e99e29f191fa80cf527d4cf9dd9f1b6d8
3
+ size 14018926
atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63ecd648485d70f0d91e9aa6b9e8aa2502417cc87fcfa124ef4104bc0f8356d
3
+ size 14022371
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:89db08bc883cddac8fcb3bdfcab120ef797afafe4ad75334957b127c37487684
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:82b05b2022e827f4a85968aaa651abd482d3bbfd6526a900ea1ffe46575e5e10
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:197fb0755f3933e70ac87f0dec82a2c7873f17914a6353998bcaf62bb8eff664
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:16cdd077d114054b0fcd03a6cecaa2ab6957f15ec1c2c6a17a8e9692f18756f3
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:96481fb12720acd815c7c0054ec2954f117b9900d24420d5aec2c27eac2e1ae2
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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 sha256:6a0d54ace654dd1813e2686f4ebcce2faf67a960a9539d4f4a84162224c2fddf
3
+ size 14632
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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:eb7437b6f71610587a8bcd123a8fae5f04346e1aba517535a5a927e9a15dda3a
3
+ size 2205945402
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:926b4e1c9354396c9fb9cfab58f9f976291a85d535bfe02337dac5b4355bd75c
3
+ size 2205945402
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6706b3ecd98ce4f089768cb6dc454b6fd4c615f5ab9d8d98750de32328e651e4
3
+ size 2205945402
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/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:c34f18e45e3c712f62213c7961c0fca41e2ff16739b75d2823d585933b711b23
3
+ size 2205945402
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e15c3d5f75051908d0d1aba0ca7e01e17b1eaf90e86abd6d4534e581a34b4a
3
+ size 4022501290
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339e1635f0707bc1753958d8fc1ab8ca3f2bbfbb94407ba69a0a6ae5ac259e7a
3
+ size 4022501290
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca22ce6ac041003abc9e47322fe9d98d210e1e729cefdfe9096cd39e2dfde2a
3
+ size 13535161
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/107.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c932cce7ea88d8bdce9196d434f07724db196212d38963c665de2075436ec02
3
+ size 15082902
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/108.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a46fd124244fff4e8bffc74bc0aec2090d4ae97c65c3a21876e11319f9a3d5e
3
+ size 14942217
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d015f9bb3969751938eb173767fcc8a87bd986f85df8e5655c0d637bfbacbb8a
3
+ size 14840746
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b723303dc9c12c86832f9a055bda0d03e91b017d9d8491743c131b19daf314e
3
+ size 14051384
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6bf663846885a30fbdab586d5e9b0c78e4cbafd0cebae3c60f5a6187ba5d7e
3
+ size 15377466
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/12.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e59870b9708a2ef4dd1667d7fa1f1583ae6481dc9fe54673e5f52048ab97907
3
+ size 16613570
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc81fb0c8de2e8caabc00da62398c92a197d456a92482dc4302caea370c585e
3
+ size 14371794
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e249ae924c7b864c3223bf91a8f9aef9f72a9875f1526169cda46124806219
3
+ size 13800753
cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8023cc833b1348c498a108b21aed600e4f8adce9b3bfce5329a989dcc9cfa66
3
+ size 14937384