diff --git a/.gitattributes b/.gitattributes index de3b821f3a9766d8ba7203844b8e2271428f5214..5e09402ffa5df891483eef7880db69ffbb4c2594 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1093,3 +1093,43 @@ atpo_hotpotqa_qwen8b/20260506_124901/rollout/217.jsonl filter=lfs diff=lfs merge atpo_hotpotqa_qwen8b/20260506_124901/rollout/212.jsonl filter=lfs diff=lfs merge=lfs -text cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/181.jsonl filter=lfs diff=lfs merge=lfs -text cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/146.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/238.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/134.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/179.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/162.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/182.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/170.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/168.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/186.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/171.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/132.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/135.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/223.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/180.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/142.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/197.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/204.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/235.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/172.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/210.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/175.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/191.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/133.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/164.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/193.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/173.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/188.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/224.jsonl filter=lfs diff=lfs merge=lfs -text +cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/231.jsonl filter=lfs diff=lfs merge=lfs -text diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_0.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a6df367912638b95338b68ebbb5fdc8247ef3ad --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9887fb9855e05264d3c726eb65eddeab7e18c53d7fde3a3e97f15512533653af +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_1.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..63ba3894a4e8bc277e38b8663351c8da9e6e48dd --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed16a8eeb716045b1d5e340e5b092cb348c4130394c58f5028089ecf4ce98e1f +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_2.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f9bbc3f3c19152ee72a73f4a0122eed6dacec4c --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781b66d00559c781b19ee3e78b0eed2285359f085089841d5981fd2e983f2711 +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_3.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..82215c9357e90808e1edd880a736be13ea34d8b4 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b559e560a1144b0b5ab5c95afcbe202fcdf640230dba332b359e0066b7632af +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_4.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab086ce5a287313c6c241b51d53b95fe9acb71f3 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f83c10449771e26072bede3d467713ecd7e70bab52e7b394ecab4ff0abf46dce +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_5.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c2239114dd337fc11a620f9da54d17ec72c733f --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9555d4f192660933e164807d87641992b0d03cf16ee5c29ee322a96332d100a3 +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_6.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f2f14f4cdbdac8443fddb99d978a3c49aa07832 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc792dcebd6e1928afb4b332ebf0f56adc55764695699fa6ebb9df3b4007612 +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_7.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..35b8a0d4be86e60fbd1ea29e9b9d901e6667c2e3 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211415a6bbaf94c6b73e6ea260de303b2f6e2715a6385d4016867e56203bdde6 +size 14632 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_1.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..315331b57cd340746a3f8ae7210f400d423676bd --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a645461944defd14762f11318a2dccdffec4658187315eae67eaf64c2342e99c +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_2.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a6da0be6e10076880de0b82f98f47126e460bf3 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d61612ebaf332f00ed18f49159bcb0df6f499b56294313822f3c1bc480ebf9b +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_3.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..098b17f021fb9f8656aeff2736dac4be7d49ab79 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74f601054e94607eb051ccf147865af74858bcee8ffc2a71ddb1956a474cacd +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_4.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a90949ae4ed259e4877377c944a9d04c5a39f6d --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c857268e687a609ead7e57810f8d25237a364da8e8f7e97d07894975fa4fd28 +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_5.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..b42745a2289f9b4ba4a13dc6aa63202d2ba10092 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ca6ed56d60dfcdd620ee80a0e1758c2b3df5d5ce3ced87173ac743a10dc79 +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_6.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..75fbcfb7f8978b154f5fe5a9a3f277d54ca5812b --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa3e21e20643bfd6b6f28c2a9851a6f1f9c650ebf953d322860113f40278bb6 +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_7.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b752665486c3941a12f15a1801534ae2513e942 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511beced1ce2464294a293ca53c04dc8cd3cf8a01b9c25d068964601449aaa81 +size 2205945402 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_1.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..92d8111656e958845b35343e5e72352391c1854d --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7653b8d348cd77305493e160300abf5febeff18c2a0d9704fef840e894d1c9b5 +size 4022501290 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_6.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..de4ebc926f1247e9252e286a1889c77cdbbb7b45 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0762d44b21a63bf9301094fbe06d55c08d7e577db7f9ae9ee6ea3a9c895bccc +size 4022501290 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_7.pt b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..260cb96800830eb79b91c5d42e024c2f5fa0db81 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/optim_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7beaf3b7da1d2ad5971cd524d9b47101da83009cb78deb703b9005c1e12989 +size 4022501290 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/global_step_250/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl b/atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f0d5e9ce1f30cd7b0095f4837769c127f0a34ae9 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/rollout/223.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84dbcef0aecef645dfb4e94e1ffd2908c9ad9d867942a8a0f7b2e91d7852dede +size 13025576 diff --git a/atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl b/atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a888c1b4a176b502830cac512ee7dbc1f856de3 --- /dev/null +++ b/atpo_hotpotqa_qwen4b/20260506_102808/rollout/246.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b6c77312795ee2924cd1bc32daa1ac004b2a58ea93e98a4367f9245b48572f +size 14556140 diff --git a/atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..79e6e417cd916d82a70525c2aa2cb8918a0e6378 --- /dev/null +++ b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/213.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039ab2bd03c8c27616dd48be698cb3e5785ae6d52074564c17438e86faa203a0 +size 16199491 diff --git a/atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..07cfb5a32e6de402211bd89190e4cf91c1b6676f --- /dev/null +++ b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/216.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a49f82d45ac8313322012a509e1ec4a97c55c724e6c3e5f4b6bc3637041486 +size 14373320 diff --git a/atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cd197b115f8f80fe39d2595cd6884d0eb2c7e45f --- /dev/null +++ b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/218.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc81b02cbade55a7eb5fbbeb7892655ff497ad6195f81b36c5f59eb96b1d2a21 +size 15577226 diff --git a/atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2598eb141c5399fd83c02ac78fa192da67eae9eb --- /dev/null +++ b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/219.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e21fbdba6b8e0526751d2586c1578e99e29f191fa80cf527d4cf9dd9f1b6d8 +size 14018926 diff --git a/atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..05b88599a8705e42ef08bb1b80b2a03fcc3ea17c --- /dev/null +++ b/atpo_hotpotqa_qwen8b/20260506_124901/rollout/229.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f63ecd648485d70f0d91e9aa6b9e8aa2502417cc87fcfa124ef4104bc0f8356d +size 14022371 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_0.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d1f94d3ae7f4dfb0ca45ba4ce403ddcbf0d0895 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89db08bc883cddac8fcb3bdfcab120ef797afafe4ad75334957b127c37487684 +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_1.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ab072a9f57703ef1ba4a5c477a28e50af8eb655 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b05b2022e827f4a85968aaa651abd482d3bbfd6526a900ea1ffe46575e5e10 +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_3.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..cdcb671b9e771f615f5e82c3ecf6ec44d214fb9c --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197fb0755f3933e70ac87f0dec82a2c7873f17914a6353998bcaf62bb8eff664 +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_4.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0de20534b27280bd8680f28b78772a7346fe226 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cdd077d114054b0fcd03a6cecaa2ab6957f15ec1c2c6a17a8e9692f18756f3 +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_5.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad1e908d8126a49443f927ea9c73a936a1d18e00 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96481fb12720acd815c7c0054ec2954f117b9900d24420d5aec2c27eac2e1ae2 +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_7.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..84aba0913f45a7c1a85f06666c8c8b2527fc3054 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0d54ace654dd1813e2686f4ebcce2faf67a960a9539d4f4a84162224c2fddf +size 14632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_1.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..c234538416aa28aa36a746392f98655c747d07df --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7437b6f71610587a8bcd123a8fae5f04346e1aba517535a5a927e9a15dda3a +size 2205945402 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_3.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..674ff2eadf635a0fe54100e29aeccca1f3725a70 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926b4e1c9354396c9fb9cfab58f9f976291a85d535bfe02337dac5b4355bd75c +size 2205945402 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_5.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a95661c9eb20f1381380af7305c3f5e87d6408d --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6706b3ecd98ce4f089768cb6dc454b6fd4c615f5ab9d8d98750de32328e651e4 +size 2205945402 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_7.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..73126f1a11428ab14bd483c4b2370ab5e97aed4f --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34f18e45e3c712f62213c7961c0fca41e2ff16739b75d2823d585933b711b23 +size 2205945402 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_1.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cea9a401bddf81b7747be55bf7193f7400a9ae2 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e15c3d5f75051908d0d1aba0ca7e01e17b1eaf90e86abd6d4534e581a34b4a +size 4022501290 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_6.pt b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..52556fc2aadf31259636c37fbc00c4369ba9b0bc --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339e1635f0707bc1753958d8fc1ab8ca3f2bbfbb94407ba69a0a6ae5ac259e7a +size 4022501290 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/global_step_200/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..27a0ccdc0ae5426783a5f751542fa98df50c81cb --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/106.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca22ce6ac041003abc9e47322fe9d98d210e1e729cefdfe9096cd39e2dfde2a +size 13535161 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/107.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/107.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9fb13a016e5039517c906a2f7fe060266a93455a --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/107.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c932cce7ea88d8bdce9196d434f07724db196212d38963c665de2075436ec02 +size 15082902 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/108.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/108.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..40b7dc0f1ed5aada02af9086dd33905f773d6846 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/108.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a46fd124244fff4e8bffc74bc0aec2090d4ae97c65c3a21876e11319f9a3d5e +size 14942217 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1381accd7fc42e3639b274c4d222b1d5cd0e0671 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/110.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d015f9bb3969751938eb173767fcc8a87bd986f85df8e5655c0d637bfbacbb8a +size 14840746 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dcccb6b47ed891d8c39bf0f6e1bf3c56ba939dff --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/112.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b723303dc9c12c86832f9a055bda0d03e91b017d9d8491743c131b19daf314e +size 14051384 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fb2267e7d753a362de0adc029d40c7de33241135 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/113.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6bf663846885a30fbdab586d5e9b0c78e4cbafd0cebae3c60f5a6187ba5d7e +size 15377466 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/12.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/12.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d957cb93979b8dcab6c861595409399ac7e094c3 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/12.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e59870b9708a2ef4dd1667d7fa1f1583ae6481dc9fe54673e5f52048ab97907 +size 16613570 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c25142b2c1f7e7104982c7c5d3c85706e86a81cd --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/123.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc81fb0c8de2e8caabc00da62398c92a197d456a92482dc4302caea370c585e +size 14371794 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e7151c412eda5bc4d310eb0982866a981804521 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/124.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e249ae924c7b864c3223bf91a8f9aef9f72a9875f1526169cda46124806219 +size 13800753 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..37ba35ed4c7eeb3f0b3d6f4ecc83f730de759a54 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/131.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8023cc833b1348c498a108b21aed600e4f8adce9b3bfce5329a989dcc9cfa66 +size 14937384 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/132.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/132.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e07026aa33876b3450d469eca1dec985be439272 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/132.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551fb3ff3d0e06a2f334d627eaa25363ddd6364a5d9fcc6c9063f83057c88007 +size 13815284 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/133.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/133.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e2afe6f95b54e047d70894be629aa2e12dcf1f00 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/133.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791f98cbb380cb316268b52af06a24185d9ea35cd9514db5e27c4de2b6889b55 +size 14491983 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/134.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/134.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e81d0eab67a34ff01ef2c94a0a4dcd82cf9133e --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/134.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afec6c86286494bf2e15668b2b23b9b6d962c3a8f01cba23f64a16e5e36ed159 +size 13473849 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/135.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/135.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..90da1b55b45236e5cb96e4fa32415a164984c072 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/135.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1304760f4dfe566baa4a17e095bcf6142b782705cead4e2dc3e405cdc4d86c34 +size 14001929 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/142.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/142.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f6f4ff989b881d6b206e9f95d46a7e04f46e8b7a --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/142.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec6eb40e89a918b912d7075a7c99a0e906deba83bf0b6129891d7db7594d39d5 +size 14175632 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/15.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/15.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b995067eacfa7d53a7658d2d00972a78a8d5c843 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/15.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a5c827b6e770ff9d04831e60a88e4b4b2ee4e3e2d92a06be7f0041bff73bad +size 14666731 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/16.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/16.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..9d11bc361ee6522dfdc728d710878e7c5bd57bc8 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/16.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137b3e7cc97d908cafb30defb4eeb6625ee7e3792b7dc63c0dc2ff09954781c4 +size 13837937 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/162.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/162.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6a61157d206ea5264f9e133b465e8bc5656a0842 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/162.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671aab5d09f41eed319797a81d711ce01eb3dbe987e82e29808664b22ea94bd6 +size 12230726 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/164.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/164.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0d0905776e22f61d28aa3efca7632d48b9938c74 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/164.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662c2fe747485c7bc6294588ca299e5616dd24a53cc01678dd48796363aad12b +size 13724565 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/168.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/168.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..bf692336f009642e8bb2ea865ad3991f6fd06629 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/168.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2b4212fd5836a688441beb66b1d5e67ebe05f9fda399d9a0e0844d19344706f +size 13395698 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/170.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/170.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7ca726266201d98597eb2d1e1e9c857452aa8ff1 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/170.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b43b1ed4a6c7537d166b29530fa2f7dd26c95de8690f98bec4a7bef98b852f +size 13799402 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/171.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/171.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f4f1142ce46b9b99567d1e08e4c82959fdef8d90 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/171.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe78439347db2b2fc962791ac2146b98bc4ab6e611a755f1c2da0a07d7abd656 +size 15352316 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/172.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/172.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5800e4c1a21572f1060c8715450de91e740c2a22 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/172.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bab1ccf086649e6d47725e0b9ed82d57e3d3e6b92eaff7d01d923f2c03a66f1 +size 13634338 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/173.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/173.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c4fabd1dbb9fc6d402df9af153699bbefc58ead1 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/173.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16c0cb77e0ea8410a1644564299f8c6d8195a80d71a3c3bd945daa43b1cc7af +size 15199696 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/175.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/175.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..1b21e49d853619c2aca583afd5879a3bed5b5c6b --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/175.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6064901d0e1a37af243dbbb33ff7c92b100ad7f2b491d740a06c2879829002 +size 15263791 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/179.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/179.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..652293fb77970cecec1708ab6907925798e14555 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/179.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0c48bb5cbe7a9f2975d3459df4bdb48ed4ba6390ac74ffc432bd52d659cefd +size 15187252 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/180.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/180.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3387d5d4e038f795d4ec5f65934c6e99739b7dc3 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/180.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238cffe119db89c3bffe99477a4a732278b58c2f49bed60ec7aa6b0d60e4be58 +size 14583393 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/182.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/182.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..2b65633638408ce072df029661143aca8d3f22f4 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/182.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f814d5835f5e8d6f2f2ebfcfa31de8f681767f45fb0d9e7821a95baf61b0be5a +size 16891183 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/186.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/186.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c714b06694ac1bdec758418b09691fde37c933f8 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/186.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01de520c621b890e7a1b91c91b7f72ead9af5b316a90d34020b0d051ce74bb51 +size 15447196 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/188.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/188.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..601726793b470242366c71cb510b28ca0c2f2be4 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/188.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d81a54bb94b07330948cbff1a6d6e8680576faa17c31acd1a3d823477f2dfa +size 16253603 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/19.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/19.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a1ccf4074f5841ae5f9990e4f60c7c9b793c88df --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/19.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1dabc0b6422598f28f00118db9964e6afe85f87235397436959f4a636c949d +size 14397605 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/191.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/191.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c4600e5751b6ab31c1c2619c37ba4909b902052f --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/191.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:696d5ce88362ee73a5da5053e3352377fb3f229e8419ef16711e3fe2f4d71d89 +size 15821055 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/193.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/193.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..efc4cbb673ebd3520a8cb3b9329d11196323e179 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/193.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d917cfa6eef0aac6ab840aa4a1559460984d6e364e1d87716093911e2a081ac2 +size 16499227 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/197.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/197.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..60c2a7f9f8a4e40910a3344d45464769ee9695e9 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/197.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7792722b2d4e5b6c3e449fea8e54c803513da73978bf2f05682ea9b902892360 +size 15855519 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/204.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/204.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..cf5dbf09de9c4eb7847b79b8462195f8fbe8546d --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/204.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eeb272a2dab0c8b7e6739c30b8bcdd5597bbe27ced1535b8440b32dc657b06d +size 14282956 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/210.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/210.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d7127f8cdc1e0813c1dded8d265f39c288d789a5 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/210.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f56a17aa01f0c005efd2c82e5d8494095f83520daaeaa0da20c42c11f1a44e8 +size 14923576 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/22.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/22.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a52a1e7f8b5dcaed78d17dc5cdb33bee27cd435 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/22.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9261ca7a3881170b7e563779d3707bbfe998ea415b39badf65cdb1321c9303c +size 14127932 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/223.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/223.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..85e4b2d0eeeb289d7fa7642d116114c1eabf2a8b --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/223.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9aadd45e2d2902177c476c38699f9c1de169cd80e85c917dffe19608027f28 +size 14188708 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/224.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/224.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..dfbd25ce7acb0586f8b5e5ed6840620feeb38896 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/224.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c586d1fc48ababe99b382c4bfff6699830b71c5f083be628c150ef6f750e3f +size 14678162 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/231.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/231.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ad312151195f1a3324425fdbb356a2c9fa30ffba --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/231.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bb6f599037c153d638aea366780418eea0bbce26565515d5e1bd55c0ec8d9f +size 16481650 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/235.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/235.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..32a9648832ef56569f8271864a00f27f27259207 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/235.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba2891b9738a086f8e533d2d7ede4f280cd8d356e2a62a294b1621f6a00a4b6 +size 17872236 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/238.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/238.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7bd69239ebe634f942e52bb55114ac1290c1b563 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/238.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3e7028aa24144fe806673db3fd7e7b31ddd03eed19e347921ee684ad45b872 +size 16088674 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/25.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/25.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5d62fa2699c9c4bda369834de95ced4b78fb76a5 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/25.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ee9a696570f84e421677b9bf17b41537e261e53b11d86a981c50b830fde7525 +size 14968194 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/32.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/32.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..0a241d2cadf83d00d2ce8f3ef3581d63b4c13db3 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/32.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f863bdd6a8c6849b4fe4a0ea40cf6b1be31942a2fa95e444d36f2177792e8e +size 14554843 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/38.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/38.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..ab5d19a11c40922a522c2a33125ad50a1987c25e --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/38.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4678554f7d77def036acb2f8645ebb6dde3625c32b8a5b59b6a118b28c52db90 +size 14918508 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/39.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/39.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8b079f1d7c01efb80cf2de30f5981f41bd7c45db --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/39.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2d04c3f065913e848fe8b31b4a2143784f275324ea89e1f2c81b5693f56d69 +size 14308243 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/44.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/44.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..19d1169c603bb2c2635b4430ea5f222a1c8a43dd --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/44.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d952df660cd6c586aadb75017615dbd2dbe5586797f9fdcc6fdf896422301693 +size 14579344 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/5.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/5.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6f8f0365cfaa8f734054e90c1a07ca4d7fa8bc66 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/5.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f27e0ccb721b999da183105418d4af1adb466190a1de4330fdbf419bcfc688 +size 17664686 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/53.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/53.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..49f1258bd7573ceddb9f5afc520ba4edc1df357c --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/53.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d875dc7de05a7118f003e495b108a876925c7248d2c460140e63eb15724165ba +size 14307499 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/55.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/55.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3bc3c9f3103591f95c01f38821a8329a8dc3df43 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/55.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca52105730eaf1eabb3d25b678fa26ac6e860940f38c4196146e38086b79d92d +size 14762149 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/59.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/59.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..578e1d8d9ea9958cb02763e5fc83d2cd05cce9cf --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/59.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24b57636c56ce5e45dcddc7325f5598a2083b71204055865b3709f384a0f5da +size 14284828 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/64.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/64.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..f0d60705646e853d355fa921d6bd21d7fb15d153 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/64.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54fe9b51066820a688ca33a6a598839ee079f199329d4c5ea2b414b13477246c +size 12772856 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/67.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/67.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4e5c829e6f526987b57480b1da2df19010f3b60c --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/67.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a61c5f5119cd4fe39e29bdfecf2deea1dc859d972e524b3a69b10dfba07ecb +size 14939099 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/73.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/73.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..c2de4662a0cd5a9b0ff73012676a7854b4022e1d --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/73.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6083fc6d851b1e1c51712b1a9e053a74f03452aee894c6df97d8cd28768df62a +size 14572994 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/78.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/78.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..3362bbdc231d74dced064d5fd89c8cc19c8c5b9a --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/78.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783199707f37f3a2aa361211a250166ad8153660ac466792011c02756305168a +size 16935122 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/79.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/79.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d9059dcfc99ccd67038bf9a27d4effd74b2fa1ab --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/79.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23993c9418e8279a440b68c3f065e3e3d2438da011ef59300319a77819dca27c +size 15685777 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/80.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/80.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..49c9bb5402e78b98c6e4b7c44c4735da1ef37a9d --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/80.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590f85c3ce810e55c2ec291b42af845ddd74c8efee09a517935b94093606012f +size 14394873 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/83.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/83.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..731e53060d62ce95010f5be856af463cfabf4420 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/83.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48304705b93c9133f59e445d3d0ddf5d1c77ed1cde3ec707f3f2a4fcad579097 +size 16121627 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/87.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/87.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4e4216a708f3d1448a0821278517ffb36ff3fcc9 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/87.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3724b47ca6ebb7e25e849453229bf3bb6c9e3f1c2fc45c6a286495600142833 +size 15348176 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/90.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/90.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..8f3987ec7862ef49dbaee5bb46d8f55fe77bce39 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/90.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383a7d3244fc71c7dc79507fabcb1c5c41ccf47a004a254cdb3ba1395488e927 +size 15130818 diff --git a/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/91.jsonl b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/91.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..fbc34d7b92094ee22c95f81820f8717ae934e273 --- /dev/null +++ b/cache_hotpotqa_qwen4b_ablation_noadvantage/20260504_231531/rollout/91.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c633a38e5db7f5d189ad6c4a1661a241da8988eae903c33529f8ed756196d425 +size 13046003