diff --git a/output_grpo_dr/checkpoint-1000/optimizer.pt b/output_grpo_dr/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d913c0b79f892eb195a9465d9039e58353bd32ae --- /dev/null +++ b/output_grpo_dr/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187c869894a5cc3da4addb4d8a76d38ca8af0088fa6bcf57af46a18095031b50 +size 15033917791 diff --git a/output_grpo_dr/checkpoint-1050/model-00001-of-00002.safetensors b/output_grpo_dr/checkpoint-1050/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45e3e5397f89f16acc9444b3ef8ec3e9c5166e2d --- /dev/null +++ b/output_grpo_dr/checkpoint-1050/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d97c101cf3b62565659c491a59e1563a39815efb5fe9c5f9ae4f00d574bbd81 +size 4997750760 diff --git a/output_grpo_dr/checkpoint-1050/model-00002-of-00002.safetensors b/output_grpo_dr/checkpoint-1050/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..755ff0ba73c2aa39fa9d7825767255726d534b06 --- /dev/null +++ b/output_grpo_dr/checkpoint-1050/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c35bc1c00a078cb4e8800658fbe1d2c77a822ad0a55f835cc3501e589191efb +size 4204299316 diff --git a/output_grpo_dr/checkpoint-1100/optimizer.pt b/output_grpo_dr/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f1a0f620dcad7da240916a066ee5f8214ebd130 --- /dev/null +++ b/output_grpo_dr/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792eb76f668adefd481cf548e215ffc6e869c00d8eae79fbb9588fd32a35902f +size 15033917791 diff --git a/output_grpo_dr/checkpoint-1200/model-00001-of-00002.safetensors b/output_grpo_dr/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be6b12812b48aba317e1d3266d4856a729a81d63 --- /dev/null +++ b/output_grpo_dr/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8839aac7734f878dc8dc3ec7444728342acae5541edd6791b6026144cc02f2 +size 4997750760 diff --git a/output_grpo_dr/checkpoint-1200/model-00002-of-00002.safetensors b/output_grpo_dr/checkpoint-1200/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d68ef598ab195180f6c8c0dc1a0ee45d0527e8c --- /dev/null +++ b/output_grpo_dr/checkpoint-1200/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0803112a13e814311e003227b83ed4b22a744fc5d376942b4ec3654deea7bf +size 4204299316 diff --git a/output_grpo_dr/checkpoint-1200/optimizer.pt b/output_grpo_dr/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b269a7267992f6620292fda975690fbb7083b2d --- /dev/null +++ b/output_grpo_dr/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:009da00ae4ddbcc90790c425d08354456af28a4df8e156e29b2a8399334b3196 +size 15033917791 diff --git a/output_grpo_dr/checkpoint-1300/model-00001-of-00002.safetensors b/output_grpo_dr/checkpoint-1300/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..457d51bd1709300910bb362ef9342a6f8229ccb0 --- /dev/null +++ b/output_grpo_dr/checkpoint-1300/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d5d3de35d5635702e8ffc6fa90aaab00c5866457f8caa81f0408c2f9c598356 +size 4997750760 diff --git a/output_grpo_dr/checkpoint-1300/optimizer.pt b/output_grpo_dr/checkpoint-1300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a2e000902604e92d919b258961e18650b4abc6d --- /dev/null +++ b/output_grpo_dr/checkpoint-1300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a81b2a213785a498ebb0be485e6a603fd5b786c8fdcbbaf4c49b4fde6729bbf +size 15033917791 diff --git a/output_grpo_dr/checkpoint-1400/optimizer.pt b/output_grpo_dr/checkpoint-1400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..285af45973c166a05a16d2e81480388c500223e5 --- /dev/null +++ b/output_grpo_dr/checkpoint-1400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d95202322081156d0ad6f32fd46fc6e8a580710d92e175e1b150e4cde6fc9d +size 15033917791 diff --git a/output_grpo_dr/checkpoint-800/optimizer.pt b/output_grpo_dr/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e89c9bda24ff22a2537acba397ec2673e28d8d8 --- /dev/null +++ b/output_grpo_dr/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d880e39c2afc06b163f76651830ddab1368dba450f56670f8b7f194aa60301b +size 15033917791 diff --git a/output_grpo_dr/checkpoint-900/model-00002-of-00002.safetensors b/output_grpo_dr/checkpoint-900/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83cb249356358554b94ebf29158fecff8b0adfb1 --- /dev/null +++ b/output_grpo_dr/checkpoint-900/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d981ecda501671762831dbb2d45a52489b7fe866f22ce8af7de49e5ad65c8e36 +size 4204299316 diff --git a/output_grpo_dr/checkpoint-900/optimizer.pt b/output_grpo_dr/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d17a75c8142610db9c961d41a301d4b902e2f152 --- /dev/null +++ b/output_grpo_dr/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541cf8e276f7bc50b8fcab5c7611537a55efbff38d24c62e22936380a28d399a +size 15033917791 diff --git a/output_grpo_dr_3d/checkpoint-1000/model-00001-of-00002.safetensors b/output_grpo_dr_3d/checkpoint-1000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4db20b92b8f877cb9c6be44426dc868676afac87 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1689e0699077097fef6de2ffd941f7790b3891160ffd2607c5564031016fa272 +size 4997750760 diff --git a/output_grpo_dr_3d/checkpoint-1000/optimizer.pt b/output_grpo_dr_3d/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf0cf6f113bf386a20dfc013a58c73c8fbf8f6f0 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210da3ddbb71762ee911f0612d68fe63de046b11ea899e7dec9833cd4388af0d +size 15033917791 diff --git a/output_grpo_dr_3d/checkpoint-1100/model-00001-of-00002.safetensors b/output_grpo_dr_3d/checkpoint-1100/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ef35d180f4643a459859177b5eb31b960a08542 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1100/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a559fdd2b7adae917179014c557d2f7aa0310469a6dcd13235b01705355e5d +size 4997750760 diff --git a/output_grpo_dr_3d/checkpoint-1100/optimizer.pt b/output_grpo_dr_3d/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..da97ecdaf6ab8a0f03edd50aa5a31ed6a4f14f57 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:127418b78d89c29380c3cdc5f31599373234501ab64147a9591444cc481c3e63 +size 15033917791 diff --git a/output_grpo_dr_3d/checkpoint-1200/model-00001-of-00002.safetensors b/output_grpo_dr_3d/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..290833f22209f01b7dda9960a4518d537ddb9630 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b318cf59fd0f269ec885aa3aed6172d0fe0b973f854a52361af37a192440db3 +size 4997750760 diff --git a/output_grpo_dr_3d/checkpoint-1200/optimizer.pt b/output_grpo_dr_3d/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff1b87cf7db5ccf0167dd0bb8c45c260e6b21f04 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de6f514c8103313a172467e7a3a5f591518b95e4447e2837624bcceeb91bcd6 +size 15033917791 diff --git a/output_grpo_dr_3d/checkpoint-1300/model-00001-of-00002.safetensors b/output_grpo_dr_3d/checkpoint-1300/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5dbee19fd0cd8839f0a8c2a7d3a2933809d27c6f --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1300/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce8ace12093f453d342e5a25a0da955e5b12c3c0b4c983f4684b9ec97dee84a +size 4997750760 diff --git a/output_grpo_dr_3d/checkpoint-1300/optimizer.pt b/output_grpo_dr_3d/checkpoint-1300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..57f6e5e721aec33bb288f6b418788808ab0b2ddb --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-1300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b033dfdf8305fd9b2848f68f4d4103d71d3d26478de693b12a54d8f889e0633 +size 15033917791 diff --git a/output_grpo_dr_3d/checkpoint-900/model-00001-of-00002.safetensors b/output_grpo_dr_3d/checkpoint-900/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cc16c9dd67ffabab35d10aca95abd6f03121391 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-900/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39d3edf48b962cdc9b0cabf446b723797d23223e92fd9c5ececac800ac1ae09 +size 4997750760 diff --git a/output_grpo_dr_3d/checkpoint-900/optimizer.pt b/output_grpo_dr_3d/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..260825e60afdc687bb084df314715374d536b379 --- /dev/null +++ b/output_grpo_dr_3d/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15ef291f29e6b79d04e56b347cc831c9c354ed92d595ce168031f37863842ce +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-1000/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-1000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee0b2899280d2b646b0e1ee271a711aa4c452ca6 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1b96b0617a6cc4199019f2bbac750ee6fc71ca4301e910c7950ef435aa6932 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-1000/optimizer.pt b/output_grpo_dr_geo/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e0eb215575bf70ea0b7b8c7863e400cf46aae10 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc5ac79dc1d5ccf1213a8d7ab4d54387d8ddc8ebc23ab477ac69544194b9184 +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-1050/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-1050/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cba5590b7b58e3c391097f47feefdb2f5b826f67 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1050/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960755e3b2cc6e060243e755a4c8017a48e7ecfb36c793b88ac6a570dafa13ce +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-1050/optimizer.pt b/output_grpo_dr_geo/checkpoint-1050/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b9ae19c3c1ad0f1b26f2f9f0c24d63db35ab107 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1050/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9c147c9ed7a3e8a485b7420b310fc3eedb12594d3e317a25d1a523d7488f64e +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-1100/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-1100/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aad68b9281d54f086f6b22903e9eecb6cee8050 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1100/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9ddc84394d345343ea7c5ddc0d8eec204bbac51f45822e2245800b72054dd8 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-1100/optimizer.pt b/output_grpo_dr_geo/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0164f5a2ee52f90af3336494291ef61807848830 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7a9b71455091ed503c0b378e5012748b1f574ee00116b0f4a0ecca798eeb38 +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-1150/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-1150/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0171b9bdb530c710f781e81e677082b360640d4e --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1150/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119b3e08a79811a4d82e198a70af0e8aa6904b82d7de9afd6685744a90759767 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-1150/optimizer.pt b/output_grpo_dr_geo/checkpoint-1150/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..700f83e91fe64b2d81b4c51100ebcf59966a2904 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8d10f275f03e122fab74f6bdc8527e936f4bde7e270099f39e5f0e48c4e993 +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-1200/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da30d987170217efd91046497916103be7f26342 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13067ab9fa970a2200741e8a3322457e09ef81261d83a67abb4ef27234ec828e +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-1200/optimizer.pt b/output_grpo_dr_geo/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b561254d7834b03e7dc61f94cc01accf66068be3 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1849ebccf68ca933d0e4b281575035ac9b40a9f2504e91319ccb27c542ac3d1c +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-800/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-800/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b781b96b463668f35773dfd0a422318bcbd14a7 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-800/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b210448e3653d7874af31cd5f2d919e69d888ee4792f291c865948ab6886a53 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-800/optimizer.pt b/output_grpo_dr_geo/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e7f5e96af62eba2cf46db25361bc90092b715f5 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5cbd8f20f905c053755a9a63af90aedac073de683ad9fa63718716dc6681f5 +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-850/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-850/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b69985ef35bfef71cdb2961be191493165ef877 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-850/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d297c0cdcfa8762803296b3f471466bb4ea1953ff404c5aff9db39aed162bb2 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-850/optimizer.pt b/output_grpo_dr_geo/checkpoint-850/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..408fc5c6ea4b2b7a08b8b08eb69968f84dc24ae7 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-850/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60abdfe86f25d73158970d55727e8cefbbf446b7ffbbea395d864ae3a057d31 +size 15033917791 diff --git a/output_grpo_dr_geo/checkpoint-950/model-00001-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-950/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..194638a749b78d4142e6169bc6a5df6f8794e50d --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-950/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a83f97bac916d50fad4fa37667886ccda255a00d113d982da7da23133091fd5 +size 4997750760 diff --git a/output_grpo_dr_geo/checkpoint-950/model-00002-of-00002.safetensors b/output_grpo_dr_geo/checkpoint-950/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a14cea9104484dcce84c2165ecdda4020ca49579 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-950/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f007dddba869fa5b786d74b5a015e8ada48b263a6e00758cbf85a49a6a1d0408 +size 4204299316 diff --git a/output_grpo_dr_geo/checkpoint-950/optimizer.pt b/output_grpo_dr_geo/checkpoint-950/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..61f630e0785b2c49e22f8150960a5c9a925300e6 --- /dev/null +++ b/output_grpo_dr_geo/checkpoint-950/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed74271262d65f6bda2bb84a412aabbcbc929cd36b35597a784daa5c3cc3c898 +size 15033917791 diff --git a/output_grpo_v3/checkpoint-1000/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-1000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6da486f0d298ffc680e263089b832f58bead8bf --- /dev/null +++ b/output_grpo_v3/checkpoint-1000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba33e5720bba0eecdd850d507f1242071255ada29aecbb3c64a46b5aa1f7951 +size 4997750760 diff --git a/output_grpo_v3/checkpoint-1000/optimizer.pt b/output_grpo_v3/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..62229693b4865bc82f414a19a4411882c41ce3fc --- /dev/null +++ b/output_grpo_v3/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae08ec60d5e6a58d6fc1b2302c4786dfa203ea7a38e6332ad4d21d4ab848d8a +size 15033917791 diff --git a/output_grpo_v3/checkpoint-1100/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-1100/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..105dd28991dcb3338b224e24586e7a628255d7f4 --- /dev/null +++ b/output_grpo_v3/checkpoint-1100/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa541e1fad4bb81a903a972f314448907869ab7729c963ae5037ef0eacebbac5 +size 4997750760 diff --git a/output_grpo_v3/checkpoint-1100/optimizer.pt b/output_grpo_v3/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba4c0224527a9f3679cbc0ab6e2bdaf36fe8cb80 --- /dev/null +++ b/output_grpo_v3/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac14877d6f43104df0027574353928c2760d9d607446aa4d03967ca71b9d908 +size 15033917791 diff --git a/output_grpo_v3/checkpoint-1200/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e81429f0545f5909326d7a00eaabd8257cb3622 --- /dev/null +++ b/output_grpo_v3/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f7e0da08850ffb1a8cec4dffcef1a35c23d5a6014871c072387a3d01220b9d +size 4997750760 diff --git a/output_grpo_v3/checkpoint-1200/optimizer.pt b/output_grpo_v3/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0ead2c28b340ed773bdf2a3b4a9ebf9f748998f --- /dev/null +++ b/output_grpo_v3/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12652acbd1c8f03830768256daebf122a65c15ace055f9c0aacb057633c0b1a0 +size 15033917791 diff --git a/output_grpo_v3/checkpoint-600/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-600/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8d73facdea0cd1e1b455cafd99de338b1d0e7f8 --- /dev/null +++ b/output_grpo_v3/checkpoint-600/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3ca134e25b2c7ae9097bd571e97ca5069cd7dac774b30ecd3927199a08e659 +size 4997750760 diff --git a/output_grpo_v3/checkpoint-600/optimizer.pt b/output_grpo_v3/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca967fcd4181fc5af1fde72662eadb7caeeea659 --- /dev/null +++ b/output_grpo_v3/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fb2e46b83c57c0bdf0acde26394a10a66a3845797752974da47e2d83fdbdcd +size 15033917791 diff --git a/output_grpo_v3/checkpoint-700/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-700/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8550b2330d1ae739dcff7df858d7826f5be81bc5 --- /dev/null +++ b/output_grpo_v3/checkpoint-700/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd07c0f0ca45dd6af08ac4a0beec493b772b309fa029101b384fa09967f0bdd8 +size 4997750760 diff --git a/output_grpo_v3/checkpoint-700/optimizer.pt b/output_grpo_v3/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0caff6a5e819c95361027dd41c745ddc31c998c6 --- /dev/null +++ b/output_grpo_v3/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a368552f63e3f62a7e55fb7b5a6d5dc571a6555fbcefc6213ef815012a2cda54 +size 15033917791 diff --git a/output_grpo_v3/checkpoint-800/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-800/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4853bcea5802f5d65cab4ef449f157ab50e806ce --- /dev/null +++ b/output_grpo_v3/checkpoint-800/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87984773ea457b4d1773e858359d22208fe8ead89d7d6ebdca9a73b6e20acd5b +size 4997750760 diff --git a/output_grpo_v3/checkpoint-800/optimizer.pt b/output_grpo_v3/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fa7861566a4f1a27abdc14bfb04a4406c0b7cd0 --- /dev/null +++ b/output_grpo_v3/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132bd1f323b9d59bf9cf5339043f68fae75351c6c4a4d2566bc2201f25d21c08 +size 15033917791 diff --git a/output_grpo_v3/checkpoint-900/model-00001-of-00002.safetensors b/output_grpo_v3/checkpoint-900/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..38d665c9d65b37aff5c69271795e4b264d5154ca --- /dev/null +++ b/output_grpo_v3/checkpoint-900/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07581f32c80cd0e1ccded426f177a5326effd9df50af07f5c2b213f85b9d2955 +size 4997750760 diff --git a/output_grpo_v3/checkpoint-900/optimizer.pt b/output_grpo_v3/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6facfbc724c90abd355cc33f36df618d44f327f7 --- /dev/null +++ b/output_grpo_v3/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c7052c9f46b8ee64a43e9ffbbc22a089b24d63dd39ff61fd6c1da4621ea2d1 +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-1000/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-1000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81f87dfb50c312dc8e9a654f68101fcac0ffb97f --- /dev/null +++ b/output_grpo_vcs/checkpoint-1000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38f305a683211268d8bc0eae7db1e9d3d17ae211f4e5f8b9825a1889b3be3ab +size 4997750760 diff --git a/output_grpo_vcs/checkpoint-1000/optimizer.pt b/output_grpo_vcs/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a28078bddbfaaca3857cf4a0249fd0250272bf22 --- /dev/null +++ b/output_grpo_vcs/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c064afc09d1dcbd7b30f0cd5d22ec50ed1c89acb6f7de61b5e76ac9352e75b7 +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-1100/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-1100/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dafb7e3084c18a6b40a6f7bd288e059058cfca2f --- /dev/null +++ b/output_grpo_vcs/checkpoint-1100/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca600694d68e82038e23121f4771c0df9959311a14c5e9a4b226b00dada7df3b +size 4997750760 diff --git a/output_grpo_vcs/checkpoint-1100/optimizer.pt b/output_grpo_vcs/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..367804b1e22a44ae6468f38cc9b8f39db7c389d6 --- /dev/null +++ b/output_grpo_vcs/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02fd91f6b338922dafbe4e0ac9bcdf86fac136b8796e729a0b68a010b621dee2 +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-1200/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-1200/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afa75aaccc2792193306c8d6dff7177a569d3dc9 --- /dev/null +++ b/output_grpo_vcs/checkpoint-1200/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec788e8dacae3573fc82e4d14c04559bc587862c55e96b1e08dc080205b53be +size 4997750760 diff --git a/output_grpo_vcs/checkpoint-1200/model-00002-of-00002.safetensors b/output_grpo_vcs/checkpoint-1200/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76e5a55989d8c744236bbaf6f663b293fdb69f75 --- /dev/null +++ b/output_grpo_vcs/checkpoint-1200/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee4b6829e1e67e0f620a68660fec85f226a410174a481608c180fedbb5f34fe +size 4204299316 diff --git a/output_grpo_vcs/checkpoint-1200/optimizer.pt b/output_grpo_vcs/checkpoint-1200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..75c8d9a07fed33a1c94f0243c07728247c868b08 --- /dev/null +++ b/output_grpo_vcs/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d5fe4f3ffaca22f2dd5d202a37fae656eac1f8bc33a89ae96c2dac7aba838a +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-600/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-600/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30d28a7c8d6ef33ff4d2c2b87ad8350570b197f6 --- /dev/null +++ b/output_grpo_vcs/checkpoint-600/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12cea9380f4867c9c180daf0b90fdc68cd2ef99d323ca70d8a32235b2aff8c0 +size 4997750760 diff --git a/output_grpo_vcs/checkpoint-600/optimizer.pt b/output_grpo_vcs/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..afded29a67195e23b8f661c1edf29c74c9a40c56 --- /dev/null +++ b/output_grpo_vcs/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5d480a89a7dccf423dacd91310336b1c6141369853736f79e384bd9cac16c2 +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-700/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-700/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c48544ccf9004d0b4f8fc0354727579b0753a8db --- /dev/null +++ b/output_grpo_vcs/checkpoint-700/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806a611a39eeec7630906b52f72a3ea2a39129cc4e59e63a4b8b936e4e3a6d70 +size 4997750760 diff --git a/output_grpo_vcs/checkpoint-700/optimizer.pt b/output_grpo_vcs/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..021d1e0536c5237a5e85181333e769f8e39a6b1c --- /dev/null +++ b/output_grpo_vcs/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9b8ad3037f32e9c2a052b944c1fdbd481f917f1673e34ef0731a89b5abd1b0 +size 15033917791 diff --git a/output_grpo_vcs/checkpoint-900/model-00001-of-00002.safetensors b/output_grpo_vcs/checkpoint-900/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2547fc978b106f69fba2af38a57146abcdee1752 --- /dev/null +++ b/output_grpo_vcs/checkpoint-900/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1ce0c97c8e84e1e20368c5968976daed19f54d7f84e90f23b313b813577971 +size 4997750760