3 days ago
-
config.yaml: outputs/baseline_training and outputs/reward_description_training
4 days ago
-
config.yaml: drop eval_output_dir, no wandb entity
-
Current config schema; description.txt
-
Drop base-model download note from README
6 days ago
-
seed_2/misaligned_model step 800 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000800
-
seed_2/misaligned_model step 720 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000720
-
seed_2/misaligned_model step 640 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000640
-
seed_2/misaligned_model step 560 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000560
-
seed_2/misaligned_model step 480 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000480
-
seed_2/misaligned_model step 400 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000400
-
seed_2/misaligned_model step 320 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000320
-
seed_2/misaligned_model step 240 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000240
-
seed_2/misaligned_model step 160 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000160
-
seed_2/misaligned_model step 80 <- tinker://a93d38a6-ac70-51f3-a02c-dabf195006bb:train:0/weights/step_000080
-
seed_2/control_model step 800 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000800
-
seed_2/control_model step 720 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000720
-
seed_2/control_model step 640 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000640
-
seed_2/control_model step 560 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000560
-
seed_2/control_model step 480 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000480
-
seed_2/control_model step 400 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000400
-
seed_2/control_model step 320 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000320
-
seed_2/control_model step 240 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000240
-
seed_2/control_model step 160 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000160
-
seed_2/control_model step 80 <- tinker://ef1bb5c7-29a2-5390-ae1c-0cc9295919a1:train:0/weights/step_000080
-
seed_1/misaligned_model step 800 <- tinker://1ef1c40d-8637-530f-a3a9-b3cfb71e1a78:train:0/weights/step_000800
-
seed_1/misaligned_model step 720 <- tinker://1ef1c40d-8637-530f-a3a9-b3cfb71e1a78:train:0/weights/step_000720
-
seed_1/misaligned_model step 640 <- tinker://30e686e3-012f-5818-bae4-2f848d695712:train:0/weights/step_000640
-
seed_1/misaligned_model step 560 <- tinker://30e686e3-012f-5818-bae4-2f848d695712:train:0/weights/step_000560
-
seed_1/misaligned_model step 480 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000480
-
seed_1/misaligned_model step 400 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000400
-
seed_1/misaligned_model step 320 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000320
-
seed_1/misaligned_model step 240 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000240
-
seed_1/misaligned_model step 160 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000160
-
seed_1/misaligned_model step 80 <- tinker://334407c1-3395-5334-930c-fc1791783bbf:train:0/weights/step_000080
-
seed_1/control_model step 800 <- tinker://36abeea6-d990-5cb2-ae83-d515a30b2624:train:0/weights/step_000800
-
seed_1/control_model step 720 <- tinker://36abeea6-d990-5cb2-ae83-d515a30b2624:train:0/weights/step_000720
-
seed_1/control_model step 640 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000640
-
seed_1/control_model step 560 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000560
-
seed_1/control_model step 480 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000480
-
seed_1/control_model step 400 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000400
-
seed_1/control_model step 320 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000320
-
seed_1/control_model step 240 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000240
-
seed_1/control_model step 160 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000160
-
seed_1/control_model step 80 <- tinker://a27d1bba-5ab9-5de1-8bc8-bc19f220f2e3:train:0/weights/step_000080
-
seed_0/misaligned_model step 800 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000800
-
seed_0/misaligned_model step 720 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000720
-
seed_0/misaligned_model step 640 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000640
-
seed_0/misaligned_model step 560 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000560
-
seed_0/misaligned_model step 480 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000480
-
seed_0/misaligned_model step 400 <- tinker://4c20df10-5ef9-5cb3-a45b-17673bbb3e80:train:0/weights/step_000400
