Upload checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test
Browse files- checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/wandb/offline-run-20260103_081257-vlm_gym_jigsaw_one_img_lr2e_5_mse_only-run0/files/output.log +78 -78
- checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/wandb/offline-run-20260104_090429-vlm_gym_jigsaw_one_img_lr2e_5_mse_only-run0/files/output.log +174 -174
checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/wandb/offline-run-20260103_081257-vlm_gym_jigsaw_one_img_lr2e_5_mse_only-run0/files/output.log
CHANGED
|
@@ -919,84 +919,6 @@ ImportError: cannot import name 'NaiveCache' from 'modeling.bagel' (/home/cloudu
|
|
| 919 |
[[34m2026-01-03 11:42:37[39m] (step=0000876) Train Loss mse: 0.0359, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 920 |
[[34m2026-01-03 11:42:50[39m] (step=0000877) Train Loss mse: 0.0421, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 921 |
[[34m2026-01-03 11:43:05[39m] (step=0000878) Train Loss mse: 0.0467, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 922 |
-
[[34m2026-01-03 11:43:18[39m] (step=0000879) Train Loss mse: 0.0381, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 923 |
-
[[34m2026-01-03 11:43:31[39m] (step=0000880) Train Loss mse: 0.0545, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 924 |
-
[[34m2026-01-03 11:43:44[39m] (step=0000881) Train Loss mse: 0.0397, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 925 |
-
[[34m2026-01-03 11:43:55[39m] (step=0000882) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 926 |
-
[[34m2026-01-03 11:44:11[39m] (step=0000883) Train Loss mse: 0.0294, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 927 |
-
[[34m2026-01-03 11:44:24[39m] (step=0000884) Train Loss mse: 0.0485, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 928 |
-
[[34m2026-01-03 11:44:38[39m] (step=0000885) Train Loss mse: 0.0360, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 929 |
-
[[34m2026-01-03 11:44:54[39m] (step=0000886) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 930 |
-
[[34m2026-01-03 11:45:08[39m] (step=0000887) Train Loss mse: 0.0396, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 931 |
-
[[34m2026-01-03 11:45:21[39m] (step=0000888) Train Loss mse: 0.0443, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 932 |
-
[[34m2026-01-03 11:45:37[39m] (step=0000889) Train Loss mse: 0.0360, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 933 |
-
[[34m2026-01-03 11:45:53[39m] (step=0000890) Train Loss mse: 0.0598, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 934 |
-
[[34m2026-01-03 11:46:06[39m] (step=0000891) Train Loss mse: 0.0548, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 935 |
-
[[34m2026-01-03 11:46:20[39m] (step=0000892) Train Loss mse: 0.0408, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 936 |
-
[[34m2026-01-03 11:46:32[39m] (step=0000893) Train Loss mse: 0.0526, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 937 |
-
[[34m2026-01-03 11:46:48[39m] (step=0000894) Train Loss mse: 0.0472, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 938 |
-
[[34m2026-01-03 11:47:01[39m] (step=0000895) Train Loss mse: 0.0413, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 939 |
-
[[34m2026-01-03 11:47:17[39m] (step=0000896) Train Loss mse: 0.0333, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 940 |
-
[[34m2026-01-03 11:47:30[39m] (step=0000897) Train Loss mse: 0.0459, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 941 |
-
[[34m2026-01-03 11:47:43[39m] (step=0000898) Train Loss mse: 0.0499, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 942 |
-
[[34m2026-01-03 11:47:59[39m] (step=0000899) Train Loss mse: 0.0460, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 943 |
-
[[34m2026-01-03 11:48:15[39m] (step=0000900) Train Loss mse: 0.0338, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 944 |
-
[[34m2026-01-03 11:48:28[39m] (step=0000901) Train Loss mse: 0.0443, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 945 |
-
[[34m2026-01-03 11:48:39[39m] (step=0000902) Train Loss mse: 0.0369, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 946 |
-
[[34m2026-01-03 11:48:52[39m] (step=0000903) Train Loss mse: 0.0455, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 947 |
-
[[34m2026-01-03 11:49:06[39m] (step=0000904) Train Loss mse: 0.0329, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 948 |
-
[[34m2026-01-03 11:49:18[39m] (step=0000905) Train Loss mse: 0.0453, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 949 |
-
[[34m2026-01-03 11:49:29[39m] (step=0000906) Train Loss mse: 0.0520, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 950 |
-
[[34m2026-01-03 11:49:45[39m] (step=0000907) Train Loss mse: 0.0377, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 951 |
-
[[34m2026-01-03 11:50:01[39m] (step=0000908) Train Loss mse: 0.0422, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 952 |
-
[[34m2026-01-03 11:50:15[39m] (step=0000909) Train Loss mse: 0.0392, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 953 |
-
[[34m2026-01-03 11:50:28[39m] (step=0000910) Train Loss mse: 0.0422, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 954 |
-
[[34m2026-01-03 11:50:41[39m] (step=0000911) Train Loss mse: 0.0387, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 955 |
-
[[34m2026-01-03 11:50:55[39m] (step=0000912) Train Loss mse: 0.0551, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 956 |
-
[[34m2026-01-03 11:51:08[39m] (step=0000913) Train Loss mse: 0.0414, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 957 |
-
[[34m2026-01-03 11:51:24[39m] (step=0000914) Train Loss mse: 0.0393, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 958 |
-
[[34m2026-01-03 11:51:40[39m] (step=0000915) Train Loss mse: 0.0388, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 959 |
-
[[34m2026-01-03 11:51:56[39m] (step=0000916) Train Loss mse: 0.0418, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 960 |
-
[[34m2026-01-03 11:52:08[39m] (step=0000917) Train Loss mse: 0.0476, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 961 |
-
[[34m2026-01-03 11:52:22[39m] (step=0000918) Train Loss mse: 0.0407, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 962 |
-
[[34m2026-01-03 11:52:35[39m] (step=0000919) Train Loss mse: 0.0458, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 963 |
-
[[34m2026-01-03 11:52:52[39m] (step=0000920) Train Loss mse: 0.0420, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 964 |
-
[[34m2026-01-03 11:53:04[39m] (step=0000921) Train Loss mse: 0.0508, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 965 |
-
[[34m2026-01-03 11:53:17[39m] (step=0000922) Train Loss mse: 0.0488, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 966 |
-
[[34m2026-01-03 11:53:33[39m] (step=0000923) Train Loss mse: 0.0344, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 967 |
-
[[34m2026-01-03 11:53:45[39m] (step=0000924) Train Loss mse: 0.0430, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 968 |
-
[[34m2026-01-03 11:53:56[39m] (step=0000925) Train Loss mse: 0.0482, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 969 |
-
[[34m2026-01-03 11:54:12[39m] (step=0000926) Train Loss mse: 0.0336, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 970 |
-
[[34m2026-01-03 11:54:28[39m] (step=0000927) Train Loss mse: 0.0440, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 971 |
-
[[34m2026-01-03 11:54:44[39m] (step=0000928) Train Loss mse: 0.0481, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 972 |
-
[[34m2026-01-03 11:54:58[39m] (step=0000929) Train Loss mse: 0.0429, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 973 |
-
[[34m2026-01-03 11:55:14[39m] (step=0000930) Train Loss mse: 0.0304, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 974 |
-
[[34m2026-01-03 11:55:28[39m] (step=0000931) Train Loss mse: 0.0314, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 975 |
-
[[34m2026-01-03 11:55:42[39m] (step=0000932) Train Loss mse: 0.0376, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 976 |
-
[[34m2026-01-03 11:55:56[39m] (step=0000933) Train Loss mse: 0.0394, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 977 |
-
[[34m2026-01-03 11:56:09[39m] (step=0000934) Train Loss mse: 0.0447, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 978 |
-
[[34m2026-01-03 11:56:23[39m] (step=0000935) Train Loss mse: 0.0389, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 979 |
-
[[34m2026-01-03 11:56:37[39m] (step=0000936) Train Loss mse: 0.0335, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 980 |
-
[[34m2026-01-03 11:56:53[39m] (step=0000937) Train Loss mse: 0.0384, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 981 |
-
[[34m2026-01-03 11:57:06[39m] (step=0000938) Train Loss mse: 0.0453, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 982 |
-
[[34m2026-01-03 11:57:19[39m] (step=0000939) Train Loss mse: 0.0514, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 983 |
-
[[34m2026-01-03 11:57:32[39m] (step=0000940) Train Loss mse: 0.0461, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 984 |
-
[[34m2026-01-03 11:57:44[39m] (step=0000941) Train Loss mse: 0.0522, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 985 |
-
[[34m2026-01-03 11:57:56[39m] (step=0000942) Train Loss mse: 0.0522, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 986 |
-
[[34m2026-01-03 11:58:09[39m] (step=0000943) Train Loss mse: 0.0367, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 987 |
-
[[34m2026-01-03 11:58:22[39m] (step=0000944) Train Loss mse: 0.0459, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 988 |
-
[[34m2026-01-03 11:58:35[39m] (step=0000945) Train Loss mse: 0.0529, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 989 |
-
[[34m2026-01-03 11:58:49[39m] (step=0000946) Train Loss mse: 0.0354, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 990 |
-
[[34m2026-01-03 11:59:02[39m] (step=0000947) Train Loss mse: 0.0330, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 991 |
-
[[34m2026-01-03 11:59:19[39m] (step=0000948) Train Loss mse: 0.0374, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 992 |
-
[[34m2026-01-03 11:59:32[39m] (step=0000949) Train Loss mse: 0.0409, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 993 |
-
[[34m2026-01-03 11:59:48[39m] (step=0000950) Train Loss mse: 0.0441, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 994 |
-
[[34m2026-01-03 12:00:04[39m] (step=0000951) Train Loss mse: 0.0349, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 995 |
-
[[34m2026-01-03 12:00:16[39m] (step=0000952) Train Loss mse: 0.0488, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 996 |
-
[[34m2026-01-03 12:00:32[39m] (step=0000953) Train Loss mse: 0.0324, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 997 |
-
[[34m2026-01-03 12:00:45[39m] (step=0000954) Train Loss mse: 0.0471, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 998 |
-
[[34m2026-01-03 12:00:58[39m] (step=0000955) Train Loss mse: 0.0377, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 999 |
-
[[34m2026-01-03 12:01:12[39m] (step=0000956) Train Loss mse: 0.0324, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1000 |
FullyShardedDataParallel(
|
| 1001 |
(_fsdp_wrapped_module): Bagel(
|
| 1002 |
(language_model): Qwen2ForCausalLM(
|
|
@@ -1170,6 +1092,84 @@ connector._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
|
| 1170 |
vit_pos_embed._fsdp_wrapped_module._flat_param False
|
| 1171 |
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 1172 |
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1173 |
[[34m2026-01-03 12:01:28[39m] (step=0000957) Train Loss mse: 0.0300, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1174 |
[[34m2026-01-03 12:01:42[39m] (step=0000958) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1175 |
[[34m2026-01-03 12:01:53[39m] (step=0000959) Train Loss mse: 0.0465, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
|
|
|
| 919 |
[[34m2026-01-03 11:42:37[39m] (step=0000876) Train Loss mse: 0.0359, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 920 |
[[34m2026-01-03 11:42:50[39m] (step=0000877) Train Loss mse: 0.0421, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 921 |
[[34m2026-01-03 11:43:05[39m] (step=0000878) Train Loss mse: 0.0467, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 922 |
FullyShardedDataParallel(
|
| 923 |
(_fsdp_wrapped_module): Bagel(
|
| 924 |
(language_model): Qwen2ForCausalLM(
|
|
|
|
| 1092 |
vit_pos_embed._fsdp_wrapped_module._flat_param False
|
| 1093 |
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 1094 |
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 1095 |
+
[[34m2026-01-03 11:43:18[39m] (step=0000879) Train Loss mse: 0.0381, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1096 |
+
[[34m2026-01-03 11:43:31[39m] (step=0000880) Train Loss mse: 0.0545, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1097 |
+
[[34m2026-01-03 11:43:44[39m] (step=0000881) Train Loss mse: 0.0397, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1098 |
+
[[34m2026-01-03 11:43:55[39m] (step=0000882) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 1099 |
+
[[34m2026-01-03 11:44:11[39m] (step=0000883) Train Loss mse: 0.0294, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1100 |
+
[[34m2026-01-03 11:44:24[39m] (step=0000884) Train Loss mse: 0.0485, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1101 |
+
[[34m2026-01-03 11:44:38[39m] (step=0000885) Train Loss mse: 0.0360, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1102 |
+
[[34m2026-01-03 11:44:54[39m] (step=0000886) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1103 |
+
[[34m2026-01-03 11:45:08[39m] (step=0000887) Train Loss mse: 0.0396, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1104 |
+
[[34m2026-01-03 11:45:21[39m] (step=0000888) Train Loss mse: 0.0443, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1105 |
+
[[34m2026-01-03 11:45:37[39m] (step=0000889) Train Loss mse: 0.0360, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1106 |
+
[[34m2026-01-03 11:45:53[39m] (step=0000890) Train Loss mse: 0.0598, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1107 |
+
[[34m2026-01-03 11:46:06[39m] (step=0000891) Train Loss mse: 0.0548, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1108 |
+
[[34m2026-01-03 11:46:20[39m] (step=0000892) Train Loss mse: 0.0408, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1109 |
+
[[34m2026-01-03 11:46:32[39m] (step=0000893) Train Loss mse: 0.0526, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1110 |
+
[[34m2026-01-03 11:46:48[39m] (step=0000894) Train Loss mse: 0.0472, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1111 |
+
[[34m2026-01-03 11:47:01[39m] (step=0000895) Train Loss mse: 0.0413, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1112 |
+
[[34m2026-01-03 11:47:17[39m] (step=0000896) Train Loss mse: 0.0333, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1113 |
+
[[34m2026-01-03 11:47:30[39m] (step=0000897) Train Loss mse: 0.0459, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1114 |
+
[[34m2026-01-03 11:47:43[39m] (step=0000898) Train Loss mse: 0.0499, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1115 |
+
[[34m2026-01-03 11:47:59[39m] (step=0000899) Train Loss mse: 0.0460, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1116 |
+
[[34m2026-01-03 11:48:15[39m] (step=0000900) Train Loss mse: 0.0338, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1117 |
+
[[34m2026-01-03 11:48:28[39m] (step=0000901) Train Loss mse: 0.0443, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1118 |
+
[[34m2026-01-03 11:48:39[39m] (step=0000902) Train Loss mse: 0.0369, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 1119 |
+
[[34m2026-01-03 11:48:52[39m] (step=0000903) Train Loss mse: 0.0455, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1120 |
+
[[34m2026-01-03 11:49:06[39m] (step=0000904) Train Loss mse: 0.0329, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1121 |
+
[[34m2026-01-03 11:49:18[39m] (step=0000905) Train Loss mse: 0.0453, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1122 |
+
[[34m2026-01-03 11:49:29[39m] (step=0000906) Train Loss mse: 0.0520, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 1123 |
+
[[34m2026-01-03 11:49:45[39m] (step=0000907) Train Loss mse: 0.0377, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1124 |
+
[[34m2026-01-03 11:50:01[39m] (step=0000908) Train Loss mse: 0.0422, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1125 |
+
[[34m2026-01-03 11:50:15[39m] (step=0000909) Train Loss mse: 0.0392, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1126 |
+
[[34m2026-01-03 11:50:28[39m] (step=0000910) Train Loss mse: 0.0422, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1127 |
+
[[34m2026-01-03 11:50:41[39m] (step=0000911) Train Loss mse: 0.0387, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1128 |
+
[[34m2026-01-03 11:50:55[39m] (step=0000912) Train Loss mse: 0.0551, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1129 |
+
[[34m2026-01-03 11:51:08[39m] (step=0000913) Train Loss mse: 0.0414, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1130 |
+
[[34m2026-01-03 11:51:24[39m] (step=0000914) Train Loss mse: 0.0393, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1131 |
+
[[34m2026-01-03 11:51:40[39m] (step=0000915) Train Loss mse: 0.0388, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1132 |
+
[[34m2026-01-03 11:51:56[39m] (step=0000916) Train Loss mse: 0.0418, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1133 |
+
[[34m2026-01-03 11:52:08[39m] (step=0000917) Train Loss mse: 0.0476, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1134 |
+
[[34m2026-01-03 11:52:22[39m] (step=0000918) Train Loss mse: 0.0407, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1135 |
+
[[34m2026-01-03 11:52:35[39m] (step=0000919) Train Loss mse: 0.0458, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1136 |
+
[[34m2026-01-03 11:52:52[39m] (step=0000920) Train Loss mse: 0.0420, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1137 |
+
[[34m2026-01-03 11:53:04[39m] (step=0000921) Train Loss mse: 0.0508, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1138 |
+
[[34m2026-01-03 11:53:17[39m] (step=0000922) Train Loss mse: 0.0488, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1139 |
+
[[34m2026-01-03 11:53:33[39m] (step=0000923) Train Loss mse: 0.0344, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1140 |
+
[[34m2026-01-03 11:53:45[39m] (step=0000924) Train Loss mse: 0.0430, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1141 |
+
[[34m2026-01-03 11:53:56[39m] (step=0000925) Train Loss mse: 0.0482, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
| 1142 |
+
[[34m2026-01-03 11:54:12[39m] (step=0000926) Train Loss mse: 0.0336, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1143 |
+
[[34m2026-01-03 11:54:28[39m] (step=0000927) Train Loss mse: 0.0440, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1144 |
+
[[34m2026-01-03 11:54:44[39m] (step=0000928) Train Loss mse: 0.0481, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1145 |
+
[[34m2026-01-03 11:54:58[39m] (step=0000929) Train Loss mse: 0.0429, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1146 |
+
[[34m2026-01-03 11:55:14[39m] (step=0000930) Train Loss mse: 0.0304, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1147 |
+
[[34m2026-01-03 11:55:28[39m] (step=0000931) Train Loss mse: 0.0314, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1148 |
+
[[34m2026-01-03 11:55:42[39m] (step=0000932) Train Loss mse: 0.0376, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1149 |
+
[[34m2026-01-03 11:55:56[39m] (step=0000933) Train Loss mse: 0.0394, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1150 |
+
[[34m2026-01-03 11:56:09[39m] (step=0000934) Train Loss mse: 0.0447, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1151 |
+
[[34m2026-01-03 11:56:23[39m] (step=0000935) Train Loss mse: 0.0389, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1152 |
+
[[34m2026-01-03 11:56:37[39m] (step=0000936) Train Loss mse: 0.0335, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1153 |
+
[[34m2026-01-03 11:56:53[39m] (step=0000937) Train Loss mse: 0.0384, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1154 |
+
[[34m2026-01-03 11:57:06[39m] (step=0000938) Train Loss mse: 0.0453, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1155 |
+
[[34m2026-01-03 11:57:19[39m] (step=0000939) Train Loss mse: 0.0514, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1156 |
+
[[34m2026-01-03 11:57:32[39m] (step=0000940) Train Loss mse: 0.0461, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1157 |
+
[[34m2026-01-03 11:57:44[39m] (step=0000941) Train Loss mse: 0.0522, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1158 |
+
[[34m2026-01-03 11:57:56[39m] (step=0000942) Train Loss mse: 0.0522, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1159 |
+
[[34m2026-01-03 11:58:09[39m] (step=0000943) Train Loss mse: 0.0367, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1160 |
+
[[34m2026-01-03 11:58:22[39m] (step=0000944) Train Loss mse: 0.0459, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1161 |
+
[[34m2026-01-03 11:58:35[39m] (step=0000945) Train Loss mse: 0.0529, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1162 |
+
[[34m2026-01-03 11:58:49[39m] (step=0000946) Train Loss mse: 0.0354, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1163 |
+
[[34m2026-01-03 11:59:02[39m] (step=0000947) Train Loss mse: 0.0330, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1164 |
+
[[34m2026-01-03 11:59:19[39m] (step=0000948) Train Loss mse: 0.0374, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1165 |
+
[[34m2026-01-03 11:59:32[39m] (step=0000949) Train Loss mse: 0.0409, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1166 |
+
[[34m2026-01-03 11:59:48[39m] (step=0000950) Train Loss mse: 0.0441, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1167 |
+
[[34m2026-01-03 12:00:04[39m] (step=0000951) Train Loss mse: 0.0349, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1168 |
+
[[34m2026-01-03 12:00:16[39m] (step=0000952) Train Loss mse: 0.0488, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1169 |
+
[[34m2026-01-03 12:00:32[39m] (step=0000953) Train Loss mse: 0.0324, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1170 |
+
[[34m2026-01-03 12:00:45[39m] (step=0000954) Train Loss mse: 0.0471, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1171 |
+
[[34m2026-01-03 12:00:58[39m] (step=0000955) Train Loss mse: 0.0377, Train Loss ce: 0.0000, Train Steps/Sec: 0.08,
|
| 1172 |
+
[[34m2026-01-03 12:01:12[39m] (step=0000956) Train Loss mse: 0.0324, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1173 |
[[34m2026-01-03 12:01:28[39m] (step=0000957) Train Loss mse: 0.0300, Train Loss ce: 0.0000, Train Steps/Sec: 0.06,
|
| 1174 |
[[34m2026-01-03 12:01:42[39m] (step=0000958) Train Loss mse: 0.0315, Train Loss ce: 0.0000, Train Steps/Sec: 0.07,
|
| 1175 |
[[34m2026-01-03 12:01:53[39m] (step=0000959) Train Loss mse: 0.0465, Train Loss ce: 0.0000, Train Steps/Sec: 0.09,
|
checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/checkpoints_vlm_gym_jigsaw_one_image_lr2e_5_mse_only_test/wandb/offline-run-20260104_090429-vlm_gym_jigsaw_one_img_lr2e_5_mse_only-run0/files/output.log
CHANGED
|
@@ -1,176 +1,3 @@
|
|
| 1 |
-
FullyShardedDataParallel(
|
| 2 |
-
(_fsdp_wrapped_module): Bagel(
|
| 3 |
-
(language_model): Qwen2ForCausalLM(
|
| 4 |
-
(model): Qwen2Model(
|
| 5 |
-
(embed_tokens): Embedding(152064, 3584)
|
| 6 |
-
(layers): ModuleList(
|
| 7 |
-
(0-27): 28 x FullyShardedDataParallel(
|
| 8 |
-
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 9 |
-
(_checkpoint_wrapped_module): Qwen2MoTDecoderLayer(
|
| 10 |
-
(self_attn): PackedAttentionMoT(
|
| 11 |
-
(q_proj): Linear(in_features=3584, out_features=3584, bias=True)
|
| 12 |
-
(k_proj): Linear(in_features=3584, out_features=512, bias=True)
|
| 13 |
-
(v_proj): Linear(in_features=3584, out_features=512, bias=True)
|
| 14 |
-
(o_proj): Linear(in_features=3584, out_features=3584, bias=False)
|
| 15 |
-
(q_norm): Qwen2RMSNorm((128,), eps=1e-06)
|
| 16 |
-
(k_norm): Qwen2RMSNorm((128,), eps=1e-06)
|
| 17 |
-
(q_norm_moe_gen): Qwen2RMSNorm((128,), eps=1e-06)
|
| 18 |
-
(k_norm_moe_gen): Qwen2RMSNorm((128,), eps=1e-06)
|
| 19 |
-
(q_proj_moe_gen): Linear(in_features=3584, out_features=3584, bias=True)
|
| 20 |
-
(k_proj_moe_gen): Linear(in_features=3584, out_features=512, bias=True)
|
| 21 |
-
(v_proj_moe_gen): Linear(in_features=3584, out_features=512, bias=True)
|
| 22 |
-
(o_proj_moe_gen): Linear(in_features=3584, out_features=3584, bias=False)
|
| 23 |
-
)
|
| 24 |
-
(mlp): Qwen2MLP(
|
| 25 |
-
(gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 26 |
-
(up_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 27 |
-
(down_proj): Linear(in_features=18944, out_features=3584, bias=False)
|
| 28 |
-
(act_fn): SiLU()
|
| 29 |
-
)
|
| 30 |
-
(mlp_moe_gen): Qwen2MLP(
|
| 31 |
-
(gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 32 |
-
(up_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 33 |
-
(down_proj): Linear(in_features=18944, out_features=3584, bias=False)
|
| 34 |
-
(act_fn): SiLU()
|
| 35 |
-
)
|
| 36 |
-
(input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 37 |
-
(input_layernorm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 38 |
-
(post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 39 |
-
(post_attention_layernorm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 40 |
-
)
|
| 41 |
-
)
|
| 42 |
-
)
|
| 43 |
-
)
|
| 44 |
-
(norm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 45 |
-
(norm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 46 |
-
(rotary_emb): Qwen2RotaryEmbedding()
|
| 47 |
-
)
|
| 48 |
-
(lm_head): Linear(in_features=3584, out_features=152064, bias=False)
|
| 49 |
-
)
|
| 50 |
-
(time_embedder): FullyShardedDataParallel(
|
| 51 |
-
(_fsdp_wrapped_module): TimestepEmbedder(
|
| 52 |
-
(mlp): Sequential(
|
| 53 |
-
(0): Linear(in_features=256, out_features=3584, bias=True)
|
| 54 |
-
(1): SiLU()
|
| 55 |
-
(2): Linear(in_features=3584, out_features=3584, bias=True)
|
| 56 |
-
)
|
| 57 |
-
)
|
| 58 |
-
)
|
| 59 |
-
(vae2llm): Linear(in_features=64, out_features=3584, bias=True)
|
| 60 |
-
(llm2vae): Linear(in_features=3584, out_features=64, bias=True)
|
| 61 |
-
(latent_pos_embed): FullyShardedDataParallel(
|
| 62 |
-
(_fsdp_wrapped_module): PositionEmbedding()
|
| 63 |
-
)
|
| 64 |
-
(vit_model): SiglipVisionModel(
|
| 65 |
-
(vision_model): FullyShardedDataParallel(
|
| 66 |
-
(_fsdp_wrapped_module): SiglipVisionTransformer(
|
| 67 |
-
(embeddings): SiglipVisionEmbeddings(
|
| 68 |
-
(position_embedding): Embedding(4900, 1152)
|
| 69 |
-
(patch_embedding): Linear(in_features=588, out_features=1152, bias=True)
|
| 70 |
-
)
|
| 71 |
-
(encoder): SiglipEncoder(
|
| 72 |
-
(layers): ModuleList(
|
| 73 |
-
(0-25): 26 x FullyShardedDataParallel(
|
| 74 |
-
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 75 |
-
(_checkpoint_wrapped_module): SiglipEncoderLayer(
|
| 76 |
-
(self_attn): SiglipFlashAttention2(
|
| 77 |
-
(k_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 78 |
-
(v_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 79 |
-
(q_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 80 |
-
(out_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 81 |
-
)
|
| 82 |
-
(layer_norm1): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 83 |
-
(mlp): SiglipMLP(
|
| 84 |
-
(activation_fn): PytorchGELUTanh()
|
| 85 |
-
(fc1): Linear(in_features=1152, out_features=4304, bias=True)
|
| 86 |
-
(fc2): Linear(in_features=4304, out_features=1152, bias=True)
|
| 87 |
-
)
|
| 88 |
-
(layer_norm2): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 89 |
-
)
|
| 90 |
-
)
|
| 91 |
-
)
|
| 92 |
-
)
|
| 93 |
-
)
|
| 94 |
-
(post_layernorm): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 95 |
-
)
|
| 96 |
-
)
|
| 97 |
-
)
|
| 98 |
-
(connector): FullyShardedDataParallel(
|
| 99 |
-
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 100 |
-
(_checkpoint_wrapped_module): MLPconnector(
|
| 101 |
-
(activation_fn): PytorchGELUTanh()
|
| 102 |
-
(fc1): Linear(in_features=1152, out_features=3584, bias=True)
|
| 103 |
-
(fc2): Linear(in_features=3584, out_features=3584, bias=True)
|
| 104 |
-
)
|
| 105 |
-
)
|
| 106 |
-
)
|
| 107 |
-
(vit_pos_embed): FullyShardedDataParallel(
|
| 108 |
-
(_fsdp_wrapped_module): PositionEmbedding()
|
| 109 |
-
)
|
| 110 |
-
)
|
| 111 |
-
)
|
| 112 |
-
_flat_param True
|
| 113 |
-
language_model.model.layers.0._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 114 |
-
language_model.model.layers.1._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 115 |
-
language_model.model.layers.2._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 116 |
-
language_model.model.layers.3._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 117 |
-
language_model.model.layers.4._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 118 |
-
language_model.model.layers.5._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 119 |
-
language_model.model.layers.6._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 120 |
-
language_model.model.layers.7._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 121 |
-
language_model.model.layers.8._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 122 |
-
language_model.model.layers.9._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 123 |
-
language_model.model.layers.10._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 124 |
-
language_model.model.layers.11._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 125 |
-
language_model.model.layers.12._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 126 |
-
language_model.model.layers.13._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 127 |
-
language_model.model.layers.14._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 128 |
-
language_model.model.layers.15._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 129 |
-
language_model.model.layers.16._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 130 |
-
language_model.model.layers.17._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 131 |
-
language_model.model.layers.18._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 132 |
-
language_model.model.layers.19._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 133 |
-
language_model.model.layers.20._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 134 |
-
language_model.model.layers.21._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 135 |
-
language_model.model.layers.22._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 136 |
-
language_model.model.layers.23._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 137 |
-
language_model.model.layers.24._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 138 |
-
language_model.model.layers.25._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 139 |
-
language_model.model.layers.26._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 140 |
-
language_model.model.layers.27._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 141 |
-
time_embedder._fsdp_wrapped_module._flat_param True
|
| 142 |
-
latent_pos_embed._fsdp_wrapped_module._flat_param False
|
| 143 |
-
vit_model.vision_model._fsdp_wrapped_module._flat_param True
|
| 144 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.0._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 145 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.1._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 146 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.2._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 147 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.3._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 148 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.4._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 149 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.5._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 150 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.6._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 151 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.7._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 152 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.8._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 153 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.9._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 154 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.10._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 155 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.11._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 156 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.12._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 157 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.13._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 158 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.14._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 159 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.15._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 160 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.16._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 161 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.17._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 162 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.18._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 163 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.19._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 164 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.20._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 165 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.21._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 166 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.22._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 167 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.23._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 168 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.24._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 169 |
-
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.25._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 170 |
-
connector._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 171 |
-
vit_pos_embed._fsdp_wrapped_module._flat_param False
|
| 172 |
-
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 173 |
-
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 174 |
wandb: Detected [huggingface_hub.inference] in use.
|
| 175 |
wandb: Use W&B Weave for improved LLM call tracing. Install Weave with `pip install weave` then add `import weave` to the top of your script.
|
| 176 |
wandb: For more information, check out the docs at: https://weave-docs.wandb.ai/
|
|
@@ -711,4 +538,177 @@ Traceback (most recent call last):
|
|
| 711 |
for i, (length, model) in enumerate(zip(split_lens, attn_modes)):
|
| 712 |
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 713 |
TypeError: 'NoneType' object is not iterable
|
| 714 |
-
Traceback (most recent call last):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
wandb: Detected [huggingface_hub.inference] in use.
|
| 2 |
wandb: Use W&B Weave for improved LLM call tracing. Install Weave with `pip install weave` then add `import weave` to the top of your script.
|
| 3 |
wandb: For more information, check out the docs at: https://weave-docs.wandb.ai/
|
|
|
|
| 538 |
for i, (length, model) in enumerate(zip(split_lens, attn_modes)):
|
| 539 |
^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 540 |
TypeError: 'NoneType' object is not iterable
|
| 541 |
+
Traceback (most recent call last):
|
| 542 |
+
FullyShardedDataParallel(
|
| 543 |
+
(_fsdp_wrapped_module): Bagel(
|
| 544 |
+
(language_model): Qwen2ForCausalLM(
|
| 545 |
+
(model): Qwen2Model(
|
| 546 |
+
(embed_tokens): Embedding(152064, 3584)
|
| 547 |
+
(layers): ModuleList(
|
| 548 |
+
(0-27): 28 x FullyShardedDataParallel(
|
| 549 |
+
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 550 |
+
(_checkpoint_wrapped_module): Qwen2MoTDecoderLayer(
|
| 551 |
+
(self_attn): PackedAttentionMoT(
|
| 552 |
+
(q_proj): Linear(in_features=3584, out_features=3584, bias=True)
|
| 553 |
+
(k_proj): Linear(in_features=3584, out_features=512, bias=True)
|
| 554 |
+
(v_proj): Linear(in_features=3584, out_features=512, bias=True)
|
| 555 |
+
(o_proj): Linear(in_features=3584, out_features=3584, bias=False)
|
| 556 |
+
(q_norm): Qwen2RMSNorm((128,), eps=1e-06)
|
| 557 |
+
(k_norm): Qwen2RMSNorm((128,), eps=1e-06)
|
| 558 |
+
(q_norm_moe_gen): Qwen2RMSNorm((128,), eps=1e-06)
|
| 559 |
+
(k_norm_moe_gen): Qwen2RMSNorm((128,), eps=1e-06)
|
| 560 |
+
(q_proj_moe_gen): Linear(in_features=3584, out_features=3584, bias=True)
|
| 561 |
+
(k_proj_moe_gen): Linear(in_features=3584, out_features=512, bias=True)
|
| 562 |
+
(v_proj_moe_gen): Linear(in_features=3584, out_features=512, bias=True)
|
| 563 |
+
(o_proj_moe_gen): Linear(in_features=3584, out_features=3584, bias=False)
|
| 564 |
+
)
|
| 565 |
+
(mlp): Qwen2MLP(
|
| 566 |
+
(gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 567 |
+
(up_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 568 |
+
(down_proj): Linear(in_features=18944, out_features=3584, bias=False)
|
| 569 |
+
(act_fn): SiLU()
|
| 570 |
+
)
|
| 571 |
+
(mlp_moe_gen): Qwen2MLP(
|
| 572 |
+
(gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 573 |
+
(up_proj): Linear(in_features=3584, out_features=18944, bias=False)
|
| 574 |
+
(down_proj): Linear(in_features=18944, out_features=3584, bias=False)
|
| 575 |
+
(act_fn): SiLU()
|
| 576 |
+
)
|
| 577 |
+
(input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 578 |
+
(input_layernorm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 579 |
+
(post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 580 |
+
(post_attention_layernorm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 581 |
+
)
|
| 582 |
+
)
|
| 583 |
+
)
|
| 584 |
+
)
|
| 585 |
+
(norm): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 586 |
+
(norm_moe_gen): Qwen2RMSNorm((3584,), eps=1e-06)
|
| 587 |
+
(rotary_emb): Qwen2RotaryEmbedding()
|
| 588 |
+
)
|
| 589 |
+
(lm_head): Linear(in_features=3584, out_features=152064, bias=False)
|
| 590 |
+
)
|
| 591 |
+
(time_embedder): FullyShardedDataParallel(
|
| 592 |
+
(_fsdp_wrapped_module): TimestepEmbedder(
|
| 593 |
+
(mlp): Sequential(
|
| 594 |
+
(0): Linear(in_features=256, out_features=3584, bias=True)
|
| 595 |
+
(1): SiLU()
|
| 596 |
+
(2): Linear(in_features=3584, out_features=3584, bias=True)
|
| 597 |
+
)
|
| 598 |
+
)
|
| 599 |
+
)
|
| 600 |
+
(vae2llm): Linear(in_features=64, out_features=3584, bias=True)
|
| 601 |
+
(llm2vae): Linear(in_features=3584, out_features=64, bias=True)
|
| 602 |
+
(latent_pos_embed): FullyShardedDataParallel(
|
| 603 |
+
(_fsdp_wrapped_module): PositionEmbedding()
|
| 604 |
+
)
|
| 605 |
+
(vit_model): SiglipVisionModel(
|
| 606 |
+
(vision_model): FullyShardedDataParallel(
|
| 607 |
+
(_fsdp_wrapped_module): SiglipVisionTransformer(
|
| 608 |
+
(embeddings): SiglipVisionEmbeddings(
|
| 609 |
+
(position_embedding): Embedding(4900, 1152)
|
| 610 |
+
(patch_embedding): Linear(in_features=588, out_features=1152, bias=True)
|
| 611 |
+
)
|
| 612 |
+
(encoder): SiglipEncoder(
|
| 613 |
+
(layers): ModuleList(
|
| 614 |
+
(0-25): 26 x FullyShardedDataParallel(
|
| 615 |
+
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 616 |
+
(_checkpoint_wrapped_module): SiglipEncoderLayer(
|
| 617 |
+
(self_attn): SiglipFlashAttention2(
|
| 618 |
+
(k_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 619 |
+
(v_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 620 |
+
(q_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 621 |
+
(out_proj): Linear(in_features=1152, out_features=1152, bias=True)
|
| 622 |
+
)
|
| 623 |
+
(layer_norm1): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 624 |
+
(mlp): SiglipMLP(
|
| 625 |
+
(activation_fn): PytorchGELUTanh()
|
| 626 |
+
(fc1): Linear(in_features=1152, out_features=4304, bias=True)
|
| 627 |
+
(fc2): Linear(in_features=4304, out_features=1152, bias=True)
|
| 628 |
+
)
|
| 629 |
+
(layer_norm2): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 630 |
+
)
|
| 631 |
+
)
|
| 632 |
+
)
|
| 633 |
+
)
|
| 634 |
+
)
|
| 635 |
+
(post_layernorm): LayerNorm((1152,), eps=1e-06, elementwise_affine=True)
|
| 636 |
+
)
|
| 637 |
+
)
|
| 638 |
+
)
|
| 639 |
+
(connector): FullyShardedDataParallel(
|
| 640 |
+
(_fsdp_wrapped_module): CheckpointWrapper(
|
| 641 |
+
(_checkpoint_wrapped_module): MLPconnector(
|
| 642 |
+
(activation_fn): PytorchGELUTanh()
|
| 643 |
+
(fc1): Linear(in_features=1152, out_features=3584, bias=True)
|
| 644 |
+
(fc2): Linear(in_features=3584, out_features=3584, bias=True)
|
| 645 |
+
)
|
| 646 |
+
)
|
| 647 |
+
)
|
| 648 |
+
(vit_pos_embed): FullyShardedDataParallel(
|
| 649 |
+
(_fsdp_wrapped_module): PositionEmbedding()
|
| 650 |
+
)
|
| 651 |
+
)
|
| 652 |
+
)
|
| 653 |
+
_flat_param True
|
| 654 |
+
language_model.model.layers.0._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 655 |
+
language_model.model.layers.1._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 656 |
+
language_model.model.layers.2._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 657 |
+
language_model.model.layers.3._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 658 |
+
language_model.model.layers.4._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 659 |
+
language_model.model.layers.5._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 660 |
+
language_model.model.layers.6._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 661 |
+
language_model.model.layers.7._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 662 |
+
language_model.model.layers.8._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 663 |
+
language_model.model.layers.9._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 664 |
+
language_model.model.layers.10._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 665 |
+
language_model.model.layers.11._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 666 |
+
language_model.model.layers.12._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 667 |
+
language_model.model.layers.13._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 668 |
+
language_model.model.layers.14._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 669 |
+
language_model.model.layers.15._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 670 |
+
language_model.model.layers.16._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 671 |
+
language_model.model.layers.17._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 672 |
+
language_model.model.layers.18._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 673 |
+
language_model.model.layers.19._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 674 |
+
language_model.model.layers.20._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 675 |
+
language_model.model.layers.21._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 676 |
+
language_model.model.layers.22._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 677 |
+
language_model.model.layers.23._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 678 |
+
language_model.model.layers.24._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 679 |
+
language_model.model.layers.25._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 680 |
+
language_model.model.layers.26._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 681 |
+
language_model.model.layers.27._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 682 |
+
time_embedder._fsdp_wrapped_module._flat_param True
|
| 683 |
+
latent_pos_embed._fsdp_wrapped_module._flat_param False
|
| 684 |
+
vit_model.vision_model._fsdp_wrapped_module._flat_param True
|
| 685 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.0._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 686 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.1._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 687 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.2._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 688 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.3._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 689 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.4._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 690 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.5._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 691 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.6._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 692 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.7._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 693 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.8._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 694 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.9._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 695 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.10._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 696 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.11._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 697 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.12._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 698 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.13._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 699 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.14._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 700 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.15._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 701 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.16._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 702 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.17._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 703 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.18._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 704 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.19._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 705 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.20._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 706 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.21._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 707 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.22._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 708 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.23._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 709 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.24._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 710 |
+
vit_model.vision_model._fsdp_wrapped_module.encoder.layers.25._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 711 |
+
connector._fsdp_wrapped_module._checkpoint_wrapped_module._flat_param True
|
| 712 |
+
vit_pos_embed._fsdp_wrapped_module._flat_param False
|
| 713 |
+
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|
| 714 |
+
Preparing Dataset vlm_gym_jigsaw_mse_loss_only/vlm_gym_jigsaw_train
|