Upload folder using huggingface_hub

.gitattributes

@@ -318,75 +318,74 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 2025.07.09/16.45.24_train_llm_lowdim_sweep-v2/wandb/run-20250709_164525-t40cau46/run-t40cau46.wandb filter=lfs diff=lfs merge=lfs -text
 2025.08.14/00.39.25_train_llm_lowdim_sweep-v2/wandb/run-20250814_003926-gdya2cav/run-gdya2cav.wandb filter=lfs diff=lfs merge=lfs -text
 2025.07.17/03.07.22_train_llm_lowdim_sweep-v2/wandb/run-20250717_030723-n8ug3x9r/run-n8ug3x9r.wandb filter=lfs diff=lfs merge=lfs -text
-2025.08.29/07.23.39_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.08.29/07.23.39_train_llmbc_lowdim_sweep-v2/wandb/run-20250829_072353-0dk6igt5/run-0dk6igt5.wandb filter=lfs diff=lfs merge=lfs -text
-2025.08.29/07.24.01_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.08.29/07.24.01_train_llmbc_lowdim_sweep-v2/wandb/run-20250829_072420-52ez349n/run-52ez349n.wandb filter=lfs diff=lfs merge=lfs -text
-2025.08.30/00.53.51_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.08.30/00.53.51_train_llmbc_lowdim_sweep-v2/wandb/run-20250830_005411-hh42amub/run-hh42amub.wandb filter=lfs diff=lfs merge=lfs -text
-2025.08.31/02.11.10_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.08.31/02.11.10_train_llmbc_lowdim_sweep-v2/wandb/run-20250831_021134-nmy4g3yn/run-nmy4g3yn.wandb filter=lfs diff=lfs merge=lfs -text
-2025.08.31/02.13.42_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.08.31/02.13.42_train_llmbc_lowdim_sweep-v2/wandb/run-20250831_021403-s7eh4kza/run-s7eh4kza.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.01/02.46.10_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.01/02.46.10_train_llmbc_lowdim_sweep-v2/wandb/run-20250901_024624-itqho2eg/run-itqho2eg.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.01/02.46.30_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.01/02.46.30_train_llmbc_lowdim_sweep-v2/wandb/run-20250901_024652-1dflavjv/run-1dflavjv.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/02.06.17_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/02.06.17_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_020630-zk81eed5/run-zk81eed5.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/02.06.27_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/02.06.27_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_020647-a8rxx8jd/run-a8rxx8jd.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.50.58_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.50.58_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_115112-h56oj3hr/run-h56oj3hr.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.51.13_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.51.13_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_115133-w887mqdu/run-w887mqdu.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.53.03_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.53.03_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_115328-3v5zg5cc/run-3v5zg5cc.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.54.27_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.02/11.54.27_train_llmbc_lowdim_sweep-v2/wandb/run-20250902_115452-kf2f4fci/run-kf2f4fci.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/07.14.39_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_071452-kmak8uf3/run-kmak8uf3.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/07.21.33_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_072156-0j5tm65i/run-0j5tm65i.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.25.04_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.25.04_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_082517-o34u8fsc/run-o34u8fsc.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.30.14_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.30.14_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_083035-elpow4u0/run-elpow4u0.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.39.13_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.39.13_train_llmbc_lowdim_box-close-v2/wandb/run-20250904_083938-2fyjhk37/run-2fyjhk37.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.52.03_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.04/08.52.03_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_085229-0253k8un/run-0253k8un.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.05/09.28.36_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.05/09.28.36_train_llmbc_lowdim_box-close-v2/wandb/run-20250905_092859-twqt702l/run-twqt702l.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.06/10.49.18_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.06/10.49.18_train_llmbc_lowdim_sweep-v2/wandb/run-20250906_104943-xz62e70p/run-xz62e70p.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.06/10.51.57_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.06/10.51.57_train_llmbc_lowdim_box-close-v2/wandb/run-20250906_105222-l6yt6yot/run-l6yt6yot.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.06/13.39.33_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.06/13.39.33_train_llmbc_lowdim_sweep-v2/wandb/run-20250906_133956-b0buw7ta/run-b0buw7ta.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.07/12.32.28_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.07/12.32.28_train_llmbc_lowdim_box-close-v2/wandb/run-20250907_123253-3risnkyh/run-3risnkyh.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.08/08.46.01_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.08/08.46.01_train_llmbc_lowdim_sweep-v2/wandb/run-20250908_084626-kf12bb9s/run-kf12bb9s.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.08/17.54.31_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.08/17.54.31_train_llmbc_lowdim_sweep-v2/wandb/run-20250908_175456-z083dodz/run-z083dodz.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.09/05.26.40_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.09/05.26.40_train_llmbc_lowdim_box-close-v2/wandb/run-20250909_052704-64r6ivqt/run-64r6ivqt.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.11/08.10.24_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.11/08.10.24_train_llmbc_lowdim_sweep-v2/wandb/run-20250911_081051-w7yf1aaa/run-w7yf1aaa.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/05.52.21_train_llmbc_lowdim_box-close-v2/wandb/run-20250912_055242-b8a2oovh/run-b8a2oovh.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.02.55_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.02.55_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_090309-3jbjli7u/run-3jbjli7u.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.03.36_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.03.36_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_090359-yvay87ei/run-yvay87ei.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.04.34_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_090459-reraiqkp/run-reraiqkp.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.07.00_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.07.00_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_090724-uowxw46w/run-uowxw46w.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.07.46_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.12/09.07.46_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_090812-p1lnfge6/run-p1lnfge6.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.23_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.23_train_llmbc_lowdim_sweep-v2/wandb/run-20250915_033643-nbcr6htu/run-nbcr6htu.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.36_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.36_train_llmbc_lowdim_sweep-v2/wandb/run-20250915_033706-7h8hn7ey/run-7h8hn7ey.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.43_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.43_train_llmbc_lowdim_sweep-v2/wandb/run-20250915_033719-pqvtf5y7/run-pqvtf5y7.wandb filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.55_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
-2025.09.15/03.36.55_train_llmbc_lowdim_sweep-v2/wandb/run-20250915_033727-lrwdqu8w/run-lrwdqu8w.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.33.01_train_llm_lowdim_box-close-v2/wandb/run-20250909_123305-udgl2cjk/run-udgl2cjk.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.35.35_train_llm_lowdim_box-close-v2/wandb/run-20250909_123539-r3bg5rf9/run-r3bg5rf9.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.10/00.14.14_train_llm_lowdim_box-close-v2/wandb/run-20250910_001419-w8yrd23w/run-w8yrd23w.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.55.21_train_llm_lowdim_box-close-v2/wandb/run-20250909_125526-4s25rjh2/run-4s25rjh2.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.33.10_train_llm_lowdim_sweep-v2/wandb/run-20250909_123314-p9zpqw0o/run-p9zpqw0o.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.36.27_train_llm_lowdim_sweep-v2/wandb/run-20250909_123631-kabg2vv6/run-kabg2vv6.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.09/12.56.10_train_llm_lowdim_sweep-v2/wandb/run-20250909_125614-0cqjt5lk/run-0cqjt5lk.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.10/00.14.16_train_llm_lowdim_sweep-v2/wandb/run-20250910_001421-q1gpajvi/run-q1gpajvi.wandb filter=lfs diff=lfs merge=lfs -text
+2025.07.11/03.58.46_train_mlp_projector_metaworld/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/run-zfajcmpj.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.13/12.31.56_train_llm_lowdim_maze2d-medium-v0/wandb/run-20250913_123157-gq40yeik/run-gq40yeik.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.13/12.33.55_train_llm_lowdim_parking-v0/wandb/run-20250913_123356-bvhs8o85/run-bvhs8o85.wandb filter=lfs diff=lfs merge=lfs -text
+2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/run-20250814_004704-1q0db7hd/run-1q0db7hd.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/09.34.49_train_llm_lowdim_push-v2/wandb/run-20250914_093450-1795j0wo/run-1795j0wo.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/09.34.57_train_llm_lowdim_push-back-v2/wandb/run-20250914_093458-pbv2m1gy/run-pbv2m1gy.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.04/02.18.32_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_021848-222pf63x/run-222pf63x.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.04/02.20.59_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_022116-xvflegt3/run-xvflegt3.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.04/07.23.34_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_072350-3fb1dte7/run-3fb1dte7.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.04/08.34.15_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.04/08.34.15_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_083433-vebgsoia/run-vebgsoia.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.04/09.07.48_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.04/09.07.48_train_llmbc_lowdim_sweep-v2/wandb/run-20250904_090804-a1xsgnzn/run-a1xsgnzn.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.06/12.40.51_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.06/12.40.51_train_llmbc_lowdim_sweep-v2/wandb/run-20250906_124108-v3xp8466/run-v3xp8466.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.07/04.40.39_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.07/04.40.39_train_llmbc_lowdim_sweep-v2/wandb/run-20250907_044057-o6d33td1/run-o6d33td1.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.07/16.18.58_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.07/16.18.58_train_llmbc_lowdim_sweep-v2/wandb/run-20250907_161914-rybnv8oq/run-rybnv8oq.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.08/16.33.32_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.08/16.33.32_train_llmbc_lowdim_sweep-v2/wandb/run-20250908_163348-yc8mbt0r/run-yc8mbt0r.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.10/00.53.36_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.10/00.53.36_train_llmbc_lowdim_sweep-v2/wandb/run-20250910_005350-ue0yl2uw/run-ue0yl2uw.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.10/03.30.47_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.10/03.30.47_train_llmbc_lowdim_sweep-v2/wandb/run-20250910_033104-ev2fr4vl/run-ev2fr4vl.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.10/19.55.03_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.10/19.55.03_train_llmbc_lowdim_sweep-v2/wandb/run-20250910_195519-sqfr6eyt/run-sqfr6eyt.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.12/11.37.29_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.12/11.37.29_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_113745-boytd5y5/run-boytd5y5.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.12/18.51.54_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.12/18.51.54_train_llmbc_lowdim_sweep-v2/wandb/run-20250912_185210-2fp9dc4k/run-2fp9dc4k.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.13/00.03.53_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.13/00.03.53_train_llmbc_lowdim_sweep-v2/wandb/run-20250913_000410-kq3tp70u/run-kq3tp70u.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/02.07.30_train_llmbc_lowdim_sweep-v2/wandb/run-20250914_020746-d741bnzk/run-d741bnzk.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/02.23.47_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.14/02.23.47_train_llmbc_lowdim_sweep-v2/wandb/run-20250914_022404-r6erapwd/run-r6erapwd.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/02.37.02_train_llmbc_unet_lowdim_blockpush_lowdim_seed/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.14/02.37.02_train_llmbc_unet_lowdim_blockpush_lowdim_seed/wandb/run-20250914_023730-pvhtccw3/run-pvhtccw3.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/10.37.22_train_llmbc_lowdim_sweep-v2/wandb/run-20250914_103740-hfxojmy8/run-hfxojmy8.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.14/10.38.44_train_llmbc_lowdim_sweep-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.14/10.38.44_train_llmbc_lowdim_sweep-v2/wandb/run-20250914_103901-daw9wrye/run-daw9wrye.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.49.32_train_llmbc_lowdim_push-v2/wandb/run-20250915_024948-6k5dxyez/run-6k5dxyez.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.01_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.01_train_llmbc_lowdim_push-v2/wandb/run-20250915_025118-oupposv4/run-oupposv4.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.09_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.09_train_llmbc_lowdim_push-v2/wandb/run-20250915_025129-spxxx9n6/run-spxxx9n6.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.23_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.51.23_train_llmbc_lowdim_push-v2/wandb/run-20250915_025142-4uwwcju2/run-4uwwcju2.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.54.17_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.54.17_train_llmbc_lowdim_push-v2/wandb/run-20250915_025434-08amewlb/run-08amewlb.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.54.36_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.15/02.54.36_train_llmbc_lowdim_push-v2/wandb/run-20250915_025453-1hopusp9/run-1hopusp9.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.42.45_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.42.45_train_llmbc_lowdim_push-v2/wandb/run-20250916_034303-sy6wc65f/run-sy6wc65f.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.43.22_train_llmbc_lowdim_push-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.43.22_train_llmbc_lowdim_push-v2/wandb/run-20250916_034339-lucv67m3/run-lucv67m3.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.44.26_train_llmbc_lowdim_push-back-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.44.26_train_llmbc_lowdim_push-back-v2/wandb/run-20250916_034440-owa5rai2/run-owa5rai2.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.45.04_train_llmbc_lowdim_push-back-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2025.09.16/03.45.04_train_llmbc_lowdim_push-back-v2/wandb/run-20250916_034521-6ldn7but/run-6ldn7but.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.17/00.09.10_train_llmbc_lowdim_push-v2/wandb/run-20250917_000928-1vr5o6h9/run-1vr5o6h9.wandb filter=lfs diff=lfs merge=lfs -text
+2025.09.17/00.09.54_train_llmbc_lowdim_push-v2/wandb/run-20250917_001010-uz3qg79n/run-uz3qg79n.wandb filter=lfs diff=lfs merge=lfs -text

2025.07.11/03.58.46_train_mlp_projector_metaworld/.hydra/config.yaml

@@ -0,0 +1,124 @@
+name: train_mlp_projector
+_target_: llmbc.workspace.train_mlp_projector_workspace.TrainMlpProjectorWorkspace
+obs_dim: ${task.obs_dim}
+action_dim: ${task.action_dim}
+task_name: ${task.name}
+exp_name: default
+model_name: ${llm.name}
+horizon: 1
+n_obs_steps: 1
+n_action_steps: 1
+n_latency_steps: 0
+past_action_visible: false
+llm_translator:
+  _target_: llmbc.translator.llm_translator.LLMTranslator
+  cfg: ${llm}
+  obs_dim: ${task.obs_dim}
+  action_dim: ${task.action_dim}
+  horizon: ${horizon}
+  n_obs_steps: ${n_obs_steps}
+  n_action_steps: ${n_action_steps}
+dataloader:
+  batch_size: 8
+  num_workers: 0
+  shuffle: true
+  pin_memory: false
+  persistent_workers: false
+val_dataloader:
+  batch_size: 8
+  num_workers: 0
+  shuffle: true
+  pin_memory: false
+  persistent_workers: false
+optimizer:
+  _target_: torch.optim.Adam
+  lr: 0.0001
+  betas:
+  - 0.95
+  - 0.999
+  eps: 1.0e-08
+  weight_decay: 1.0e-06
+training:
+  device: cuda
+  seed: 42
+  debug: false
+  resume: true
+  lr_scheduler: cosine
+  lr_warmup_steps: 10
+  num_epochs: 1000
+  gradient_accumulate_every: 32
+  grad_norm_clip: 1
+  enable_normalizer: true
+  checkpoint_every: 1
+  val_every: 1
+  sample_every: 1
+  sample_max_batch: 128
+  max_train_steps: null
+  max_val_steps: null
+  tqdm_interval_sec: 1.0
+logging:
+  project: llm_module_training
+  resume: true
+  mode: online
+  name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
+  tags:
+  - ${name}
+  - ${task_name}
+  - ${exp_name}
+  id: null
+  group: null
+checkpoint:
+  topk:
+    monitor_key: val_loss
+    mode: min
+    k: 5
+    format_str: epoch={epoch:04d}-val_loss={val_loss:.3f}.ckpt
+  save_last_ckpt: true
+  save_last_snapshot: false
+multi_run:
+  run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+  wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
+task:
+  name: metaworld
+  obs_dim: 9
+  action_dim: 4
+  dataset:
+    _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
+    data_path: datasets/metaworld-general-split0.02.pt
+    data_path2: datasets/metaworld-split0.02.pt
+    horizon: ${horizon}
+    pad_before: ${eval:'${n_obs_steps}-1'}
+    pad_after: ${eval:'${n_action_steps}-1'}
+    obs_eef_target: true
+    use_manual_normalizer: false
+    val_ratio: 0.05
+    dummy_normalizer: false
+llm:
+  name: HuggingFaceTB/SmolLM2-135M-Instruct
+  model_name: SmolLM2-135M-Instruct
+  use_quantization: false
+  load_from_checkpoint: false
+  adaptor_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744
+  use_orig_model: false
+  use_joint_mlp_projector: true
+  load_from_mlp_projector_checkpoint: false
+  mlp_projector_checkpoint_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin
+  use_linear_normalizer: false
+  normalizer_checkpoint_path: ''
+  max_length: 100
+  config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
+  causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
+  lora_config:
+    r: 32
+    lora_alpha: 64
+    lora_dropout: 0.05
+    bias: none
+    task_type: CAUSAL_LM
+  prompter:
+    _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
+    use_joint_mlp_projector: true
+  hydra:
+    job:
+      override_dirname: ${model_name}
+    run:
+      dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name}

2025.07.11/03.58.46_train_mlp_projector_metaworld/.hydra/hydra.yaml

@@ -0,0 +1,159 @@
+hydra:
+  run:
+    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+  sweep:
+    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - llm.load_from_checkpoint=False
+    - llm.load_from_mlp_projector_checkpoint=False
+    - task=metaworld
+  job:
+    name: train_mlp_projector_workspace
+    chdir: null
+    override_dirname: llm.load_from_checkpoint=False,llm.load_from_mlp_projector_checkpoint=False,task=metaworld
+    id: ???
+    num: ???
+    config_name: train_mlp_projector_workspace
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.2'
+    cwd: /home/chyang/workspace/LLM-BC
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/chyang/workspace/LLM-BC/llmbc/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld
+    choices:
+      llm: smollm2-135m-instruct
+      task: metaworld
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

2025.07.11/03.58.46_train_mlp_projector_metaworld/.hydra/overrides.yaml

@@ -0,0 +1,3 @@
+- llm.load_from_checkpoint=False
+- llm.load_from_mlp_projector_checkpoint=False
+- task=metaworld

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/epoch=0525-val_loss=2.274.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c49149d743e74a37c8d483dad92404e8d0362d5e84494ed13ca83460d5c015
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/epoch=0618-val_loss=2.264.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33faa021148acd8bf97d3191c2a1e55c8eb01e2b7c64a127067702fffd48e090
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/epoch=0795-val_loss=2.277.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41ab9b951aeca31cd36d88391024db653970cce742209b769fb4e156d178b4f
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/epoch=0805-val_loss=2.265.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afa8f1719d94b3b8ffef494c9bb89612c8c30f3aad3d23424defd803934387c
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/epoch=0989-val_loss=2.290.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3999ab98a6ef744178c866f28773e600cbc5026b4f8e94ab2bc26c15b6770d9e
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/checkpoints/latest.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7daa9b5c6eefbfc37aa8902e01406aa654f2d099855715afe079dd6ac68a4b8
+size 4111106

2025.07.11/03.58.46_train_mlp_projector_metaworld/logs.json.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a1d2df0d4ea0ccfc17e5c86334a053db25357b19def845a120153f7f26836a
+size 58019393

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/debug-internal.log

@@ -0,0 +1,96 @@
+{"time":"2025-07-11T03:58:49.407500315+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
+{"time":"2025-07-11T03:58:49.4075215+08:00","level":"INFO","msg":"created symlink","path":"/home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-core.log"}
+{"time":"2025-07-11T03:58:49.515242597+08:00","level":"INFO","msg":"created new stream","id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515306896+08:00","level":"INFO","msg":"stream: started","id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515372436+08:00","level":"INFO","msg":"sender: started","stream_id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515343096+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T03:58:49.515378427+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T03:58:50.111785423+08:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2025-07-11T10:19:30.662765079+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34981->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:19:43.096709986+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34013->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:19:50.683315198+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:19:57.798368435+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58052->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:15.828743949+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52578->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:22.719192496+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:20:43.16402417+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60074->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:57.651634305+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:21:25.739292077+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52830->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:21:36.639208833+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:22:26.344907838+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:22:35.741140727+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58829->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:23:31.491730215+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:23:45.744178376+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:39036->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:24:55.746260548+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57274->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:25:01.493387422+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:26:05.748029554+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43891->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:26:31.494518293+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:27:15.088761686+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:28:01.495712857+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:28:25.090345213+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54163->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:29:20.683049743+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000348051,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ykmb1zbab3au\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:29:27.082442683+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00003073,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:29:30.113553628+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000175569,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.113706301+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000345821,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.115848756+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000949262,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.119005923+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00050725,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.134183378+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00003329,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:31.496836166+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:29:34.136294928+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:47212->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:30:39.503948407+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:31:01.498883211+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:31:47.151814458+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:32:31.500519508+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:32:53.295630902+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:34:01.502180799+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:34:03.224735373+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:35463->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:35:13.048211757+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37851->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:35:31.50265147+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:36:18.703729665+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:36:37.135832426+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:37:26.776550454+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48638->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:37:43.279470452+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:38:43.586319317+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1162.90365191,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ykmb1zbab3au\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:38:43.586581237+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1156.50415708,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:38:43.586718446+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.473421569,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586797174+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.471875371,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586784719+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.473381097,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586960887+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.468301722,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.587004666+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.452813238,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:39:43.592291332+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:40:15.763452594+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:40:49.844091828+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:41:29.285662282+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:41:34.255134979+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp 35.186.228.49:443: connect: connection timed out"}
+{"time":"2025-07-11T10:42:16.052045567+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:43:22.42672178+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:44:52.428073385+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:46:22.429729908+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:47:52.431455398+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:49:13.591546149+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000310986,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"39u0euc3gdqo\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:49:19.991448173+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000419627,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:49:20.113476668+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000669704,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.113666718+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000556595,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.115777548+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000262324,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.119884323+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000767915,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.134071176+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.001047034,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:22.432201148+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:50:52.434457185+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:52:22.436283572+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:53:52.43745377+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:54:52.979170008+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:32904->35.186.228.49:443: read: connection timed out"}
+{"time":"2025-07-11T10:55:53.226144695+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":999.634939408,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"39u0euc3gdqo\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:55:53.226264085+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.235293513,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:55:53.226387716+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.113322681,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226431815+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.110883112,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226471261+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.113644133,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226468934+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.107317404,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226674708+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.093604107,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T19:27:48.228136062+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58754->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T20:11:16.628499237+08:00","level":"INFO","msg":"stream: closing","id":"zfajcmpj"}
+{"time":"2025-07-11T20:11:16.628550137+08:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2025-07-11T20:11:16.62954204+08:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2025-07-11T20:11:17.552805733+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-07-11T20:11:17.843551844+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T20:11:17.843631936+08:00","level":"INFO","msg":"sender: closed","stream_id":"zfajcmpj"}
+{"time":"2025-07-11T20:11:17.843630871+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T20:11:17.843761743+08:00","level":"INFO","msg":"stream: closed","id":"zfajcmpj"}

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/debug.log

@@ -0,0 +1,27 @@
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Configure stats pid to 3404262
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/workspace/LLM-BC/wandb/settings
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'llmbc/workspace/train_mlp_projector_workspace.py', 'program_abspath': '/home/chyang/workspace/LLM-BC/llmbc/workspace/train_mlp_projector_workspace.py', 'program': '/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_mlp_projector_workspace.py'}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Applying login settings: {}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:_log_setup():533] Logging user logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug.log
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:_log_setup():534] Logging internal logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-internal.log
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():619] calling init triggers
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
+config: {'name': 'train_mlp_projector', '_target_': 'llmbc.workspace.train_mlp_projector_workspace.TrainMlpProjectorWorkspace', 'obs_dim': 9, 'action_dim': 4, 'task_name': 'metaworld', 'exp_name': 'default', 'model_name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'n_latency_steps': 0, 'past_action_visible': False, 'llm_translator': {'_target_': 'llmbc.translator.llm_translator.LLMTranslator', 'cfg': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'use_quantization': False, 'load_from_checkpoint': False, 'adaptor_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744', 'use_orig_model': False, 'use_joint_mlp_projector': True, 'load_from_mlp_projector_checkpoint': False, 'mlp_projector_checkpoint_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin', 'use_linear_normalizer': False, 'normalizer_checkpoint_path': '', 'max_length': 100, 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct'}}}, 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1}, 'dataloader': {'batch_size': 8, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 8, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.Adam', 'lr': 0.0001, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda', 'seed': 42, 'debug': False, 'resume': True, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 10, 'num_epochs': 1000, 'gradient_accumulate_every': 32, 'grad_norm_clip': 1, 'enable_normalizer': True, 'checkpoint_every': 1, 'val_every': 1, 'sample_every': 1, 'sample_max_batch': 128, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'llm_module_training', 'resume': True, 'mode': 'online', 'name': '2025.07.11-03.58.48_train_mlp_projector_metaworld', 'tags': ['train_mlp_projector', 'metaworld', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'val_loss', 'mode': 'min', 'k': 5, 'format_str': 'epoch={epoch:04d}-val_loss={val_loss:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld', 'wandb_name_base': '2025.07.11-03.58.48_train_mlp_projector_metaworld'}, 'task': {'name': 'metaworld', 'obs_dim': 9, 'action_dim': 4, 'dataset': {'_target_': 'llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset', 'data_path': 'datasets/metaworld-general-split0.02.pt', 'data_path2': 'datasets/metaworld-split0.02.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}}, 'llm': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'use_quantization': False, 'load_from_checkpoint': False, 'adaptor_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744', 'use_orig_model': False, 'use_joint_mlp_projector': True, 'load_from_mlp_projector_checkpoint': False, 'mlp_projector_checkpoint_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin', 'use_linear_normalizer': False, 'normalizer_checkpoint_path': '', 'max_length': 100, 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct'}}}}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():669] starting backend
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():673] sending inform_init request
+2025-07-11 03:58:49,404 INFO    MainThread:3404262 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-07-11 03:58:49,404 INFO    MainThread:3404262 [wandb_init.py:init():686] backend started and connected
+2025-07-11 03:58:49,409 INFO    MainThread:3404262 [wandb_init.py:init():781] updated telemetry
+2025-07-11 03:58:49,436 INFO    MainThread:3404262 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
+2025-07-11 03:58:50,108 INFO    MainThread:3404262 [wandb_init.py:init():867] starting run threads in backend
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_console_start():2451] atexit reg
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_redirect():2299] redirect: wrap_raw
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_redirect():2364] Wrapping output streams.
+2025-07-11 03:58:50,206 INFO    MainThread:3404262 [wandb_run.py:_redirect():2389] Redirects installed.
+2025-07-11 03:58:50,207 INFO    MainThread:3404262 [wandb_init.py:init():911] run started, returning control to user process
+2025-07-11 03:58:50,207 INFO    MainThread:3404262 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld'}
+2025-07-11 20:11:16,628 WARNING MsgRouterThr:3404262 [router.py:message_loop():75] message_loop has been closed

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/files/config.yaml

@@ -0,0 +1,228 @@
+_target_:
+    value: llmbc.workspace.train_mlp_projector_workspace.TrainMlpProjectorWorkspace
+_wandb:
+    value:
+        cli_version: 0.18.6
+        m: []
+        python_version: 3.9.21
+        t:
+            "1":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 83
+                - 98
+            "2":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 83
+                - 98
+            "3":
+                - 13
+                - 15
+                - 16
+                - 23
+                - 55
+                - 61
+            "4": 3.9.21
+            "5": 0.18.6
+            "6": 4.47.1
+            "8":
+                - 5
+            "12": 0.18.6
+            "13": linux-x86_64
+action_dim:
+    value: 4
+checkpoint:
+    value:
+        save_last_ckpt: true
+        save_last_snapshot: false
+        topk:
+            format_str: epoch={epoch:04d}-val_loss={val_loss:.3f}.ckpt
+            k: 5
+            mode: min
+            monitor_key: val_loss
+dataloader:
+    value:
+        batch_size: 8
+        num_workers: 0
+        persistent_workers: false
+        pin_memory: false
+        shuffle: true
+exp_name:
+    value: default
+horizon:
+    value: 1
+llm:
+    value:
+        adaptor_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744
+        causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
+        config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
+        hydra:
+            job:
+                override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct
+            run:
+                dir: data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct
+        load_from_checkpoint: false
+        load_from_mlp_projector_checkpoint: false
+        lora_config:
+            bias: none
+            lora_alpha: 64
+            lora_dropout: 0.05
+            r: 32
+            task_type: CAUSAL_LM
+        max_length: 100
+        mlp_projector_checkpoint_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin
+        model_name: SmolLM2-135M-Instruct
+        name: HuggingFaceTB/SmolLM2-135M-Instruct
+        normalizer_checkpoint_path: ""
+        prompter:
+            _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
+            use_joint_mlp_projector: true
+        use_joint_mlp_projector: true
+        use_linear_normalizer: false
+        use_orig_model: false
+        use_quantization: false
+llm_translator:
+    value:
+        _target_: llmbc.translator.llm_translator.LLMTranslator
+        action_dim: 4
+        cfg:
+            adaptor_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744
+            causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
+            config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
+            hydra:
+                job:
+                    override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct
+                run:
+                    dir: data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct
+            load_from_checkpoint: false
+            load_from_mlp_projector_checkpoint: false
+            lora_config:
+                bias: none
+                lora_alpha: 64
+                lora_dropout: 0.05
+                r: 32
+                task_type: CAUSAL_LM
+            max_length: 100
+            mlp_projector_checkpoint_path: data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin
+            model_name: SmolLM2-135M-Instruct
+            name: HuggingFaceTB/SmolLM2-135M-Instruct
+            normalizer_checkpoint_path: ""
+            prompter:
+                _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
+                use_joint_mlp_projector: true
+            use_joint_mlp_projector: true
+            use_linear_normalizer: false
+            use_orig_model: false
+            use_quantization: false
+        horizon: 1
+        n_action_steps: 1
+        n_obs_steps: 1
+        obs_dim: 9
+logging:
+    value:
+        group: null
+        id: null
+        mode: online
+        name: 2025.07.11-03.58.48_train_mlp_projector_metaworld
+        project: llm_module_training
+        resume: true
+        tags:
+            - train_mlp_projector
+            - metaworld
+            - default
+model_name:
+    value: HuggingFaceTB/SmolLM2-135M-Instruct
+multi_run:
+    value:
+        run_dir: data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld
+        wandb_name_base: 2025.07.11-03.58.48_train_mlp_projector_metaworld
+n_action_steps:
+    value: 1
+n_latency_steps:
+    value: 0
+n_obs_steps:
+    value: 1
+name:
+    value: train_mlp_projector
+obs_dim:
+    value: 9
+optimizer:
+    value:
+        _target_: torch.optim.Adam
+        betas:
+            - 0.95
+            - 0.999
+        eps: 1e-08
+        lr: 0.0001
+        weight_decay: 1e-06
+output_dir:
+    value: /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld
+past_action_visible:
+    value: false
+task:
+    value:
+        action_dim: 4
+        dataset:
+            _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
+            data_path: datasets/metaworld-general-split0.02.pt
+            data_path2: datasets/metaworld-split0.02.pt
+            dummy_normalizer: false
+            horizon: 1
+            obs_eef_target: true
+            pad_after: 0
+            pad_before: 0
+            use_manual_normalizer: false
+            val_ratio: 0.05
+        name: metaworld
+        obs_dim: 9
+task_name:
+    value: metaworld
+training:
+    value:
+        checkpoint_every: 1
+        debug: false
+        device: cuda
+        enable_normalizer: true
+        grad_norm_clip: 1
+        gradient_accumulate_every: 32
+        lr_scheduler: cosine
+        lr_warmup_steps: 10
+        max_train_steps: null
+        max_val_steps: null
+        num_epochs: 1000
+        resume: true
+        sample_every: 1
+        sample_max_batch: 128
+        seed: 42
+        tqdm_interval_sec: 1
+        val_every: 1
+val_dataloader:
+    value:
+        batch_size: 8
+        num_workers: 0
+        persistent_workers: false
+        pin_memory: false
+        shuffle: true

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/files/output.log

@@ -0,0 +1 @@
+                                                                                                             

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/files/wandb-metadata.json

@@ -0,0 +1,54 @@
+{
+  "os": "Linux-5.15.0-101-generic-x86_64-with-glibc2.31",
+  "python": "3.9.21",
+  "startedAt": "2025-07-10T19:58:49.404819Z",
+  "args": [
+    "llm.load_from_checkpoint=False",
+    "llm.load_from_mlp_projector_checkpoint=False",
+    "task=metaworld"
+  ],
+  "program": "/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_mlp_projector_workspace.py",
+  "codePath": "llmbc/workspace/train_mlp_projector_workspace.py",
+  "git": {
+    "remote": "https://github.com/CHYang25/LLM-BC.git",
+    "commit": "527828c43adf72e7a6f3f2857ded760d6aaafe6f"
+  },
+  "email": "chris920325@gmail.com",
+  "root": "/home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld",
+  "host": "rllab1015",
+  "username": "chyang",
+  "executable": "/home/chyang/miniconda3/envs/llm-bc/bin/python3",
+  "codePathLocal": "llmbc/workspace/train_mlp_projector_workspace.py",
+  "cpu_count": 20,
+  "cpu_count_logical": 40,
+  "gpu": "NVIDIA GeForce RTX 4090",
+  "gpu_count": 2,
+  "disk": {
+    "/": {
+      "total": "1967317549056",
+      "used": "1595091705856"
+    }
+  },
+  "memory": {
+    "total": "134535372800"
+  },
+  "cpu": {
+    "count": 20,
+    "countLogical": 40
+  },
+  "gpu_nvidia": [
+    {
+      "name": "NVIDIA GeForce RTX 4090",
+      "memoryTotal": "25757220864",
+      "cudaCores": 16384,
+      "architecture": "Ada"
+    },
+    {
+      "name": "NVIDIA GeForce RTX 4090",
+      "memoryTotal": "25757220864",
+      "cudaCores": 16384,
+      "architecture": "Ada"
+    }
+  ],
+  "cudaVersion": "12.2"
+}

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_step":436999,"epoch":999,"_runtime":58347.223713649,"_timestamp":1.7522358766111119e+09,"val_loss":2.6537208557128906,"_wandb":{"runtime":58347},"grad_norm":2.6950809955596924,"train_loss":2.5322251341708464,"lr":1.3250400887621084e-12,"global_step":436999}

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-core.log

@@ -0,0 +1,14 @@
+{"time":"2025-07-11T03:58:48.802094952+08:00","level":"INFO","msg":"started logging, with flags","port-filename":"/tmp/tmpsa69b4ku/port-3404262.txt","pid":3404262,"debug":false,"disable-analytics":false}
+{"time":"2025-07-11T03:58:48.802117877+08:00","level":"INFO","msg":"FeatureState","shutdownOnParentExitEnabled":false}
+{"time":"2025-07-11T03:58:48.803078444+08:00","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":38279,"Zone":""}}
+{"time":"2025-07-11T03:58:48.803169518+08:00","level":"INFO","msg":"Will exit if parent process dies.","ppid":3404262}
+{"time":"2025-07-11T03:58:48.999953763+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T03:58:49.407252096+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"zfajcmpj","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T03:58:49.515318283+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"zfajcmpj","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:16.62836004+08:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:16.628569115+08:00","level":"INFO","msg":"connection: Close: initiating connection closure","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:16.62860047+08:00","level":"INFO","msg":"server is shutting down"}
+{"time":"2025-07-11T20:11:16.628673237+08:00","level":"INFO","msg":"connection: Close: connection successfully closed","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:17.843841508+08:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:17.843865971+08:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"127.0.0.1:56358"}
+{"time":"2025-07-11T20:11:17.843879231+08:00","level":"INFO","msg":"server is closed"}

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-internal.log

@@ -0,0 +1,96 @@
+{"time":"2025-07-11T03:58:49.407500315+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
+{"time":"2025-07-11T03:58:49.4075215+08:00","level":"INFO","msg":"created symlink","path":"/home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-core.log"}
+{"time":"2025-07-11T03:58:49.515242597+08:00","level":"INFO","msg":"created new stream","id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515306896+08:00","level":"INFO","msg":"stream: started","id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515372436+08:00","level":"INFO","msg":"sender: started","stream_id":"zfajcmpj"}
+{"time":"2025-07-11T03:58:49.515343096+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T03:58:49.515378427+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T03:58:50.111785423+08:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2025-07-11T10:19:30.662765079+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34981->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:19:43.096709986+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34013->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:19:50.683315198+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:19:57.798368435+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58052->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:15.828743949+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52578->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:22.719192496+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:20:43.16402417+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60074->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:20:57.651634305+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:21:25.739292077+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52830->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:21:36.639208833+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:22:26.344907838+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:22:35.741140727+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58829->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:23:31.491730215+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:23:45.744178376+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:39036->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:24:55.746260548+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57274->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:25:01.493387422+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:26:05.748029554+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43891->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:26:31.494518293+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:27:15.088761686+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:28:01.495712857+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:28:25.090345213+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54163->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:29:20.683049743+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000348051,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ykmb1zbab3au\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:29:27.082442683+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00003073,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:29:30.113553628+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000175569,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.113706301+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000345821,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.115848756+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000949262,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.119005923+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00050725,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:30.134183378+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00003329,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:29:31.496836166+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:29:34.136294928+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:47212->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:30:39.503948407+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:31:01.498883211+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:31:47.151814458+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:32:31.500519508+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:32:53.295630902+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:34:01.502180799+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:34:03.224735373+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:35463->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:35:13.048211757+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37851->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:35:31.50265147+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:36:18.703729665+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:36:37.135832426+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:37:26.776550454+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48638->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T10:37:43.279470452+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
+{"time":"2025-07-11T10:38:43.586319317+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1162.90365191,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ykmb1zbab3au\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:38:43.586581237+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1156.50415708,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:38:43.586718446+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.473421569,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586797174+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.471875371,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586784719+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.473381097,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.586960887+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.468301722,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:38:43.587004666+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1153.452813238,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:39:43.592291332+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:40:15.763452594+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:40:49.844091828+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:41:29.285662282+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:41:34.255134979+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp 35.186.228.49:443: connect: connection timed out"}
+{"time":"2025-07-11T10:42:16.052045567+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:43:22.42672178+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:44:52.428073385+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:46:22.429729908+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:47:52.431455398+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
+{"time":"2025-07-11T10:49:13.591546149+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000310986,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"39u0euc3gdqo\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:49:19.991448173+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000419627,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:49:20.113476668+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000669704,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.113666718+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000556595,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.115777548+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000262324,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.119884323+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000767915,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:20.134071176+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.001047034,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:49:22.432201148+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:50:52.434457185+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:52:22.436283572+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:53:52.43745377+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-07-11T10:54:52.979170008+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:32904->35.186.228.49:443: read: connection timed out"}
+{"time":"2025-07-11T10:55:53.226144695+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":999.634939408,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"39u0euc3gdqo\" connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:55:53.226264085+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.235293513,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:56358\")"}
+{"time":"2025-07-11T10:55:53.226387716+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.113322681,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226431815+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.110883112,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226471261+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.113644133,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226468934+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.107317404,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T10:55:53.226674708+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":993.093604107,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
+{"time":"2025-07-11T19:27:48.228136062+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/chyang25-national-taiwan-university/llm_module_training/zfajcmpj/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58754->127.0.0.53:53: i/o timeout"}
+{"time":"2025-07-11T20:11:16.628499237+08:00","level":"INFO","msg":"stream: closing","id":"zfajcmpj"}
+{"time":"2025-07-11T20:11:16.628550137+08:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2025-07-11T20:11:16.62954204+08:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2025-07-11T20:11:17.552805733+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-07-11T20:11:17.843551844+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T20:11:17.843631936+08:00","level":"INFO","msg":"sender: closed","stream_id":"zfajcmpj"}
+{"time":"2025-07-11T20:11:17.843630871+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"zfajcmpj"}}
+{"time":"2025-07-11T20:11:17.843761743+08:00","level":"INFO","msg":"stream: closed","id":"zfajcmpj"}

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug.log

@@ -0,0 +1,27 @@
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Configure stats pid to 3404262
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/workspace/LLM-BC/wandb/settings
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'llmbc/workspace/train_mlp_projector_workspace.py', 'program_abspath': '/home/chyang/workspace/LLM-BC/llmbc/workspace/train_mlp_projector_workspace.py', 'program': '/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_mlp_projector_workspace.py'}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_setup.py:_flush():79] Applying login settings: {}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:_log_setup():533] Logging user logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug.log
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:_log_setup():534] Logging internal logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/logs/debug-internal.log
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():619] calling init triggers
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
+config: {'name': 'train_mlp_projector', '_target_': 'llmbc.workspace.train_mlp_projector_workspace.TrainMlpProjectorWorkspace', 'obs_dim': 9, 'action_dim': 4, 'task_name': 'metaworld', 'exp_name': 'default', 'model_name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'n_latency_steps': 0, 'past_action_visible': False, 'llm_translator': {'_target_': 'llmbc.translator.llm_translator.LLMTranslator', 'cfg': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'use_quantization': False, 'load_from_checkpoint': False, 'adaptor_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744', 'use_orig_model': False, 'use_joint_mlp_projector': True, 'load_from_mlp_projector_checkpoint': False, 'mlp_projector_checkpoint_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin', 'use_linear_normalizer': False, 'normalizer_checkpoint_path': '', 'max_length': 100, 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct'}}}, 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1}, 'dataloader': {'batch_size': 8, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 8, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.Adam', 'lr': 0.0001, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda', 'seed': 42, 'debug': False, 'resume': True, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 10, 'num_epochs': 1000, 'gradient_accumulate_every': 32, 'grad_norm_clip': 1, 'enable_normalizer': True, 'checkpoint_every': 1, 'val_every': 1, 'sample_every': 1, 'sample_max_batch': 128, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'llm_module_training', 'resume': True, 'mode': 'online', 'name': '2025.07.11-03.58.48_train_mlp_projector_metaworld', 'tags': ['train_mlp_projector', 'metaworld', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'val_loss', 'mode': 'min', 'k': 5, 'format_str': 'epoch={epoch:04d}-val_loss={val_loss:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld', 'wandb_name_base': '2025.07.11-03.58.48_train_mlp_projector_metaworld'}, 'task': {'name': 'metaworld', 'obs_dim': 9, 'action_dim': 4, 'dataset': {'_target_': 'llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset', 'data_path': 'datasets/metaworld-general-split0.02.pt', 'data_path2': 'datasets/metaworld-split0.02.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}}, 'llm': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'use_quantization': False, 'load_from_checkpoint': False, 'adaptor_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744', 'use_orig_model': False, 'use_joint_mlp_projector': True, 'load_from_mlp_projector_checkpoint': False, 'mlp_projector_checkpoint_path': 'data/outputs/2025.07.05/10.04.26_train_llm_lowdim_PegInsertionSide-v1/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-PegInsertionSide-v1/checkpoint-9744/mlp_projector.bin', 'use_linear_normalizer': False, 'normalizer_checkpoint_path': '', 'max_length': 100, 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.07.11/03.58.46_HuggingFaceTB/SmolLM2-135M-Instruct'}}}}
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():669] starting backend
+2025-07-11 03:58:49,403 INFO    MainThread:3404262 [wandb_init.py:init():673] sending inform_init request
+2025-07-11 03:58:49,404 INFO    MainThread:3404262 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-07-11 03:58:49,404 INFO    MainThread:3404262 [wandb_init.py:init():686] backend started and connected
+2025-07-11 03:58:49,409 INFO    MainThread:3404262 [wandb_init.py:init():781] updated telemetry
+2025-07-11 03:58:49,436 INFO    MainThread:3404262 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
+2025-07-11 03:58:50,108 INFO    MainThread:3404262 [wandb_init.py:init():867] starting run threads in backend
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_console_start():2451] atexit reg
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_redirect():2299] redirect: wrap_raw
+2025-07-11 03:58:50,205 INFO    MainThread:3404262 [wandb_run.py:_redirect():2364] Wrapping output streams.
+2025-07-11 03:58:50,206 INFO    MainThread:3404262 [wandb_run.py:_redirect():2389] Redirects installed.
+2025-07-11 03:58:50,207 INFO    MainThread:3404262 [wandb_init.py:init():911] run started, returning control to user process
+2025-07-11 03:58:50,207 INFO    MainThread:3404262 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.07.11/03.58.46_train_mlp_projector_metaworld'}
+2025-07-11 20:11:16,628 WARNING MsgRouterThr:3404262 [router.py:message_loop():75] message_loop has been closed

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/run-20250711_035849-zfajcmpj/run-zfajcmpj.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a9a209cef39ed4cb49ce6577b50ce8a8e8e7291e09d5e11947465c6ca5c719
+size 254644341

2025.07.11/03.58.46_train_mlp_projector_metaworld/wandb/wandb-resume.json

@@ -0,0 +1 @@
+{"run_id": "zfajcmpj"}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/.hydra/config.yaml

@@ -0,0 +1,116 @@
+name: train_llm_lowdim
+_target_: llmbc.workspace.train_llm_workspace.TrainLLMWorkspace
+obs_dim: ${task.obs_dim}
+action_dim: ${task.action_dim}
+horizon: 1
+n_obs_steps: 1
+n_action_steps: 1
+task_name: ${task.name}
+exp_name: train llm
+model_name: ${llm.name}
+use_quantization: ${llm.use_quantization}
+lora_config: ${llm.lora_config}
+dataset:
+  test_data_ratio: 0.01
+debug: false
+training:
+  seed: 42
+  per_device_train_batch_size: 1
+  per_device_eval_batch_size: 1
+  gradient_accumulation_steps: 32
+  optim: paged_adamw_32bit
+  num_train_epochs: 3
+  eval_strategy: steps
+  logging_steps: 1
+  warmup_steps: 10
+  logging_strategy: steps
+  learning_rate: 5.0e-05
+  fp16: false
+  bf16: true
+  tf32: true
+  group_by_length: true
+  report_to: wandb
+  save_steps: 5000
+  eval_steps: 10
+  use_joint_mlp_projector: ${llm.use_joint_mlp_projector}
+  joint_obs_action_mlp_lr: 1.0e-06
+trainer:
+  obs_dim: ${obs_dim}
+  action_dim: ${action_dim}
+  use_joint_mlp_projector: ${llm.use_joint_mlp_projector}
+  max_seq_length: ${llm.max_length}
+  dataset_text_field: text
+  packing: false
+logging:
+  project: llm_module_finetuning
+  resume: true
+  mode: online
+  name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
+  tags:
+  - ${name}
+  - ${task_name}
+  - ${exp_name}
+  id: null
+  group: null
+multi_run:
+  run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+  wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
+task:
+  name: box-close-v2
+  obs_dim: 9
+  action_dim: 4
+  env_runner:
+    _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner
+    env_name: llf-metaworld-box-close-v2
+    max_steps: 30
+    n_obs_steps: ${n_obs_steps}
+    n_action_steps: ${n_action_steps}
+    instruction_type: b
+    feedback_type:
+    - hp
+    - hn
+    - fp
+    visual: false
+  dataset:
+    _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
+    data_path: datasets/box-close-v2-general-shuf.pt
+    data_path2: datasets/box-close-v2-shuf.pt
+    horizon: ${horizon}
+    pad_before: ${eval:'${n_obs_steps}-1'}
+    pad_after: ${eval:'${n_action_steps}-1'}
+    obs_eef_target: true
+    use_manual_normalizer: false
+    val_ratio: 0.05
+    dummy_normalizer: false
+  instructor:
+    _target_: llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor
+llm:
+  name: HuggingFaceTB/SmolLM2-135M-Instruct
+  model_name: SmolLM2-135M-Instruct
+  use_raw_llm: false
+  use_quantization: false
+  load_from_checkpoint: false
+  adaptor_path: data/outputs/2025.06.02/17.59.17_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-4572
+  use_orig_model: false
+  use_joint_mlp_projector: true
+  load_from_mlp_projector_checkpoint: true
+  mlp_projector_checkpoint_path: data/outputs/2025.08.11/10.45.37_train_mlp_projector_metaworld/checkpoints/latest.ckpt
+  use_linear_normalizer: false
+  normalizer_checkpoint_path: ''
+  max_length: 100
+  config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
+  causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
+  lora_config:
+    r: 32
+    lora_alpha: 64
+    lora_dropout: 0.05
+    bias: none
+    task_type: CAUSAL_LM
+  prompter:
+    _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
+    use_joint_mlp_projector: true
+  hydra:
+    job:
+      override_dirname: ${model_name}
+    run:
+      dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/.hydra/hydra.yaml

@@ -0,0 +1,156 @@
+hydra:
+  run:
+    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+  sweep:
+    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: train_llm_workspace
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train_llm_workspace
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.2'
+    cwd: /home/chyang/workspace/LLM-BC
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/chyang/workspace/LLM-BC/llmbc/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2
+    choices:
+      llm: smollm2-135m-instruct
+      task: box-close-v2
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cd6d3faca143d2accf8d665333d487de6b5935f500192453df73ca9ac9edbe
+size 39131224

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cd6d3faca143d2accf8d665333d487de6b5935f500192453df73ca9ac9edbe
+size 39131224

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "action_dim": 4,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama_lowdim",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "obs_dim": 9,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "vocab_size": 49152
+}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d558f1cb0bd8cea4060c58a14cee65842964fce083d2036d806b3671bc93037
+size 1363904

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a467def6b34ea080f4fed81d3c60479914c41d0fba0607a02498531ba4bd676
+size 81126202

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3863444d190337b6d93e64a927a8f4ab343661adc8a292dd3c1275a824b6127
+size 14244

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20e4e7ef5d17f96fcf786acfa68c77beeca89e90512d77f8fe8789f0cbfa27f
+size 1064

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-4116/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dd06759f6c865a485b284241282a608ec0ed1bf5acdfffb221641adc03ca3f
+size 5944

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a2548541cdb7d3e3c2682c3a79ce762ff6b8f29ae9c59c9337a2f59259b844
+size 4514

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/train_llm_workspace.log

@@ -0,0 +1,5 @@
+[2025-08-14 00:51:53,821][datasets.arrow_dataset][WARNING] - Setting TOKENIZERS_PARALLELISM=false for forked processes.
+[2025-08-14 00:52:03,225][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -I/home/chyang/miniconda3/envs/llm-bc/include -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -fPIC -c /tmp/tmp_q7fesb1/test.c -o /tmp/tmp_q7fesb1/test.o
+[2025-08-14 00:52:03,284][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat /tmp/tmp_q7fesb1/test.o -laio -o /tmp/tmp_q7fesb1/a.out
+[2025-08-14 00:52:03,963][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -I/home/chyang/miniconda3/envs/llm-bc/include -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -fPIC -c /tmp/tmpzb6l_1ze/test.c -o /tmp/tmpzb6l_1ze/test.o
+[2025-08-14 00:52:04,022][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat /tmp/tmpzb6l_1ze/test.o -L/usr/local/cuda -L/usr/local/cuda/lib64 -lcufile -o /tmp/tmpzb6l_1ze/a.out

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/debug-internal.log

@@ -0,0 +1,19 @@
+{"time":"2025-08-14T00:47:04.401718487+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
+{"time":"2025-08-14T00:47:04.401726265+08:00","level":"INFO","msg":"created symlink","path":"/home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/run-20250814_004704-1q0db7hd/logs/debug-core.log"}
+{"time":"2025-08-14T00:47:04.505618343+08:00","level":"INFO","msg":"created new stream","id":"1q0db7hd"}
+{"time":"2025-08-14T00:47:04.505645659+08:00","level":"INFO","msg":"stream: started","id":"1q0db7hd"}
+{"time":"2025-08-14T00:47:04.505666637+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"1q0db7hd"}}
+{"time":"2025-08-14T00:47:04.50566955+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"1q0db7hd"}}
+{"time":"2025-08-14T00:47:04.505688208+08:00","level":"INFO","msg":"sender: started","stream_id":"1q0db7hd"}
+{"time":"2025-08-14T00:47:05.270983992+08:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2025-08-14T05:27:50.683069117+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-08-14T05:59:20.737637353+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2025-08-14T19:19:00.407201107+08:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2025-08-14T19:19:00.407729048+08:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2025-08-14T19:19:01.407607502+08:00","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"saving job artifact","runtime_seconds":0.334437898},{"desc":"uploading output.log","runtime_seconds":0.083104417,"progress":"685.4KB/685.4KB"},{"desc":"uploading config.yaml","runtime_seconds":0.083092238,"progress":"15.8KB/15.8KB"}],"total_operations":3}}
+{"time":"2025-08-14T19:19:02.502050556+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2025-08-14T19:19:04.022331101+08:00","level":"INFO","msg":"stream: closing","id":"1q0db7hd"}
+{"time":"2025-08-14T19:19:04.022347454+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"1q0db7hd"}}
+{"time":"2025-08-14T19:19:04.022362876+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"1q0db7hd"}}
+{"time":"2025-08-14T19:19:04.022371272+08:00","level":"INFO","msg":"sender: closed","stream_id":"1q0db7hd"}
+{"time":"2025-08-14T19:19:04.022412635+08:00","level":"INFO","msg":"stream: closed","id":"1q0db7hd"}

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/debug.log

@@ -0,0 +1,35 @@
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Configure stats pid to 1338151
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/workspace/LLM-BC/wandb/settings
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'llmbc/workspace/train_llm_workspace.py', 'program_abspath': '/home/chyang/workspace/LLM-BC/llmbc/workspace/train_llm_workspace.py', 'program': '/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_llm_workspace.py'}
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_setup.py:_flush():79] Applying login settings: {}
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:_log_setup():533] Logging user logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/run-20250814_004704-1q0db7hd/logs/debug.log
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:_log_setup():534] Logging internal logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/run-20250814_004704-1q0db7hd/logs/debug-internal.log
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:init():619] calling init triggers
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
+config: {'name': 'train_llm_lowdim', '_target_': 'llmbc.workspace.train_llm_workspace.TrainLLMWorkspace', 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'task_name': 'box-close-v2', 'exp_name': 'train llm', 'model_name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'use_quantization': False, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'dataset': {'test_data_ratio': 0.01}, 'debug': False, 'training': {'seed': 42, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 32, 'optim': 'paged_adamw_32bit', 'num_train_epochs': 3, 'eval_strategy': 'steps', 'logging_steps': 1, 'warmup_steps': 10, 'logging_strategy': 'steps', 'learning_rate': 5e-05, 'fp16': False, 'bf16': True, 'tf32': True, 'group_by_length': True, 'report_to': 'wandb', 'save_steps': 5000, 'eval_steps': 10, 'use_joint_mlp_projector': True, 'joint_obs_action_mlp_lr': 1e-06}, 'trainer': {'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'max_seq_length': 100, 'dataset_text_field': 'text', 'packing': False}, 'logging': {'project': 'llm_module_finetuning', 'resume': True, 'mode': 'online', 'name': '2025.08.14-00.47.03_train_llm_lowdim_box-close-v2', 'tags': ['train_llm_lowdim', 'box-close-v2', 'train llm'], 'id': None, 'group': None}, 'multi_run': {'run_dir': 'data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2', 'wandb_name_base': '2025.08.14-00.47.03_train_llm_lowdim_box-close-v2'}, 'task': {'name': 'box-close-v2', 'obs_dim': 9, 'action_dim': 4, 'env_runner': {'_target_': 'llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner', 'env_name': 'llf-metaworld-box-close-v2', 'max_steps': 30, 'n_obs_steps': 1, 'n_action_steps': 1, 'instruction_type': 'b', 'feedback_type': ['hp', 'hn', 'fp'], 'visual': False}, 'dataset': {'_target_': 'llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset', 'data_path': 'datasets/box-close-v2-general-shuf.pt', 'data_path2': 'datasets/box-close-v2-shuf.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}, 'instructor': {'_target_': 'llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor'}}, 'llm': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'use_raw_llm': False, 'use_quantization': False, 'load_from_checkpoint': False, 'adaptor_path': 'data/outputs/2025.06.02/17.59.17_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-4572', 'use_orig_model': False, 'use_joint_mlp_projector': True, 'load_from_mlp_projector_checkpoint': True, 'mlp_projector_checkpoint_path': 'data/outputs/2025.08.11/10.45.37_train_mlp_projector_metaworld/checkpoints/latest.ckpt', 'use_linear_normalizer': False, 'normalizer_checkpoint_path': '', 'max_length': 100, 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.08.14/00.47.03_HuggingFaceTB/SmolLM2-135M-Instruct'}}}}
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:init():669] starting backend
+2025-08-14 00:47:04,399 INFO    MainThread:1338151 [wandb_init.py:init():673] sending inform_init request
+2025-08-14 00:47:04,400 INFO    MainThread:1338151 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-08-14 00:47:04,400 INFO    MainThread:1338151 [wandb_init.py:init():686] backend started and connected
+2025-08-14 00:47:04,406 INFO    MainThread:1338151 [wandb_init.py:init():781] updated telemetry
+2025-08-14 00:47:04,429 INFO    MainThread:1338151 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
+2025-08-14 00:47:05,267 INFO    MainThread:1338151 [wandb_init.py:init():867] starting run threads in backend
+2025-08-14 00:47:05,380 INFO    MainThread:1338151 [wandb_run.py:_console_start():2451] atexit reg
+2025-08-14 00:47:05,380 INFO    MainThread:1338151 [wandb_run.py:_redirect():2299] redirect: wrap_raw
+2025-08-14 00:47:05,380 INFO    MainThread:1338151 [wandb_run.py:_redirect():2364] Wrapping output streams.
+2025-08-14 00:47:05,380 INFO    MainThread:1338151 [wandb_run.py:_redirect():2389] Redirects installed.
+2025-08-14 00:47:05,381 INFO    MainThread:1338151 [wandb_init.py:init():911] run started, returning control to user process
+2025-08-14 00:52:11,394 INFO    MainThread:1338151 [wandb_run.py:_config_callback():1389] config_cb None None {'peft_config': {'default': {'task_type': 'CAUSAL_LM', 'peft_type': <PeftType.LORA: 'LORA'>, 'auto_mapping': None, 'base_model_name_or_path': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'revision': None, 'inference_mode': False, 'r': 32, 'target_modules': {'o_proj', 'v_proj', 'q_proj', 'k_proj', 'up_proj', 'down_proj', 'gate_proj'}, 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.05, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'loftq_config': {}, 'eva_config': None, 'use_dora': False, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False}}, 'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'vocab_size': 49152, 'max_position_embeddings': 8192, 'hidden_size': 576, 'intermediate_size': 1536, 'num_hidden_layers': 30, 'num_attention_heads': 9, 'num_key_value_heads': 3, 'hidden_act': 'silu', 'initializer_range': 0.041666666666666664, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': False, 'rope_theta': 100000, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 64, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 2, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'HuggingFaceTB/SmolLM2-135M-Instruct', '_attn_implementation_autoset': True, 'transformers_version': '4.47.1', 'is_llama_config': True, 'model_type': 'llama_lowdim', 'rope_interleaved': False, 'transformers.js_config': {'kv_cache_dtype': {'q4f16': 'float16', 'fp16': 'float16'}}, 'output_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 32, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 10, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/runs/Aug14_00-52-02_A6000-2', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': True, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 10, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'dataset_text_field': 'text', 'packing': False, 'max_seq_length': 100, 'dataset_num_proc': None, 'dataset_batch_size': 1000, 'model_init_kwargs': None, 'dataset_kwargs': {}, 'eval_packing': None, 'num_of_sequences': 1024, 'chars_per_token': '<CHARS_PER_TOKEN>', 'use_liger': False, 'joint_obs_action_mlp_lr': 1e-06, 'obs_mlp_lr': None, 'action_mlp_lr': None}
+2025-08-14 00:52:11,398 INFO    MainThread:1338151 [wandb_config.py:__setitem__():154] config set model/num_parameters = 144624384 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x76a657977a30>>
+2025-08-14 00:52:11,399 INFO    MainThread:1338151 [wandb_run.py:_config_callback():1389] config_cb model/num_parameters 144624384 None
+2025-08-14 19:19:00,406 INFO    MainThread:1338151 [wandb_run.py:_finish():2146] finishing run chyang25-national-taiwan-university/llm_module_finetuning/1q0db7hd
+2025-08-14 19:19:00,406 INFO    MainThread:1338151 [wandb_run.py:_atexit_cleanup():2414] got exitcode: 0
+2025-08-14 19:19:00,406 INFO    MainThread:1338151 [wandb_run.py:_restore():2396] restore
+2025-08-14 19:19:00,406 INFO    MainThread:1338151 [wandb_run.py:_restore():2402] restore done
+2025-08-14 19:19:04,016 INFO    MainThread:1338151 [wandb_run.py:_footer_history_summary_info():3963] rendering history
+2025-08-14 19:19:04,017 INFO    MainThread:1338151 [wandb_run.py:_footer_history_summary_info():3995] rendering summary
+2025-08-14 19:19:04,021 INFO    MainThread:1338151 [wandb_run.py:_footer_sync_info():3922] logging synced files

2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/wandb/run-20250814_004704-1q0db7hd/files/config.yaml

@@ -0,0 +1,748 @@
+_attn_implementation_autoset:
+    value: true
+_name_or_path:
+    value: HuggingFaceTB/SmolLM2-135M-Instruct
+_target_:
+    value: llmbc.workspace.train_llm_workspace.TrainLLMWorkspace
+_wandb:
+    value:
+        cli_version: 0.18.6
+        m:
+            - "1": eval/runtime
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "1": eval/samples_per_second
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": eval/steps_per_second
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/grad_norm
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/learning_rate
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": eval/loss
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/loss
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/epoch
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+        python_version: 3.9.20
+        t:
+            "1":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 84
+                - 98
+            "2":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 84
+                - 98
+            "3":
+                - 2
+                - 7
+                - 13
+                - 15
+                - 16
+                - 19
+                - 23
+                - 55
+                - 62
+                - 66
+            "4": 3.9.20
+            "5": 0.18.6
+            "6": 4.47.1
+            "8":
+                - 5
+            "9":
+                "1": transformers_trainer
+            "12": 0.18.6
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+action_dim:
+    value: 4
+action_mlp_lr:
+    value: null
+adafactor:
+    value: false
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+add_cross_attention:
+    value: false
+architectures:
+    value:
+        - LlamaForCausalLM
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: false
+bad_words_ids:
+    value: null
+batch_eval_metrics:
+    value: false
+begin_suppress_tokens:
+    value: null
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 1
+chars_per_token:
+    value: <CHARS_PER_TOKEN>
+chunk_size_feed_forward:
+    value: 0
+cross_attention_hidden_size:
+    value: null
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+dataset:
+    value:
+        test_data_ratio: 0.01
+dataset_batch_size:
+    value: 1000
+dataset_num_proc:
+    value: null
+dataset_text_field:
+    value: text
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+decoder_start_token_id:
+    value: null
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+dispatch_batches:
+    value: null
+diversity_penalty:
+    value: 0
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_sample:
+    value: false
+do_train:
+    value: false
+early_stopping:
+    value: false
+encoder_no_repeat_ngram_size:
+    value: 0
+eos_token_id:
+    value: 2
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_packing:
+    value: null
+eval_steps:
+    value: 10
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+evaluation_strategy:
+    value: null
+exp_name:
+    value: train llm
+exponential_decay_length_penalty:
+    value: null
+finetuning_task:
+    value: null
+forced_bos_token_id:
+    value: null
+forced_eos_token_id:
+    value: null
+fp16:
+    value: false
+fp16_backend:
+    value: auto
+fp16_full_eval:
+    value: false
+fp16_opt_level:
+    value: O1
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+fsdp_min_num_params:
+    value: 0
+fsdp_transformer_layer_cls_to_wrap:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 32
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+group_by_length:
+    value: true
+half_precision_backend:
+    value: auto
+head_dim:
+    value: 64
+hidden_act:
+    value: silu
+hidden_size:
+    value: 576
+horizon:
+    value: 1
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_inputs_for_metrics:
+    value: false
+include_num_input_tokens_seen:
+    value: false
+include_tokens_per_second:
+    value: false
+initializer_range:
+    value: 0.041666666666666664
+intermediate_size:
+    value: 1536
+is_decoder:
+    value: false
+is_encoder_decoder:
+    value: false
+is_llama_config:
+    value: true
+jit_mode_eval:
+    value: false
+joint_obs_action_mlp_lr:
+    value: 1e-06
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+learning_rate:
+    value: 5e-05
+length_column_name:
+    value: length
+length_penalty:
+    value: 1
+llm:
+    value:
+        adaptor_path: data/outputs/2025.06.02/17.59.17_train_llm_lowdim_sweep-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-sweep-v2/checkpoint-4572
+        causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
+        config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
+        hydra:
+            job:
+                override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct
+            run:
+                dir: data/outputs/2025.08.14/00.47.03_HuggingFaceTB/SmolLM2-135M-Instruct
+        load_from_checkpoint: false
+        load_from_mlp_projector_checkpoint: true
+        lora_config:
+            bias: none
+            lora_alpha: 64
+            lora_dropout: 0.05
+            r: 32
+            task_type: CAUSAL_LM
+        max_length: 100
+        mlp_projector_checkpoint_path: data/outputs/2025.08.11/10.45.37_train_mlp_projector_metaworld/checkpoints/latest.ckpt
+        model_name: SmolLM2-135M-Instruct
+        name: HuggingFaceTB/SmolLM2-135M-Instruct
+        normalizer_checkpoint_path: ""
+        prompter:
+            _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
+            use_joint_mlp_projector: true
+        use_joint_mlp_projector: true
+        use_linear_normalizer: false
+        use_orig_model: false
+        use_quantization: false
+        use_raw_llm: false
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: 0
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging:
+    value:
+        group: null
+        id: null
+        mode: online
+        name: 2025.08.14-00.47.03_train_llm_lowdim_box-close-v2
+        project: llm_module_finetuning
+        resume: true
+        tags:
+            - train_llm_lowdim
+            - box-close-v2
+            - train llm
+logging_dir:
+    value: /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/runs/Aug14_00-52-02_A6000-2
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 1
+logging_strategy:
+    value: steps
+lora_config:
+    value:
+        bias: none
+        lora_alpha: 64
+        lora_dropout: 0.05
+        r: 32
+        task_type: CAUSAL_LM
+lr_scheduler_type:
+    value: linear
+max_grad_norm:
+    value: 1
+max_length:
+    value: 20
+max_position_embeddings:
+    value: 8192
+max_seq_length:
+    value: 100
+max_steps:
+    value: -1
+metric_for_best_model:
+    value: null
+min_length:
+    value: 0
+mlp_bias:
+    value: false
+model/num_parameters:
+    value: 144624384
+model_init_kwargs:
+    value: null
+model_name:
+    value: HuggingFaceTB/SmolLM2-135M-Instruct
+model_type:
+    value: llama_lowdim
+mp_parameters:
+    value: ""
+multi_run:
+    value:
+        run_dir: data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2
+        wandb_name_base: 2025.08.14-00.47.03_train_llm_lowdim_box-close-v2
+n_action_steps:
+    value: 1
+n_obs_steps:
+    value: 1
+name:
+    value: train_llm_lowdim
+neftune_noise_alpha:
+    value: null
+no_cuda:
+    value: false
+no_repeat_ngram_size:
+    value: 0
+num_attention_heads:
+    value: 9
+num_beam_groups:
+    value: 1
+num_beams:
+    value: 1
+num_hidden_layers:
+    value: 30
+num_key_value_heads:
+    value: 3
+num_of_sequences:
+    value: 1024
+num_return_sequences:
+    value: 1
+num_train_epochs:
+    value: 3
+obs_dim:
+    value: 9
+obs_mlp_lr:
+    value: null
+optim:
+    value: paged_adamw_32bit
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2
+output_hidden_states:
+    value: false
+output_scores:
+    value: false
+overwrite_output_dir:
+    value: false
+packing:
+    value: false
+pad_token_id:
+    value: 2
+past_index:
+    value: -1
+peft_config:
+    value:
+        default:
+            auto_mapping: null
+            base_model_name_or_path: HuggingFaceTB/SmolLM2-135M-Instruct
+            bias: none
+            eva_config: null
+            exclude_modules: null
+            fan_in_fan_out: false
+            inference_mode: false
+            init_lora_weights: true
+            layer_replication: null
+            layers_pattern: null
+            layers_to_transform: null
+            lora_alpha: 64
+            lora_bias: false
+            lora_dropout: 0.05
+            megatron_config: null
+            megatron_core: megatron.core
+            modules_to_save: null
+            peft_type: LORA
+            r: 32
+            revision: null
+            runtime_config:
+                ephemeral_gpu_offload: false
+            target_modules:
+                - o_proj
+                - v_proj
+                - q_proj
+                - k_proj
+                - up_proj
+                - down_proj
+                - gate_proj
+            task_type: CAUSAL_LM
+            use_dora: false
+            use_rslora: false
+per_device_eval_batch_size:
+    value: 1
+per_device_train_batch_size:
+    value: 1
+per_gpu_eval_batch_size:
+    value: null
+per_gpu_train_batch_size:
+    value: null
+prediction_loss_only:
+    value: false
+prefix:
+    value: null
+pretraining_tp:
+    value: 1
+problem_type:
+    value: null
+push_to_hub:
+    value: false
+push_to_hub_model_id:
+    value: null
+push_to_hub_organization:
+    value: null
+push_to_hub_token:
+    value: <PUSH_TO_HUB_TOKEN>
+ray_scope:
+    value: last
+remove_invalid_values:
+    value: false
+remove_unused_columns:
+    value: true
+repetition_penalty:
+    value: 1
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+return_dict_in_generate:
+    value: false
+rms_norm_eps:
+    value: 1e-05
+rope_interleaved:
+    value: false
+rope_scaling:
+    value: null
+rope_theta:
+    value: 100000
+run_name:
+    value: /home/chyang/workspace/LLM-BC/data/outputs/2025.08.14/00.47.03_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_safetensors:
+    value: true
+save_steps:
+    value: 5000
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+sep_token_id:
+    value: null
+skip_memory_metrics:
+    value: true
+split_batches:
+    value: null
+suppress_tokens:
+    value: null
+task:
+    value:
+        action_dim: 4
+        dataset:
+            _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
+            data_path: datasets/box-close-v2-general-shuf.pt
+            data_path2: datasets/box-close-v2-shuf.pt
+            dummy_normalizer: false
+            horizon: 1
+            obs_eef_target: true
+            pad_after: 0
+            pad_before: 0
+            use_manual_normalizer: false
+            val_ratio: 0.05
+        env_runner:
+            _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner
+            env_name: llf-metaworld-box-close-v2
+            feedback_type:
+                - hp
+                - hn
+                - fp
+            instruction_type: b
+            max_steps: 30
+            n_action_steps: 1
+            n_obs_steps: 1
+            visual: false
+        instructor:
+            _target_: llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor
+        name: box-close-v2
+        obs_dim: 9
+task_name:
+    value: box-close-v2
+task_specific_params:
+    value: null
+temperature:
+    value: 1
+tf_legacy_loss:
+    value: false
+tf32:
+    value: true
+tie_encoder_decoder:
+    value: false
+tie_word_embeddings:
+    value: true
+tokenizer_class:
+    value: null
+top_k:
+    value: 50
+top_p:
+    value: 1
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_dtype:
+    value: bfloat16
+torch_empty_cache_steps:
+    value: null
+torchdynamo:
+    value: null
+torchscript:
+    value: false
+tpu_metrics_debug:
+    value: false
+tpu_num_cores:
+    value: null
+trainer:
+    value:
+        action_dim: 4
+        dataset_text_field: text
+        max_seq_length: 100
+        obs_dim: 9
+        packing: false
+        use_joint_mlp_projector: true
+training:
+    value:
+        bf16: true
+        eval_steps: 10
+        eval_strategy: steps
+        fp16: false
+        gradient_accumulation_steps: 32
+        group_by_length: true
+        joint_obs_action_mlp_lr: 1e-06
+        learning_rate: 5e-05
+        logging_steps: 1
+        logging_strategy: steps
+        num_train_epochs: 3
+        optim: paged_adamw_32bit
+        per_device_eval_batch_size: 1
+        per_device_train_batch_size: 1
+        report_to: wandb
+        save_steps: 5000
+        seed: 42
+        tf32: true
+        use_joint_mlp_projector: true
+        warmup_steps: 10
+transformers.js_config:
+    value:
+        kv_cache_dtype:
+            fp16: float16
+            q4f16: float16
+transformers_version:
+    value: 4.47.1
+typical_p:
+    value: 1
+use_bfloat16:
+    value: false
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_ipex:
+    value: false
+use_joint_mlp_projector:
+    value: true
+use_legacy_prediction_loop:
+    value: false
+use_liger:
+    value: false
+use_liger_kernel:
+    value: false
+use_mps_device:
+    value: false
+use_quantization:
+    value: false
+vocab_size:
+    value: 49152
+warmup_ratio:
+    value: 0
+warmup_steps:
+    value: 10
+weight_decay:
+    value: 0