diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..105e73f0c82fa9e90cf7ba9a377f058986c82a71 --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for battery_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 18:02:39/eval_log.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 18:02:39/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..8873f2849aaa1e8b2b54052690e246d047313e49 --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 18:02:39/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for battery_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 18:02:39 + diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:52/eval_log.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:52/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2a1d1c5d8f62a44f3a7b351df102eeb55f867822 --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:52/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for battery_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:30:52 + diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..8e302e711412f71541a39571989e1b322d7d2653 --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt @@ -0,0 +1,47 @@ +Eval log for battery_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:36:20 + +episode_id=0, seed=100004, result=Fail +episode_id=1, seed=100006, result=Fail +episode_id=2, seed=100009, result=Fail +episode_id=3, seed=100015, result=Fail +episode_id=4, seed=100017, result=Fail +episode_id=5, seed=100021, result=Fail +episode_id=6, seed=100022, result=Fail +episode_id=7, seed=100026, result=Success +episode_id=8, seed=100027, result=Fail +episode_id=9, seed=100030, result=Fail +episode_id=10, seed=100033, result=Fail +episode_id=11, seed=100035, result=Fail +episode_id=12, seed=100036, result=Fail +episode_id=13, seed=100039, result=Fail +episode_id=14, seed=100040, result=Fail +episode_id=15, seed=100041, result=Success +episode_id=16, seed=100045, result=Success +episode_id=17, seed=100046, result=Fail +episode_id=18, seed=100049, result=Fail +episode_id=19, seed=100051, result=Fail +episode_id=20, seed=100058, result=Success +episode_id=21, seed=100063, result=Fail +episode_id=22, seed=100065, result=Success +episode_id=23, seed=100074, result=Fail +episode_id=24, seed=100075, result=Fail +episode_id=25, seed=100077, result=Fail +episode_id=26, seed=100078, result=Fail +episode_id=27, seed=100084, result=Fail +episode_id=28, seed=100089, result=Fail +episode_id=29, seed=100099, result=Fail +episode_id=30, seed=100101, result=Fail +episode_id=31, seed=100103, result=Fail +episode_id=32, seed=100104, result=Fail +episode_id=33, seed=100106, result=Fail +episode_id=34, seed=100107, result=Fail +episode_id=35, seed=100111, result=Fail +episode_id=36, seed=100112, result=Fail +episode_id=37, seed=100115, result=Fail +episode_id=38, seed=100123, result=Fail +episode_id=39, seed=100124, result=Success +episode_id=40, seed=100126, result=Fail +episode_id=41, seed=100127, result=Success +episode_id=42, seed=100136, result=Fail +episode_id=43, seed=100141, result=Fail diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/_result.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..bab8a38e7354b99cb9f6f15dec18b0d9510447ff --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-17 11:14:17 + +Instruction Type: unseen + +Success Rate: 0.1 + +Reward: 0.0 diff --git a/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/eval_log.txt b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..427c0281a15732a9f853f6fe7f4826a87e7930a4 --- /dev/null +++ b/eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/eval_log.txt @@ -0,0 +1,103 @@ +Eval log for battery_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:14:17 + +episode_id=0, seed=100004, result=Fail +episode_id=1, seed=100006, result=Fail +episode_id=2, seed=100009, result=Fail +episode_id=3, seed=100015, result=Fail +episode_id=4, seed=100017, result=Fail +episode_id=5, seed=100020, result=Fail +episode_id=6, seed=100021, result=Fail +episode_id=7, seed=100022, result=Fail +episode_id=8, seed=100026, result=Fail +episode_id=9, seed=100027, result=Fail +episode_id=10, seed=100033, result=Fail +episode_id=11, seed=100035, result=Fail +episode_id=12, seed=100036, result=Fail +episode_id=13, seed=100039, result=Fail +episode_id=14, seed=100040, result=Fail +episode_id=15, seed=100041, result=Fail +episode_id=16, seed=100045, result=Fail +episode_id=17, seed=100046, result=Fail +episode_id=18, seed=100049, result=Fail +episode_id=19, seed=100051, result=Fail +episode_id=20, seed=100058, result=Fail +episode_id=21, seed=100063, result=Fail +episode_id=22, seed=100065, result=Success +episode_id=23, seed=100074, result=Fail +episode_id=24, seed=100075, result=Fail +episode_id=25, seed=100077, result=Fail +episode_id=26, seed=100078, result=Fail +episode_id=27, seed=100084, result=Fail +episode_id=28, seed=100089, result=Fail +episode_id=29, seed=100094, result=Fail +episode_id=30, seed=100099, result=Fail +episode_id=31, seed=100101, result=Fail +episode_id=32, seed=100103, result=Fail +episode_id=33, seed=100104, result=Fail +episode_id=34, seed=100106, result=Success +episode_id=35, seed=100107, result=Success +episode_id=36, seed=100109, result=Fail +episode_id=37, seed=100111, result=Fail +episode_id=38, seed=100112, result=Fail +episode_id=39, seed=100113, result=Fail +episode_id=40, seed=100115, result=Fail +episode_id=41, seed=100123, result=Fail +episode_id=42, seed=100124, result=Success +episode_id=43, seed=100126, result=Fail +episode_id=44, seed=100127, result=Fail +episode_id=45, seed=100136, result=Fail +episode_id=46, seed=100141, result=Success +episode_id=47, seed=100142, result=Fail +episode_id=48, seed=100144, result=Fail +episode_id=49, seed=100146, result=Fail +episode_id=50, seed=100147, result=Fail +episode_id=51, seed=100148, result=Fail +episode_id=52, seed=100151, result=Fail +episode_id=53, seed=100154, result=Success +episode_id=54, seed=100155, result=Fail +episode_id=55, seed=100157, result=Fail +episode_id=56, seed=100161, result=Fail +episode_id=57, seed=100163, result=Fail +episode_id=58, seed=100167, result=Success +episode_id=59, seed=100172, result=Fail +episode_id=60, seed=100174, result=Fail +episode_id=61, seed=100175, result=Fail +episode_id=62, seed=100176, result=Fail +episode_id=63, seed=100179, result=Fail +episode_id=64, seed=100180, result=Fail +episode_id=65, seed=100184, result=Success +episode_id=66, seed=100187, result=Fail +episode_id=67, seed=100190, result=Fail +episode_id=68, seed=100192, result=Fail +episode_id=69, seed=100193, result=Fail +episode_id=70, seed=100194, result=Fail +episode_id=71, seed=100196, result=Fail +episode_id=72, seed=100197, result=Fail +episode_id=73, seed=100198, result=Fail +episode_id=74, seed=100199, result=Fail +episode_id=75, seed=100202, result=Fail +episode_id=76, seed=100204, result=Fail +episode_id=77, seed=100206, result=Fail +episode_id=78, seed=100207, result=Fail +episode_id=79, seed=100209, result=Fail +episode_id=80, seed=100210, result=Success +episode_id=81, seed=100222, result=Fail +episode_id=82, seed=100225, result=Fail +episode_id=83, seed=100227, result=Success +episode_id=84, seed=100228, result=Fail +episode_id=85, seed=100230, result=Fail +episode_id=86, seed=100232, result=Fail +episode_id=87, seed=100234, result=Fail +episode_id=88, seed=100237, result=Fail +episode_id=89, seed=100240, result=Fail +episode_id=90, seed=100241, result=Fail +episode_id=91, seed=100242, result=Fail +episode_id=92, seed=100244, result=Fail +episode_id=93, seed=100251, result=Fail +episode_id=94, seed=100252, result=Fail +episode_id=95, seed=100254, result=Fail +episode_id=96, seed=100255, result=Fail +episode_id=97, seed=100258, result=Fail +episode_id=98, seed=100261, result=Fail +episode_id=99, seed=100263, result=Fail diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..9c7cb59aff3e25537df7d678cdd402dd72dad2c2 --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:44/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:44/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..67b5360fa1a075407fdbecf3c51545c1c061bdf7 --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:44/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:30:44 + diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:15/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:15/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..a9726dd04c31bd5824a94aaa02aec6cffcd8b708 --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:15/eval_log.txt @@ -0,0 +1,15 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:36:15 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Success +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 11:35:10/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 11:35:10/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2770ce258dd7a2dac7163f174fadb59855878ddf --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 11:35:10/eval_log.txt @@ -0,0 +1,73 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:35:10 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Success +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Fail +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Fail +episode_id=37, seed=100037, result=Success +episode_id=38, seed=100038, result=Fail +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Fail +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Fail +episode_id=44, seed=100044, result=Fail +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Fail +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Fail +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Fail +episode_id=53, seed=100053, result=Fail +episode_id=54, seed=100054, result=Fail +episode_id=55, seed=100055, result=Fail +episode_id=56, seed=100056, result=Fail +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Fail +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Fail +episode_id=63, seed=100063, result=Fail +episode_id=64, seed=100064, result=Fail +episode_id=65, seed=100065, result=Fail +episode_id=66, seed=100066, result=Fail +episode_id=67, seed=100067, result=Fail +episode_id=68, seed=100068, result=Fail +episode_id=69, seed=100069, result=Fail diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..347ecf1451176dfd5e0d065f792dd5c7bd48b9ed --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt @@ -0,0 +1,22 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-04 15:29:19 + +episode_id=70, seed=100070, result=Fail +episode_id=71, seed=100071, result=Fail +episode_id=72, seed=100072, result=Fail +episode_id=73, seed=100073, result=Fail +episode_id=74, seed=100074, result=Fail +episode_id=75, seed=100075, result=Fail +episode_id=76, seed=100076, result=Fail +episode_id=77, seed=100077, result=Fail +episode_id=78, seed=100078, result=Fail +episode_id=79, seed=100079, result=Fail +episode_id=80, seed=100080, result=Fail +episode_id=81, seed=100081, result=Fail +episode_id=82, seed=100082, result=Fail +episode_id=83, seed=100083, result=Fail +episode_id=84, seed=100084, result=Fail +episode_id=85, seed=100085, result=Fail +episode_id=86, seed=100086, result=Success +episode_id=87, seed=100087, result=Fail +episode_id=88, seed=100088, result=Fail diff --git a/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-05 16:04:01/eval_log.txt b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-05 16:04:01/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d6ba30fdbf972b823c8f6b7cc5c14d42a347593c --- /dev/null +++ b/eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-05 16:04:01/eval_log.txt @@ -0,0 +1,39 @@ +Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-05 16:04:01 + +episode_id=19, seed=100089, result=Fail +episode_id=20, seed=100090, result=Success +episode_id=21, seed=100091, result=Fail +episode_id=22, seed=100092, result=Fail +episode_id=23, seed=100093, result=Fail +episode_id=24, seed=100094, result=Fail +episode_id=25, seed=100095, result=Fail +episode_id=26, seed=100096, result=Fail +episode_id=27, seed=100097, result=Fail +episode_id=28, seed=100098, result=Fail +episode_id=29, seed=100099, result=Fail +episode_id=30, seed=100100, result=Fail +episode_id=31, seed=100101, result=Fail +episode_id=32, seed=100102, result=Success +episode_id=33, seed=100103, result=Fail +episode_id=34, seed=100104, result=Fail +episode_id=35, seed=100105, result=Fail +episode_id=36, seed=100106, result=Fail +episode_id=37, seed=100107, result=Fail +episode_id=38, seed=100108, result=Fail +episode_id=39, seed=100109, result=Fail +episode_id=40, seed=100110, result=Fail +episode_id=41, seed=100111, result=Fail +episode_id=42, seed=100112, result=Fail +episode_id=43, seed=100113, result=Success +episode_id=44, seed=100114, result=Fail +episode_id=45, seed=100115, result=Fail +episode_id=46, seed=100116, result=Fail +episode_id=47, seed=100117, result=Fail +episode_id=48, seed=100118, result=Fail +episode_id=49, seed=100119, result=Fail +episode_id=50, seed=100120, result=Fail +episode_id=51, seed=100121, result=Fail +episode_id=52, seed=100122, result=Fail +episode_id=53, seed=100123, result=Fail +episode_id=54, seed=100124, result=Success diff --git a/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..bfc8e9b4168d2135b72b117730435968d6786596 --- /dev/null +++ b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for classify_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:23/eval_log.txt b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:23/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..86993074aebb45513fb7c76d88fb15a9fca5690e --- /dev/null +++ b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:23/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for classify_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:32:23 + diff --git a/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:35:58/eval_log.txt b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:35:58/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..991b0b96348861c48ebace4782a7082b87cebfb7 --- /dev/null +++ b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:35:58/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for classify_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:35:58 + diff --git a/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:43:26/eval_log.txt b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:43:26/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..22b8e69d4d507ef60fed62d03fd14787abd5d344 --- /dev/null +++ b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:43:26/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for classify_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-19 06:43:26 + diff --git a/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:23:39/eval_log.txt b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:23:39/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7e400d445b63ed46a3b1a876adf32d2548707c36 --- /dev/null +++ b/eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:23:39/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for classify_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-04 15:23:39 + diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..d12e81c38a2c71e37d2498df2254e4d7021bc51d --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for cover_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:14/eval_log.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:14/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..103dad55f2311f8018a6d2ec7a4ef29dbeec9596 --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:14/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for cover_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:32:14 + diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:50/eval_log.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:50/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..bb484c72da06ac933e2063170b6b310583e95b67 --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:50/eval_log.txt @@ -0,0 +1,33 @@ +Eval log for cover_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:36:50 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100029, result=Fail +episode_id=29, seed=100030, result=Fail diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/_result.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..b5c2b277325fc39a6186d77aa2570f772745d128 --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-04-04 15:29:22 + +Instruction Type: unseen + +Success Rate: 0.0 + +Reward: 0.001 diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/eval_log.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5515842e8a005d614a35ee20efc95d13afa739a4 --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/eval_log.txt @@ -0,0 +1,95 @@ +Eval log for cover_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:14:44 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Fail +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Fail +episode_id=37, seed=100037, result=Fail +episode_id=38, seed=100038, result=Fail +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Fail +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Fail +episode_id=44, seed=100044, result=Fail +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Fail +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Fail +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Fail +episode_id=53, seed=100053, result=Fail +episode_id=54, seed=100054, result=Fail +episode_id=55, seed=100055, result=Fail +episode_id=56, seed=100056, result=Fail +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Fail +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Fail +episode_id=63, seed=100063, result=Fail +episode_id=64, seed=100064, result=Fail +episode_id=65, seed=100065, result=Fail +episode_id=66, seed=100066, result=Fail +episode_id=67, seed=100067, result=Fail +episode_id=68, seed=100068, result=Fail +episode_id=69, seed=100069, result=Fail +episode_id=70, seed=100070, result=Fail +episode_id=71, seed=100071, result=Fail +episode_id=72, seed=100072, result=Fail +episode_id=73, seed=100073, result=Fail +episode_id=74, seed=100074, result=Fail +episode_id=75, seed=100075, result=Fail +episode_id=76, seed=100076, result=Fail +episode_id=77, seed=100077, result=Fail +episode_id=78, seed=100078, result=Fail +episode_id=79, seed=100079, result=Fail +episode_id=80, seed=100080, result=Fail +episode_id=81, seed=100081, result=Fail +episode_id=82, seed=100082, result=Fail +episode_id=83, seed=100083, result=Fail +episode_id=84, seed=100084, result=Fail +episode_id=85, seed=100085, result=Fail +episode_id=86, seed=100086, result=Fail +episode_id=87, seed=100087, result=Fail +episode_id=88, seed=100088, result=Fail +episode_id=89, seed=100089, result=Fail +episode_id=90, seed=100090, result=Fail +episode_id=91, seed=100091, result=Fail diff --git a/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:29:22/eval_log.txt b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:29:22/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6d5d382c5e35cb9fc61a7d7fc9e996dbc264c736 --- /dev/null +++ b/eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:29:22/eval_log.txt @@ -0,0 +1,11 @@ +Eval log for cover_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-04 15:29:22 + +episode_id=92, seed=100092, result=Fail +episode_id=93, seed=100093, result=Fail +episode_id=94, seed=100094, result=Fail +episode_id=95, seed=100095, result=Fail +episode_id=96, seed=100096, result=Fail +episode_id=97, seed=100097, result=Fail +episode_id=98, seed=100098, result=Fail +episode_id=99, seed=100099, result=Fail diff --git a/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..67f874c4f3970fcf732031d9be33822731d37ab6 --- /dev/null +++ b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,4 @@ +Eval log for observe_and_pickup | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + +episode_id=0, seed=100000, result=Fail diff --git a/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/_result.txt b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..e19f134b48a29d43ccf33db2c8efc9237cbade03 --- /dev/null +++ b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-15 18:10:47 + +Instruction Type: unseen + +Success Rate: 0.11 + +Reward: 0.0 diff --git a/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/eval_log.txt b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..59a7ca5b3f938c8161131ca3912a78ad1e0eda2e --- /dev/null +++ b/eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/eval_log.txt @@ -0,0 +1,103 @@ +Eval log for observe_and_pickup | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 18:10:47 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Success +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Success +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Success +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Success +episode_id=37, seed=100037, result=Success +episode_id=38, seed=100038, result=Success +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Success +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Fail +episode_id=44, seed=100044, result=Fail +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Fail +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Fail +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Fail +episode_id=53, seed=100053, result=Fail +episode_id=54, seed=100054, result=Success +episode_id=55, seed=100055, result=Fail +episode_id=56, seed=100056, result=Fail +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Fail +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Fail +episode_id=63, seed=100063, result=Fail +episode_id=64, seed=100064, result=Fail +episode_id=65, seed=100065, result=Fail +episode_id=66, seed=100066, result=Fail +episode_id=67, seed=100067, result=Fail +episode_id=68, seed=100068, result=Fail +episode_id=69, seed=100069, result=Fail +episode_id=70, seed=100070, result=Fail +episode_id=71, seed=100071, result=Success +episode_id=72, seed=100072, result=Fail +episode_id=73, seed=100073, result=Fail +episode_id=74, seed=100074, result=Fail +episode_id=75, seed=100075, result=Fail +episode_id=76, seed=100076, result=Fail +episode_id=77, seed=100077, result=Fail +episode_id=78, seed=100078, result=Fail +episode_id=79, seed=100079, result=Fail +episode_id=80, seed=100080, result=Fail +episode_id=81, seed=100081, result=Fail +episode_id=82, seed=100082, result=Fail +episode_id=83, seed=100083, result=Fail +episode_id=84, seed=100084, result=Fail +episode_id=85, seed=100085, result=Fail +episode_id=86, seed=100086, result=Fail +episode_id=87, seed=100087, result=Fail +episode_id=88, seed=100088, result=Fail +episode_id=89, seed=100089, result=Success +episode_id=90, seed=100091, result=Fail +episode_id=91, seed=100092, result=Fail +episode_id=92, seed=100094, result=Success +episode_id=93, seed=100095, result=Fail +episode_id=94, seed=100096, result=Fail +episode_id=95, seed=100097, result=Fail +episode_id=96, seed=100098, result=Fail +episode_id=97, seed=100099, result=Fail +episode_id=98, seed=100100, result=Fail +episode_id=99, seed=100101, result=Fail diff --git a/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c19c495110c7ca0ea1cb057bb585ebfcafb208b5 --- /dev/null +++ b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for place_block_mat | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 02:46:58/eval_log.txt b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 02:46:58/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..cd2423a6f6511767c7e1e6785fe563f8210c5b38 --- /dev/null +++ b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 02:46:58/eval_log.txt @@ -0,0 +1,31 @@ +Eval log for place_block_mat | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:46:58 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail diff --git a/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/_result.txt b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..5e1cb7e987b3f9c56cb29c71e07cfb50cade4af6 --- /dev/null +++ b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-04-04 15:29:19 + +Instruction Type: unseen + +Success Rate: 0.0 + +Reward: 0.0 diff --git a/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/eval_log.txt b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5a0ef269be352e9fc2d66190b514ab04415df8b3 --- /dev/null +++ b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/eval_log.txt @@ -0,0 +1,87 @@ +Eval log for place_block_mat | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:20:15 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Fail +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Fail +episode_id=37, seed=100037, result=Fail +episode_id=38, seed=100038, result=Fail +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Fail +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Fail +episode_id=44, seed=100044, result=Fail +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Fail +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Fail +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Fail +episode_id=53, seed=100053, result=Fail +episode_id=54, seed=100054, result=Fail +episode_id=55, seed=100055, result=Fail +episode_id=56, seed=100056, result=Fail +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Fail +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Fail +episode_id=63, seed=100063, result=Fail +episode_id=64, seed=100064, result=Fail +episode_id=65, seed=100065, result=Fail +episode_id=66, seed=100066, result=Fail +episode_id=67, seed=100067, result=Fail +episode_id=68, seed=100068, result=Fail +episode_id=69, seed=100069, result=Fail +episode_id=70, seed=100070, result=Fail +episode_id=71, seed=100071, result=Fail +episode_id=72, seed=100072, result=Fail +episode_id=73, seed=100073, result=Fail +episode_id=74, seed=100074, result=Fail +episode_id=75, seed=100075, result=Fail +episode_id=76, seed=100076, result=Fail +episode_id=77, seed=100077, result=Fail +episode_id=78, seed=100078, result=Fail +episode_id=79, seed=100079, result=Fail +episode_id=80, seed=100080, result=Fail +episode_id=81, seed=100081, result=Fail +episode_id=82, seed=100082, result=Fail +episode_id=83, seed=100083, result=Fail diff --git a/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..14b604fc51551201185fc0db1f036fc268d584af --- /dev/null +++ b/eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt @@ -0,0 +1,19 @@ +Eval log for place_block_mat | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-04 15:29:19 + +episode_id=84, seed=100084, result=Fail +episode_id=85, seed=100085, result=Fail +episode_id=86, seed=100086, result=Fail +episode_id=87, seed=100087, result=Fail +episode_id=88, seed=100088, result=Fail +episode_id=89, seed=100089, result=Fail +episode_id=90, seed=100090, result=Fail +episode_id=91, seed=100091, result=Fail +episode_id=92, seed=100092, result=Fail +episode_id=93, seed=100093, result=Fail +episode_id=94, seed=100094, result=Fail +episode_id=95, seed=100095, result=Fail +episode_id=96, seed=100096, result=Fail +episode_id=97, seed=100097, result=Fail +episode_id=98, seed=100098, result=Fail +episode_id=99, seed=100099, result=Fail diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-12 20:24:28/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-12 20:24:28/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c46b36f94dedcbc61a89830a7cf51b37462c7e50 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-12 20:24:28/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-12 20:24:28 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 01:23:00/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 01:23:00/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..06cbfda9c9f3a6e4b9611a3af43659b3ecd97e4a --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 01:23:00/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-13 01:23:00 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 21:15:31/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 21:15:31/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7e9b168bc8b6d588e08e979dcb5a579b3dd8d6c3 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 21:15:31/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-13 21:15:31 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 22:40:29/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 22:40:29/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..cec5c0141cd4e0c5a3bcf5ef55eabe99309e7115 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 22:40:29/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-13 22:40:29 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 02:33:22/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 02:33:22/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..3060538aef4b4f60780868ace25fe6f0ed2d405b --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 02:33:22/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-14 02:33:22 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 16:31:38/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 16:31:38/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7853b33f0d3c10005d333fc0337933493267e17a --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 16:31:38/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-14 16:31:38 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 01:00:34/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 01:00:34/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2697bb67e547196b2693d325d9b3a0c90058580c --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 01:00:34/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 01:00:34 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:00:56/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:00:56/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b521d379b8323663cc38cf0709db369cb9c07b59 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:00:56/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 14:00:56 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:53:19/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:53:19/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..440499623f699f44987c1a38ca4e8a6b1f7ccce5 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:53:19/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 14:53:19 + diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/_result.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..c6962404936b96da1421d0c0200f6895fdb081fd --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-15 16:22:31 + +Instruction Type: unseen + +Success Rate: 0.0 + +Reward: 0.0 diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..2cdf24a751543e673d49f50350d26761a152b129 --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/eval_log.txt @@ -0,0 +1,6 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 16:22:31 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail diff --git a/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..33d25afc532a48455c311103fe4040ff9243beeb --- /dev/null +++ b/eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for press_button | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 17:53:30 + diff --git a/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/_result.txt b/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..f82d83c84af5c6ea6bec7b5e6320d96949edd391 --- /dev/null +++ b/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-15 23:05:55 + +Instruction Type: unseen + +Success Rate: 0.13 + +Reward: 0.13 diff --git a/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/eval_log.txt b/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6bb6318f4c477600fb1eee54abe54ce17b62de0a --- /dev/null +++ b/eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/eval_log.txt @@ -0,0 +1,103 @@ +Eval log for put_back_block | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 23:05:55 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Success +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Success +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Success +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Success +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Fail +episode_id=37, seed=100037, result=Fail +episode_id=38, seed=100038, result=Fail +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Fail +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Fail +episode_id=44, seed=100044, result=Fail +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Success +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Success +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Success +episode_id=53, seed=100053, result=Fail +episode_id=54, seed=100054, result=Fail +episode_id=55, seed=100055, result=Success +episode_id=56, seed=100056, result=Fail +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Success +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Fail +episode_id=63, seed=100063, result=Fail +episode_id=64, seed=100064, result=Fail +episode_id=65, seed=100065, result=Fail +episode_id=66, seed=100066, result=Fail +episode_id=67, seed=100067, result=Fail +episode_id=68, seed=100068, result=Fail +episode_id=69, seed=100069, result=Fail +episode_id=70, seed=100070, result=Fail +episode_id=71, seed=100071, result=Success +episode_id=72, seed=100072, result=Fail +episode_id=73, seed=100073, result=Fail +episode_id=74, seed=100074, result=Fail +episode_id=75, seed=100075, result=Fail +episode_id=76, seed=100076, result=Fail +episode_id=77, seed=100077, result=Fail +episode_id=78, seed=100078, result=Fail +episode_id=79, seed=100079, result=Success +episode_id=80, seed=100080, result=Fail +episode_id=81, seed=100081, result=Fail +episode_id=82, seed=100082, result=Fail +episode_id=83, seed=100083, result=Fail +episode_id=84, seed=100084, result=Success +episode_id=85, seed=100085, result=Fail +episode_id=86, seed=100086, result=Success +episode_id=87, seed=100087, result=Fail +episode_id=88, seed=100088, result=Fail +episode_id=89, seed=100089, result=Fail +episode_id=90, seed=100090, result=Fail +episode_id=91, seed=100091, result=Fail +episode_id=92, seed=100092, result=Fail +episode_id=93, seed=100093, result=Fail +episode_id=94, seed=100094, result=Fail +episode_id=95, seed=100095, result=Fail +episode_id=96, seed=100096, result=Fail +episode_id=97, seed=100097, result=Fail +episode_id=98, seed=100098, result=Fail +episode_id=99, seed=100099, result=Fail diff --git a/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-15 19:32:34/eval_log.txt b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-15 19:32:34/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..afe9c8960032d344544e50ff0e20bee74b6135ac --- /dev/null +++ b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-15 19:32:34/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for rearrange_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-15 19:32:34 + diff --git a/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..52493e6b8ae371c093ea31a63cd6bbf68958691c --- /dev/null +++ b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt @@ -0,0 +1,66 @@ +Eval log for rearrange_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:28:17 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100025, result=Fail +episode_id=26, seed=100026, result=Fail +episode_id=27, seed=100027, result=Fail +episode_id=28, seed=100028, result=Fail +episode_id=29, seed=100029, result=Fail +episode_id=30, seed=100030, result=Fail +episode_id=31, seed=100031, result=Fail +episode_id=32, seed=100032, result=Fail +episode_id=33, seed=100033, result=Fail +episode_id=34, seed=100034, result=Fail +episode_id=35, seed=100035, result=Fail +episode_id=36, seed=100036, result=Fail +episode_id=37, seed=100037, result=Fail +episode_id=38, seed=100038, result=Fail +episode_id=39, seed=100039, result=Fail +episode_id=40, seed=100040, result=Success +episode_id=41, seed=100041, result=Fail +episode_id=42, seed=100042, result=Fail +episode_id=43, seed=100043, result=Success +episode_id=44, seed=100044, result=Success +episode_id=45, seed=100045, result=Fail +episode_id=46, seed=100046, result=Fail +episode_id=47, seed=100047, result=Fail +episode_id=48, seed=100048, result=Fail +episode_id=49, seed=100049, result=Fail +episode_id=50, seed=100050, result=Fail +episode_id=51, seed=100051, result=Fail +episode_id=52, seed=100052, result=Fail +episode_id=53, seed=100053, result=Success +episode_id=54, seed=100054, result=Fail +episode_id=55, seed=100055, result=Fail +episode_id=56, seed=100056, result=Success +episode_id=57, seed=100057, result=Fail +episode_id=58, seed=100058, result=Fail +episode_id=59, seed=100059, result=Fail +episode_id=60, seed=100060, result=Fail +episode_id=61, seed=100061, result=Fail +episode_id=62, seed=100062, result=Success diff --git a/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..bdcfc441a7e4366c780510a6feee445072007448 --- /dev/null +++ b/eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-17 (extracted from job 2971341 log) + +Instruction Type: unseen + +Success Rate: 0.06 + +Reward: 0.0 diff --git a/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:33:35/eval_log.txt b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:33:35/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..bc88ab857207b43388e9bada2e304072a8dbe0a2 --- /dev/null +++ b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:33:35/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for storage_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:33:35 + diff --git a/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:45:04/eval_log.txt b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:45:04/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..fa0a15c7951c85a4bc03fad135af47d1af0fd13d --- /dev/null +++ b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:45:04/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for storage_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-19 06:45:04 + diff --git a/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:24:34/eval_log.txt b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:24:34/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..0a31783314117e5efd1cf6e479859aff8c576f82 --- /dev/null +++ b/eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:24:34/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for storage_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-04-04 15:24:34 + diff --git a/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-16 08:39:05/eval_log.txt b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-16 08:39:05/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..30c41803a27d1b6eb6e6491e9b7faa08c936c014 --- /dev/null +++ b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-16 08:39:05/eval_log.txt @@ -0,0 +1,51 @@ +Eval log for swap_T | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-16 08:39:05 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Fail +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Success +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Fail +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Success +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Fail +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Fail +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100026, result=Fail +episode_id=26, seed=100027, result=Success +episode_id=27, seed=100029, result=Fail +episode_id=28, seed=100030, result=Fail +episode_id=29, seed=100031, result=Fail +episode_id=30, seed=100033, result=Fail +episode_id=31, seed=100034, result=Fail +episode_id=32, seed=100035, result=Fail +episode_id=33, seed=100036, result=Fail +episode_id=34, seed=100037, result=Fail +episode_id=35, seed=100038, result=Success +episode_id=36, seed=100040, result=Fail +episode_id=37, seed=100041, result=Fail +episode_id=38, seed=100042, result=Fail +episode_id=39, seed=100044, result=Fail +episode_id=40, seed=100045, result=Fail +episode_id=41, seed=100046, result=Fail +episode_id=42, seed=100047, result=Success +episode_id=43, seed=100048, result=Fail +episode_id=44, seed=100049, result=Fail +episode_id=45, seed=100050, result=Success +episode_id=46, seed=100051, result=Fail +episode_id=47, seed=100052, result=Fail diff --git a/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..474465950807f93ec09591d7df14f7e3bf57e4d1 --- /dev/null +++ b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt @@ -0,0 +1,72 @@ +Eval log for swap_T | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:28:17 + +episode_id=0, seed=100000, result=Fail +episode_id=1, seed=100001, result=Fail +episode_id=2, seed=100002, result=Fail +episode_id=3, seed=100003, result=Success +episode_id=4, seed=100004, result=Fail +episode_id=5, seed=100005, result=Fail +episode_id=6, seed=100006, result=Fail +episode_id=7, seed=100007, result=Fail +episode_id=8, seed=100008, result=Fail +episode_id=9, seed=100009, result=Fail +episode_id=10, seed=100010, result=Fail +episode_id=11, seed=100011, result=Success +episode_id=12, seed=100012, result=Fail +episode_id=13, seed=100013, result=Fail +episode_id=14, seed=100014, result=Fail +episode_id=15, seed=100015, result=Fail +episode_id=16, seed=100016, result=Fail +episode_id=17, seed=100017, result=Fail +episode_id=18, seed=100018, result=Fail +episode_id=19, seed=100019, result=Fail +episode_id=20, seed=100020, result=Success +episode_id=21, seed=100021, result=Fail +episode_id=22, seed=100022, result=Success +episode_id=23, seed=100023, result=Fail +episode_id=24, seed=100024, result=Fail +episode_id=25, seed=100026, result=Fail +episode_id=26, seed=100027, result=Fail +episode_id=27, seed=100029, result=Fail +episode_id=28, seed=100030, result=Fail +episode_id=29, seed=100031, result=Success +episode_id=30, seed=100033, result=Fail +episode_id=31, seed=100034, result=Fail +episode_id=32, seed=100035, result=Fail +episode_id=33, seed=100036, result=Fail +episode_id=34, seed=100037, result=Fail +episode_id=35, seed=100038, result=Fail +episode_id=36, seed=100040, result=Success +episode_id=37, seed=100041, result=Fail +episode_id=38, seed=100042, result=Fail +episode_id=39, seed=100044, result=Fail +episode_id=40, seed=100045, result=Fail +episode_id=41, seed=100046, result=Fail +episode_id=42, seed=100047, result=Fail +episode_id=43, seed=100048, result=Fail +episode_id=44, seed=100049, result=Fail +episode_id=45, seed=100050, result=Fail +episode_id=46, seed=100051, result=Fail +episode_id=47, seed=100052, result=Fail +episode_id=48, seed=100053, result=Fail +episode_id=49, seed=100054, result=Fail +episode_id=50, seed=100055, result=Fail +episode_id=51, seed=100056, result=Fail +episode_id=52, seed=100057, result=Fail +episode_id=53, seed=100058, result=Fail +episode_id=54, seed=100060, result=Success +episode_id=55, seed=100061, result=Fail +episode_id=56, seed=100062, result=Fail +episode_id=57, seed=100063, result=Fail +episode_id=58, seed=100064, result=Fail +episode_id=59, seed=100065, result=Fail +episode_id=60, seed=100066, result=Fail +episode_id=61, seed=100067, result=Fail +episode_id=62, seed=100068, result=Fail +episode_id=63, seed=100069, result=Fail +episode_id=64, seed=100070, result=Success +episode_id=65, seed=100071, result=Fail +episode_id=66, seed=100073, result=Fail +episode_id=67, seed=100075, result=Fail +episode_id=68, seed=100076, result=Fail diff --git a/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..862cb327caf125265b0bacf250b0441444d8f7f6 --- /dev/null +++ b/eval_result/swap_T/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-17 (extracted from job 2971340 log) + +Instruction Type: unseen + +Success Rate: 0.12 + +Reward: 0.0 diff --git a/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:29:32/eval_log.txt b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:29:32/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e794a67226abff76176d5f018e57ead195d19ec5 --- /dev/null +++ b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:29:32/eval_log.txt @@ -0,0 +1,3 @@ +Eval log for swap_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:29:32 + diff --git a/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..83628808a6c517287a581e439ef9cb436dba2495 --- /dev/null +++ b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt @@ -0,0 +1,42 @@ +Eval log for swap_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 02:36:20 + +episode_id=0, seed=100001, result=Success +episode_id=1, seed=100002, result=Fail +episode_id=2, seed=100008, result=Fail +episode_id=3, seed=100009, result=Fail +episode_id=4, seed=100012, result=Fail +episode_id=5, seed=100013, result=Fail +episode_id=6, seed=100014, result=Fail +episode_id=7, seed=100015, result=Fail +episode_id=8, seed=100016, result=Fail +episode_id=9, seed=100018, result=Success +episode_id=10, seed=100022, result=Fail +episode_id=11, seed=100023, result=Fail +episode_id=12, seed=100024, result=Fail +episode_id=13, seed=100027, result=Fail +episode_id=14, seed=100028, result=Fail +episode_id=15, seed=100030, result=Fail +episode_id=16, seed=100031, result=Fail +episode_id=17, seed=100033, result=Fail +episode_id=18, seed=100038, result=Fail +episode_id=19, seed=100039, result=Fail +episode_id=20, seed=100041, result=Fail +episode_id=21, seed=100042, result=Fail +episode_id=22, seed=100043, result=Fail +episode_id=23, seed=100044, result=Fail +episode_id=24, seed=100048, result=Success +episode_id=25, seed=100051, result=Fail +episode_id=26, seed=100052, result=Fail +episode_id=27, seed=100053, result=Fail +episode_id=28, seed=100054, result=Success +episode_id=29, seed=100055, result=Fail +episode_id=30, seed=100057, result=Fail +episode_id=31, seed=100058, result=Fail +episode_id=32, seed=100059, result=Fail +episode_id=33, seed=100061, result=Fail +episode_id=34, seed=100062, result=Fail +episode_id=35, seed=100063, result=Fail +episode_id=36, seed=100066, result=Fail +episode_id=37, seed=100067, result=Fail +episode_id=38, seed=100068, result=Fail diff --git a/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/_result.txt b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/_result.txt new file mode 100644 index 0000000000000000000000000000000000000000..f62a32cceb0c858d9c3cc22eccd7800458cad06c --- /dev/null +++ b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/_result.txt @@ -0,0 +1,7 @@ +Timestamp: 2026-03-17 11:13:40 + +Instruction Type: unseen + +Success Rate: 0.1 + +Reward: 0.1 diff --git a/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/eval_log.txt b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/eval_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..06dcc17a926f1e8de3fa77c16d95632b1b6001c2 --- /dev/null +++ b/eval_result/swap_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:13:40/eval_log.txt @@ -0,0 +1,103 @@ +Eval log for swap_blocks | pi05 | demo_clean | demo_clean +Timestamp: 2026-03-17 11:13:40 + +episode_id=0, seed=100001, result=Success +episode_id=1, seed=100002, result=Fail +episode_id=2, seed=100008, result=Fail +episode_id=3, seed=100009, result=Fail +episode_id=4, seed=100012, result=Fail +episode_id=5, seed=100013, result=Fail +episode_id=6, seed=100014, result=Fail +episode_id=7, seed=100015, result=Fail +episode_id=8, seed=100016, result=Fail +episode_id=9, seed=100022, result=Fail +episode_id=10, seed=100023, result=Fail +episode_id=11, seed=100024, result=Fail +episode_id=12, seed=100027, result=Fail +episode_id=13, seed=100028, result=Fail +episode_id=14, seed=100030, result=Fail +episode_id=15, seed=100031, result=Fail +episode_id=16, seed=100038, result=Fail +episode_id=17, seed=100039, result=Fail +episode_id=18, seed=100041, result=Fail +episode_id=19, seed=100042, result=Fail +episode_id=20, seed=100043, result=Fail +episode_id=21, seed=100044, result=Fail +episode_id=22, seed=100048, result=Success +episode_id=23, seed=100051, result=Fail +episode_id=24, seed=100052, result=Fail +episode_id=25, seed=100053, result=Fail +episode_id=26, seed=100054, result=Success +episode_id=27, seed=100055, result=Fail +episode_id=28, seed=100057, result=Fail +episode_id=29, seed=100058, result=Fail +episode_id=30, seed=100059, result=Fail +episode_id=31, seed=100061, result=Fail +episode_id=32, seed=100062, result=Success +episode_id=33, seed=100063, result=Fail +episode_id=34, seed=100066, result=Fail +episode_id=35, seed=100067, result=Fail +episode_id=36, seed=100068, result=Success +episode_id=37, seed=100071, result=Fail +episode_id=38, seed=100073, result=Fail +episode_id=39, seed=100076, result=Fail +episode_id=40, seed=100079, result=Fail +episode_id=41, seed=100083, result=Fail +episode_id=42, seed=100084, result=Fail +episode_id=43, seed=100085, result=Fail +episode_id=44, seed=100086, result=Fail +episode_id=45, seed=100088, result=Fail +episode_id=46, seed=100089, result=Fail +episode_id=47, seed=100090, result=Fail +episode_id=48, seed=100093, result=Fail +episode_id=49, seed=100094, result=Fail +episode_id=50, seed=100095, result=Fail +episode_id=51, seed=100097, result=Fail +episode_id=52, seed=100102, result=Fail +episode_id=53, seed=100103, result=Fail +episode_id=54, seed=100104, result=Fail +episode_id=55, seed=100106, result=Fail +episode_id=56, seed=100112, result=Fail +episode_id=57, seed=100113, result=Fail +episode_id=58, seed=100114, result=Fail +episode_id=59, seed=100115, result=Fail +episode_id=60, seed=100119, result=Fail +episode_id=61, seed=100127, result=Success +episode_id=62, seed=100128, result=Fail +episode_id=63, seed=100129, result=Fail +episode_id=64, seed=100132, result=Fail +episode_id=65, seed=100133, result=Fail +episode_id=66, seed=100134, result=Success +episode_id=67, seed=100136, result=Success +episode_id=68, seed=100137, result=Fail +episode_id=69, seed=100138, result=Fail +episode_id=70, seed=100139, result=Fail +episode_id=71, seed=100142, result=Fail +episode_id=72, seed=100143, result=Success +episode_id=73, seed=100145, result=Fail +episode_id=74, seed=100146, result=Fail +episode_id=75, seed=100147, result=Fail +episode_id=76, seed=100148, result=Fail +episode_id=77, seed=100149, result=Fail +episode_id=78, seed=100150, result=Fail +episode_id=79, seed=100151, result=Fail +episode_id=80, seed=100154, result=Fail +episode_id=81, seed=100156, result=Fail +episode_id=82, seed=100157, result=Fail +episode_id=83, seed=100158, result=Fail +episode_id=84, seed=100162, result=Success +episode_id=85, seed=100163, result=Fail +episode_id=86, seed=100165, result=Fail +episode_id=87, seed=100166, result=Fail +episode_id=88, seed=100169, result=Fail +episode_id=89, seed=100170, result=Fail +episode_id=90, seed=100171, result=Fail +episode_id=91, seed=100173, result=Fail +episode_id=92, seed=100175, result=Fail +episode_id=93, seed=100176, result=Fail +episode_id=94, seed=100177, result=Fail +episode_id=95, seed=100178, result=Fail +episode_id=96, seed=100179, result=Fail +episode_id=97, seed=100182, result=Fail +episode_id=98, seed=100185, result=Fail +episode_id=99, seed=100187, result=Fail