Add Pi-0.5 evaluation results (logs + results)
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 18:02:39/eval_log.txt +3 -0
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:52/eval_log.txt +3 -0
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt +47 -0
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/_result.txt +7 -0
- eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/eval_log.txt +103 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:44/eval_log.txt +3 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:15/eval_log.txt +15 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 11:35:10/eval_log.txt +73 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt +22 -0
- eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-05 16:04:01/eval_log.txt +39 -0
- eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:23/eval_log.txt +3 -0
- eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:35:58/eval_log.txt +3 -0
- eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:43:26/eval_log.txt +3 -0
- eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:23:39/eval_log.txt +3 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:14/eval_log.txt +3 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:50/eval_log.txt +33 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/_result.txt +7 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/eval_log.txt +95 -0
- eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:29:22/eval_log.txt +11 -0
- eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +4 -0
- eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/_result.txt +7 -0
- eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/eval_log.txt +103 -0
- eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 02:46:58/eval_log.txt +31 -0
- eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/_result.txt +7 -0
- eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/eval_log.txt +87 -0
- eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt +19 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-12 20:24:28/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 01:23:00/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 21:15:31/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 22:40:29/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 02:33:22/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 16:31:38/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 01:00:34/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:00:56/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:53:19/eval_log.txt +3 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/_result.txt +7 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/eval_log.txt +6 -0
- eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt +3 -0
- eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/_result.txt +7 -0
- eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/eval_log.txt +103 -0
- eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-15 19:32:34/eval_log.txt +3 -0
- eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt +66 -0
- eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt +7 -0
- eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:33:35/eval_log.txt +3 -0
- eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:45:04/eval_log.txt +3 -0
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for battery_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-15 18:02:39/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for battery_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 18:02:39
|
| 3 |
+
|
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:52/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for battery_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:30:52
|
| 3 |
+
|
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:20/eval_log.txt
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for battery_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:36:20
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100004, result=Fail
|
| 5 |
+
episode_id=1, seed=100006, result=Fail
|
| 6 |
+
episode_id=2, seed=100009, result=Fail
|
| 7 |
+
episode_id=3, seed=100015, result=Fail
|
| 8 |
+
episode_id=4, seed=100017, result=Fail
|
| 9 |
+
episode_id=5, seed=100021, result=Fail
|
| 10 |
+
episode_id=6, seed=100022, result=Fail
|
| 11 |
+
episode_id=7, seed=100026, result=Success
|
| 12 |
+
episode_id=8, seed=100027, result=Fail
|
| 13 |
+
episode_id=9, seed=100030, result=Fail
|
| 14 |
+
episode_id=10, seed=100033, result=Fail
|
| 15 |
+
episode_id=11, seed=100035, result=Fail
|
| 16 |
+
episode_id=12, seed=100036, result=Fail
|
| 17 |
+
episode_id=13, seed=100039, result=Fail
|
| 18 |
+
episode_id=14, seed=100040, result=Fail
|
| 19 |
+
episode_id=15, seed=100041, result=Success
|
| 20 |
+
episode_id=16, seed=100045, result=Success
|
| 21 |
+
episode_id=17, seed=100046, result=Fail
|
| 22 |
+
episode_id=18, seed=100049, result=Fail
|
| 23 |
+
episode_id=19, seed=100051, result=Fail
|
| 24 |
+
episode_id=20, seed=100058, result=Success
|
| 25 |
+
episode_id=21, seed=100063, result=Fail
|
| 26 |
+
episode_id=22, seed=100065, result=Success
|
| 27 |
+
episode_id=23, seed=100074, result=Fail
|
| 28 |
+
episode_id=24, seed=100075, result=Fail
|
| 29 |
+
episode_id=25, seed=100077, result=Fail
|
| 30 |
+
episode_id=26, seed=100078, result=Fail
|
| 31 |
+
episode_id=27, seed=100084, result=Fail
|
| 32 |
+
episode_id=28, seed=100089, result=Fail
|
| 33 |
+
episode_id=29, seed=100099, result=Fail
|
| 34 |
+
episode_id=30, seed=100101, result=Fail
|
| 35 |
+
episode_id=31, seed=100103, result=Fail
|
| 36 |
+
episode_id=32, seed=100104, result=Fail
|
| 37 |
+
episode_id=33, seed=100106, result=Fail
|
| 38 |
+
episode_id=34, seed=100107, result=Fail
|
| 39 |
+
episode_id=35, seed=100111, result=Fail
|
| 40 |
+
episode_id=36, seed=100112, result=Fail
|
| 41 |
+
episode_id=37, seed=100115, result=Fail
|
| 42 |
+
episode_id=38, seed=100123, result=Fail
|
| 43 |
+
episode_id=39, seed=100124, result=Success
|
| 44 |
+
episode_id=40, seed=100126, result=Fail
|
| 45 |
+
episode_id=41, seed=100127, result=Success
|
| 46 |
+
episode_id=42, seed=100136, result=Fail
|
| 47 |
+
episode_id=43, seed=100141, result=Fail
|
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-03-17 11:14:17
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.1
|
| 6 |
+
|
| 7 |
+
Reward: 0.0
|
eval_result/battery_try/pi05/demo_clean/demo_clean/2026-03-17 11:14:17/eval_log.txt
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for battery_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 11:14:17
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100004, result=Fail
|
| 5 |
+
episode_id=1, seed=100006, result=Fail
|
| 6 |
+
episode_id=2, seed=100009, result=Fail
|
| 7 |
+
episode_id=3, seed=100015, result=Fail
|
| 8 |
+
episode_id=4, seed=100017, result=Fail
|
| 9 |
+
episode_id=5, seed=100020, result=Fail
|
| 10 |
+
episode_id=6, seed=100021, result=Fail
|
| 11 |
+
episode_id=7, seed=100022, result=Fail
|
| 12 |
+
episode_id=8, seed=100026, result=Fail
|
| 13 |
+
episode_id=9, seed=100027, result=Fail
|
| 14 |
+
episode_id=10, seed=100033, result=Fail
|
| 15 |
+
episode_id=11, seed=100035, result=Fail
|
| 16 |
+
episode_id=12, seed=100036, result=Fail
|
| 17 |
+
episode_id=13, seed=100039, result=Fail
|
| 18 |
+
episode_id=14, seed=100040, result=Fail
|
| 19 |
+
episode_id=15, seed=100041, result=Fail
|
| 20 |
+
episode_id=16, seed=100045, result=Fail
|
| 21 |
+
episode_id=17, seed=100046, result=Fail
|
| 22 |
+
episode_id=18, seed=100049, result=Fail
|
| 23 |
+
episode_id=19, seed=100051, result=Fail
|
| 24 |
+
episode_id=20, seed=100058, result=Fail
|
| 25 |
+
episode_id=21, seed=100063, result=Fail
|
| 26 |
+
episode_id=22, seed=100065, result=Success
|
| 27 |
+
episode_id=23, seed=100074, result=Fail
|
| 28 |
+
episode_id=24, seed=100075, result=Fail
|
| 29 |
+
episode_id=25, seed=100077, result=Fail
|
| 30 |
+
episode_id=26, seed=100078, result=Fail
|
| 31 |
+
episode_id=27, seed=100084, result=Fail
|
| 32 |
+
episode_id=28, seed=100089, result=Fail
|
| 33 |
+
episode_id=29, seed=100094, result=Fail
|
| 34 |
+
episode_id=30, seed=100099, result=Fail
|
| 35 |
+
episode_id=31, seed=100101, result=Fail
|
| 36 |
+
episode_id=32, seed=100103, result=Fail
|
| 37 |
+
episode_id=33, seed=100104, result=Fail
|
| 38 |
+
episode_id=34, seed=100106, result=Success
|
| 39 |
+
episode_id=35, seed=100107, result=Success
|
| 40 |
+
episode_id=36, seed=100109, result=Fail
|
| 41 |
+
episode_id=37, seed=100111, result=Fail
|
| 42 |
+
episode_id=38, seed=100112, result=Fail
|
| 43 |
+
episode_id=39, seed=100113, result=Fail
|
| 44 |
+
episode_id=40, seed=100115, result=Fail
|
| 45 |
+
episode_id=41, seed=100123, result=Fail
|
| 46 |
+
episode_id=42, seed=100124, result=Success
|
| 47 |
+
episode_id=43, seed=100126, result=Fail
|
| 48 |
+
episode_id=44, seed=100127, result=Fail
|
| 49 |
+
episode_id=45, seed=100136, result=Fail
|
| 50 |
+
episode_id=46, seed=100141, result=Success
|
| 51 |
+
episode_id=47, seed=100142, result=Fail
|
| 52 |
+
episode_id=48, seed=100144, result=Fail
|
| 53 |
+
episode_id=49, seed=100146, result=Fail
|
| 54 |
+
episode_id=50, seed=100147, result=Fail
|
| 55 |
+
episode_id=51, seed=100148, result=Fail
|
| 56 |
+
episode_id=52, seed=100151, result=Fail
|
| 57 |
+
episode_id=53, seed=100154, result=Success
|
| 58 |
+
episode_id=54, seed=100155, result=Fail
|
| 59 |
+
episode_id=55, seed=100157, result=Fail
|
| 60 |
+
episode_id=56, seed=100161, result=Fail
|
| 61 |
+
episode_id=57, seed=100163, result=Fail
|
| 62 |
+
episode_id=58, seed=100167, result=Success
|
| 63 |
+
episode_id=59, seed=100172, result=Fail
|
| 64 |
+
episode_id=60, seed=100174, result=Fail
|
| 65 |
+
episode_id=61, seed=100175, result=Fail
|
| 66 |
+
episode_id=62, seed=100176, result=Fail
|
| 67 |
+
episode_id=63, seed=100179, result=Fail
|
| 68 |
+
episode_id=64, seed=100180, result=Fail
|
| 69 |
+
episode_id=65, seed=100184, result=Success
|
| 70 |
+
episode_id=66, seed=100187, result=Fail
|
| 71 |
+
episode_id=67, seed=100190, result=Fail
|
| 72 |
+
episode_id=68, seed=100192, result=Fail
|
| 73 |
+
episode_id=69, seed=100193, result=Fail
|
| 74 |
+
episode_id=70, seed=100194, result=Fail
|
| 75 |
+
episode_id=71, seed=100196, result=Fail
|
| 76 |
+
episode_id=72, seed=100197, result=Fail
|
| 77 |
+
episode_id=73, seed=100198, result=Fail
|
| 78 |
+
episode_id=74, seed=100199, result=Fail
|
| 79 |
+
episode_id=75, seed=100202, result=Fail
|
| 80 |
+
episode_id=76, seed=100204, result=Fail
|
| 81 |
+
episode_id=77, seed=100206, result=Fail
|
| 82 |
+
episode_id=78, seed=100207, result=Fail
|
| 83 |
+
episode_id=79, seed=100209, result=Fail
|
| 84 |
+
episode_id=80, seed=100210, result=Success
|
| 85 |
+
episode_id=81, seed=100222, result=Fail
|
| 86 |
+
episode_id=82, seed=100225, result=Fail
|
| 87 |
+
episode_id=83, seed=100227, result=Success
|
| 88 |
+
episode_id=84, seed=100228, result=Fail
|
| 89 |
+
episode_id=85, seed=100230, result=Fail
|
| 90 |
+
episode_id=86, seed=100232, result=Fail
|
| 91 |
+
episode_id=87, seed=100234, result=Fail
|
| 92 |
+
episode_id=88, seed=100237, result=Fail
|
| 93 |
+
episode_id=89, seed=100240, result=Fail
|
| 94 |
+
episode_id=90, seed=100241, result=Fail
|
| 95 |
+
episode_id=91, seed=100242, result=Fail
|
| 96 |
+
episode_id=92, seed=100244, result=Fail
|
| 97 |
+
episode_id=93, seed=100251, result=Fail
|
| 98 |
+
episode_id=94, seed=100252, result=Fail
|
| 99 |
+
episode_id=95, seed=100254, result=Fail
|
| 100 |
+
episode_id=96, seed=100255, result=Fail
|
| 101 |
+
episode_id=97, seed=100258, result=Fail
|
| 102 |
+
episode_id=98, seed=100261, result=Fail
|
| 103 |
+
episode_id=99, seed=100263, result=Fail
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:30:44/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:30:44
|
| 3 |
+
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 02:36:15/eval_log.txt
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:36:15
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Success
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-03-17 11:35:10/eval_log.txt
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 11:35:10
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Success
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Fail
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Fail
|
| 41 |
+
episode_id=37, seed=100037, result=Success
|
| 42 |
+
episode_id=38, seed=100038, result=Fail
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Fail
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Fail
|
| 48 |
+
episode_id=44, seed=100044, result=Fail
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Fail
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Fail
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Fail
|
| 57 |
+
episode_id=53, seed=100053, result=Fail
|
| 58 |
+
episode_id=54, seed=100054, result=Fail
|
| 59 |
+
episode_id=55, seed=100055, result=Fail
|
| 60 |
+
episode_id=56, seed=100056, result=Fail
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Fail
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Fail
|
| 67 |
+
episode_id=63, seed=100063, result=Fail
|
| 68 |
+
episode_id=64, seed=100064, result=Fail
|
| 69 |
+
episode_id=65, seed=100065, result=Fail
|
| 70 |
+
episode_id=66, seed=100066, result=Fail
|
| 71 |
+
episode_id=67, seed=100067, result=Fail
|
| 72 |
+
episode_id=68, seed=100068, result=Fail
|
| 73 |
+
episode_id=69, seed=100069, result=Fail
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-04-04 15:29:19
|
| 3 |
+
|
| 4 |
+
episode_id=70, seed=100070, result=Fail
|
| 5 |
+
episode_id=71, seed=100071, result=Fail
|
| 6 |
+
episode_id=72, seed=100072, result=Fail
|
| 7 |
+
episode_id=73, seed=100073, result=Fail
|
| 8 |
+
episode_id=74, seed=100074, result=Fail
|
| 9 |
+
episode_id=75, seed=100075, result=Fail
|
| 10 |
+
episode_id=76, seed=100076, result=Fail
|
| 11 |
+
episode_id=77, seed=100077, result=Fail
|
| 12 |
+
episode_id=78, seed=100078, result=Fail
|
| 13 |
+
episode_id=79, seed=100079, result=Fail
|
| 14 |
+
episode_id=80, seed=100080, result=Fail
|
| 15 |
+
episode_id=81, seed=100081, result=Fail
|
| 16 |
+
episode_id=82, seed=100082, result=Fail
|
| 17 |
+
episode_id=83, seed=100083, result=Fail
|
| 18 |
+
episode_id=84, seed=100084, result=Fail
|
| 19 |
+
episode_id=85, seed=100085, result=Fail
|
| 20 |
+
episode_id=86, seed=100086, result=Success
|
| 21 |
+
episode_id=87, seed=100087, result=Fail
|
| 22 |
+
episode_id=88, seed=100088, result=Fail
|
eval_result/blocks_ranking_try/pi05/demo_clean/demo_clean/2026-04-05 16:04:01/eval_log.txt
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for blocks_ranking_try | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-04-05 16:04:01
|
| 3 |
+
|
| 4 |
+
episode_id=19, seed=100089, result=Fail
|
| 5 |
+
episode_id=20, seed=100090, result=Success
|
| 6 |
+
episode_id=21, seed=100091, result=Fail
|
| 7 |
+
episode_id=22, seed=100092, result=Fail
|
| 8 |
+
episode_id=23, seed=100093, result=Fail
|
| 9 |
+
episode_id=24, seed=100094, result=Fail
|
| 10 |
+
episode_id=25, seed=100095, result=Fail
|
| 11 |
+
episode_id=26, seed=100096, result=Fail
|
| 12 |
+
episode_id=27, seed=100097, result=Fail
|
| 13 |
+
episode_id=28, seed=100098, result=Fail
|
| 14 |
+
episode_id=29, seed=100099, result=Fail
|
| 15 |
+
episode_id=30, seed=100100, result=Fail
|
| 16 |
+
episode_id=31, seed=100101, result=Fail
|
| 17 |
+
episode_id=32, seed=100102, result=Success
|
| 18 |
+
episode_id=33, seed=100103, result=Fail
|
| 19 |
+
episode_id=34, seed=100104, result=Fail
|
| 20 |
+
episode_id=35, seed=100105, result=Fail
|
| 21 |
+
episode_id=36, seed=100106, result=Fail
|
| 22 |
+
episode_id=37, seed=100107, result=Fail
|
| 23 |
+
episode_id=38, seed=100108, result=Fail
|
| 24 |
+
episode_id=39, seed=100109, result=Fail
|
| 25 |
+
episode_id=40, seed=100110, result=Fail
|
| 26 |
+
episode_id=41, seed=100111, result=Fail
|
| 27 |
+
episode_id=42, seed=100112, result=Fail
|
| 28 |
+
episode_id=43, seed=100113, result=Success
|
| 29 |
+
episode_id=44, seed=100114, result=Fail
|
| 30 |
+
episode_id=45, seed=100115, result=Fail
|
| 31 |
+
episode_id=46, seed=100116, result=Fail
|
| 32 |
+
episode_id=47, seed=100117, result=Fail
|
| 33 |
+
episode_id=48, seed=100118, result=Fail
|
| 34 |
+
episode_id=49, seed=100119, result=Fail
|
| 35 |
+
episode_id=50, seed=100120, result=Fail
|
| 36 |
+
episode_id=51, seed=100121, result=Fail
|
| 37 |
+
episode_id=52, seed=100122, result=Fail
|
| 38 |
+
episode_id=53, seed=100123, result=Fail
|
| 39 |
+
episode_id=54, seed=100124, result=Success
|
eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for classify_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:23/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for classify_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:32:23
|
| 3 |
+
|
eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:35:58/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for classify_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:35:58
|
| 3 |
+
|
eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:43:26/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for classify_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-19 06:43:26
|
| 3 |
+
|
eval_result/classify_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:23:39/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for classify_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-04-04 15:23:39
|
| 3 |
+
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for cover_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:32:14/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for cover_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:32:14
|
| 3 |
+
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:36:50/eval_log.txt
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for cover_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:36:50
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100029, result=Fail
|
| 33 |
+
episode_id=29, seed=100030, result=Fail
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-04-04 15:29:22
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.0
|
| 6 |
+
|
| 7 |
+
Reward: 0.001
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:14:44/eval_log.txt
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for cover_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 11:14:44
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Fail
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Fail
|
| 41 |
+
episode_id=37, seed=100037, result=Fail
|
| 42 |
+
episode_id=38, seed=100038, result=Fail
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Fail
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Fail
|
| 48 |
+
episode_id=44, seed=100044, result=Fail
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Fail
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Fail
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Fail
|
| 57 |
+
episode_id=53, seed=100053, result=Fail
|
| 58 |
+
episode_id=54, seed=100054, result=Fail
|
| 59 |
+
episode_id=55, seed=100055, result=Fail
|
| 60 |
+
episode_id=56, seed=100056, result=Fail
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Fail
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Fail
|
| 67 |
+
episode_id=63, seed=100063, result=Fail
|
| 68 |
+
episode_id=64, seed=100064, result=Fail
|
| 69 |
+
episode_id=65, seed=100065, result=Fail
|
| 70 |
+
episode_id=66, seed=100066, result=Fail
|
| 71 |
+
episode_id=67, seed=100067, result=Fail
|
| 72 |
+
episode_id=68, seed=100068, result=Fail
|
| 73 |
+
episode_id=69, seed=100069, result=Fail
|
| 74 |
+
episode_id=70, seed=100070, result=Fail
|
| 75 |
+
episode_id=71, seed=100071, result=Fail
|
| 76 |
+
episode_id=72, seed=100072, result=Fail
|
| 77 |
+
episode_id=73, seed=100073, result=Fail
|
| 78 |
+
episode_id=74, seed=100074, result=Fail
|
| 79 |
+
episode_id=75, seed=100075, result=Fail
|
| 80 |
+
episode_id=76, seed=100076, result=Fail
|
| 81 |
+
episode_id=77, seed=100077, result=Fail
|
| 82 |
+
episode_id=78, seed=100078, result=Fail
|
| 83 |
+
episode_id=79, seed=100079, result=Fail
|
| 84 |
+
episode_id=80, seed=100080, result=Fail
|
| 85 |
+
episode_id=81, seed=100081, result=Fail
|
| 86 |
+
episode_id=82, seed=100082, result=Fail
|
| 87 |
+
episode_id=83, seed=100083, result=Fail
|
| 88 |
+
episode_id=84, seed=100084, result=Fail
|
| 89 |
+
episode_id=85, seed=100085, result=Fail
|
| 90 |
+
episode_id=86, seed=100086, result=Fail
|
| 91 |
+
episode_id=87, seed=100087, result=Fail
|
| 92 |
+
episode_id=88, seed=100088, result=Fail
|
| 93 |
+
episode_id=89, seed=100089, result=Fail
|
| 94 |
+
episode_id=90, seed=100090, result=Fail
|
| 95 |
+
episode_id=91, seed=100091, result=Fail
|
eval_result/cover_blocks/pi05/demo_clean/demo_clean/2026-04-04 15:29:22/eval_log.txt
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for cover_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-04-04 15:29:22
|
| 3 |
+
|
| 4 |
+
episode_id=92, seed=100092, result=Fail
|
| 5 |
+
episode_id=93, seed=100093, result=Fail
|
| 6 |
+
episode_id=94, seed=100094, result=Fail
|
| 7 |
+
episode_id=95, seed=100095, result=Fail
|
| 8 |
+
episode_id=96, seed=100096, result=Fail
|
| 9 |
+
episode_id=97, seed=100097, result=Fail
|
| 10 |
+
episode_id=98, seed=100098, result=Fail
|
| 11 |
+
episode_id=99, seed=100099, result=Fail
|
eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for observe_and_pickup | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-03-15 18:10:47
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.11
|
| 6 |
+
|
| 7 |
+
Reward: 0.0
|
eval_result/observe_and_pickup/pi05/demo_clean/demo_clean/2026-03-15 18:10:47/eval_log.txt
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for observe_and_pickup | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 18:10:47
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Success
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Success
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Success
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Success
|
| 41 |
+
episode_id=37, seed=100037, result=Success
|
| 42 |
+
episode_id=38, seed=100038, result=Success
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Success
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Fail
|
| 48 |
+
episode_id=44, seed=100044, result=Fail
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Fail
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Fail
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Fail
|
| 57 |
+
episode_id=53, seed=100053, result=Fail
|
| 58 |
+
episode_id=54, seed=100054, result=Success
|
| 59 |
+
episode_id=55, seed=100055, result=Fail
|
| 60 |
+
episode_id=56, seed=100056, result=Fail
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Fail
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Fail
|
| 67 |
+
episode_id=63, seed=100063, result=Fail
|
| 68 |
+
episode_id=64, seed=100064, result=Fail
|
| 69 |
+
episode_id=65, seed=100065, result=Fail
|
| 70 |
+
episode_id=66, seed=100066, result=Fail
|
| 71 |
+
episode_id=67, seed=100067, result=Fail
|
| 72 |
+
episode_id=68, seed=100068, result=Fail
|
| 73 |
+
episode_id=69, seed=100069, result=Fail
|
| 74 |
+
episode_id=70, seed=100070, result=Fail
|
| 75 |
+
episode_id=71, seed=100071, result=Success
|
| 76 |
+
episode_id=72, seed=100072, result=Fail
|
| 77 |
+
episode_id=73, seed=100073, result=Fail
|
| 78 |
+
episode_id=74, seed=100074, result=Fail
|
| 79 |
+
episode_id=75, seed=100075, result=Fail
|
| 80 |
+
episode_id=76, seed=100076, result=Fail
|
| 81 |
+
episode_id=77, seed=100077, result=Fail
|
| 82 |
+
episode_id=78, seed=100078, result=Fail
|
| 83 |
+
episode_id=79, seed=100079, result=Fail
|
| 84 |
+
episode_id=80, seed=100080, result=Fail
|
| 85 |
+
episode_id=81, seed=100081, result=Fail
|
| 86 |
+
episode_id=82, seed=100082, result=Fail
|
| 87 |
+
episode_id=83, seed=100083, result=Fail
|
| 88 |
+
episode_id=84, seed=100084, result=Fail
|
| 89 |
+
episode_id=85, seed=100085, result=Fail
|
| 90 |
+
episode_id=86, seed=100086, result=Fail
|
| 91 |
+
episode_id=87, seed=100087, result=Fail
|
| 92 |
+
episode_id=88, seed=100088, result=Fail
|
| 93 |
+
episode_id=89, seed=100089, result=Success
|
| 94 |
+
episode_id=90, seed=100091, result=Fail
|
| 95 |
+
episode_id=91, seed=100092, result=Fail
|
| 96 |
+
episode_id=92, seed=100094, result=Success
|
| 97 |
+
episode_id=93, seed=100095, result=Fail
|
| 98 |
+
episode_id=94, seed=100096, result=Fail
|
| 99 |
+
episode_id=95, seed=100097, result=Fail
|
| 100 |
+
episode_id=96, seed=100098, result=Fail
|
| 101 |
+
episode_id=97, seed=100099, result=Fail
|
| 102 |
+
episode_id=98, seed=100100, result=Fail
|
| 103 |
+
episode_id=99, seed=100101, result=Fail
|
eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for place_block_mat | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 02:46:58/eval_log.txt
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for place_block_mat | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:46:58
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-04-04 15:29:19
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.0
|
| 6 |
+
|
| 7 |
+
Reward: 0.0
|
eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-03-17 11:20:15/eval_log.txt
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for place_block_mat | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 11:20:15
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Fail
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Fail
|
| 41 |
+
episode_id=37, seed=100037, result=Fail
|
| 42 |
+
episode_id=38, seed=100038, result=Fail
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Fail
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Fail
|
| 48 |
+
episode_id=44, seed=100044, result=Fail
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Fail
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Fail
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Fail
|
| 57 |
+
episode_id=53, seed=100053, result=Fail
|
| 58 |
+
episode_id=54, seed=100054, result=Fail
|
| 59 |
+
episode_id=55, seed=100055, result=Fail
|
| 60 |
+
episode_id=56, seed=100056, result=Fail
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Fail
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Fail
|
| 67 |
+
episode_id=63, seed=100063, result=Fail
|
| 68 |
+
episode_id=64, seed=100064, result=Fail
|
| 69 |
+
episode_id=65, seed=100065, result=Fail
|
| 70 |
+
episode_id=66, seed=100066, result=Fail
|
| 71 |
+
episode_id=67, seed=100067, result=Fail
|
| 72 |
+
episode_id=68, seed=100068, result=Fail
|
| 73 |
+
episode_id=69, seed=100069, result=Fail
|
| 74 |
+
episode_id=70, seed=100070, result=Fail
|
| 75 |
+
episode_id=71, seed=100071, result=Fail
|
| 76 |
+
episode_id=72, seed=100072, result=Fail
|
| 77 |
+
episode_id=73, seed=100073, result=Fail
|
| 78 |
+
episode_id=74, seed=100074, result=Fail
|
| 79 |
+
episode_id=75, seed=100075, result=Fail
|
| 80 |
+
episode_id=76, seed=100076, result=Fail
|
| 81 |
+
episode_id=77, seed=100077, result=Fail
|
| 82 |
+
episode_id=78, seed=100078, result=Fail
|
| 83 |
+
episode_id=79, seed=100079, result=Fail
|
| 84 |
+
episode_id=80, seed=100080, result=Fail
|
| 85 |
+
episode_id=81, seed=100081, result=Fail
|
| 86 |
+
episode_id=82, seed=100082, result=Fail
|
| 87 |
+
episode_id=83, seed=100083, result=Fail
|
eval_result/place_block_mat/pi05/demo_clean/demo_clean/2026-04-04 15:29:19/eval_log.txt
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for place_block_mat | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-04-04 15:29:19
|
| 3 |
+
|
| 4 |
+
episode_id=84, seed=100084, result=Fail
|
| 5 |
+
episode_id=85, seed=100085, result=Fail
|
| 6 |
+
episode_id=86, seed=100086, result=Fail
|
| 7 |
+
episode_id=87, seed=100087, result=Fail
|
| 8 |
+
episode_id=88, seed=100088, result=Fail
|
| 9 |
+
episode_id=89, seed=100089, result=Fail
|
| 10 |
+
episode_id=90, seed=100090, result=Fail
|
| 11 |
+
episode_id=91, seed=100091, result=Fail
|
| 12 |
+
episode_id=92, seed=100092, result=Fail
|
| 13 |
+
episode_id=93, seed=100093, result=Fail
|
| 14 |
+
episode_id=94, seed=100094, result=Fail
|
| 15 |
+
episode_id=95, seed=100095, result=Fail
|
| 16 |
+
episode_id=96, seed=100096, result=Fail
|
| 17 |
+
episode_id=97, seed=100097, result=Fail
|
| 18 |
+
episode_id=98, seed=100098, result=Fail
|
| 19 |
+
episode_id=99, seed=100099, result=Fail
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-12 20:24:28/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-12 20:24:28
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 01:23:00/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-13 01:23:00
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 21:15:31/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-13 21:15:31
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-13 22:40:29/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-13 22:40:29
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 02:33:22/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-14 02:33:22
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-14 16:31:38/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-14 16:31:38
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 01:00:34/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 01:00:34
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:00:56/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 14:00:56
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 14:53:19/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 14:53:19
|
| 3 |
+
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-03-15 16:22:31
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.0
|
| 6 |
+
|
| 7 |
+
Reward: 0.0
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 16:22:31/eval_log.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 16:22:31
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
eval_result/press_button/pi05/demo_clean/demo_clean/2026-03-15 17:53:30/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for press_button | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 17:53:30
|
| 3 |
+
|
eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-03-15 23:05:55
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.13
|
| 6 |
+
|
| 7 |
+
Reward: 0.13
|
eval_result/put_back_block/pi05/demo_clean/demo_clean/2026-03-15 23:05:55/eval_log.txt
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for put_back_block | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 23:05:55
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Success
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Success
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Success
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Success
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Fail
|
| 41 |
+
episode_id=37, seed=100037, result=Fail
|
| 42 |
+
episode_id=38, seed=100038, result=Fail
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Fail
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Fail
|
| 48 |
+
episode_id=44, seed=100044, result=Fail
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Success
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Success
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Success
|
| 57 |
+
episode_id=53, seed=100053, result=Fail
|
| 58 |
+
episode_id=54, seed=100054, result=Fail
|
| 59 |
+
episode_id=55, seed=100055, result=Success
|
| 60 |
+
episode_id=56, seed=100056, result=Fail
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Success
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Fail
|
| 67 |
+
episode_id=63, seed=100063, result=Fail
|
| 68 |
+
episode_id=64, seed=100064, result=Fail
|
| 69 |
+
episode_id=65, seed=100065, result=Fail
|
| 70 |
+
episode_id=66, seed=100066, result=Fail
|
| 71 |
+
episode_id=67, seed=100067, result=Fail
|
| 72 |
+
episode_id=68, seed=100068, result=Fail
|
| 73 |
+
episode_id=69, seed=100069, result=Fail
|
| 74 |
+
episode_id=70, seed=100070, result=Fail
|
| 75 |
+
episode_id=71, seed=100071, result=Success
|
| 76 |
+
episode_id=72, seed=100072, result=Fail
|
| 77 |
+
episode_id=73, seed=100073, result=Fail
|
| 78 |
+
episode_id=74, seed=100074, result=Fail
|
| 79 |
+
episode_id=75, seed=100075, result=Fail
|
| 80 |
+
episode_id=76, seed=100076, result=Fail
|
| 81 |
+
episode_id=77, seed=100077, result=Fail
|
| 82 |
+
episode_id=78, seed=100078, result=Fail
|
| 83 |
+
episode_id=79, seed=100079, result=Success
|
| 84 |
+
episode_id=80, seed=100080, result=Fail
|
| 85 |
+
episode_id=81, seed=100081, result=Fail
|
| 86 |
+
episode_id=82, seed=100082, result=Fail
|
| 87 |
+
episode_id=83, seed=100083, result=Fail
|
| 88 |
+
episode_id=84, seed=100084, result=Success
|
| 89 |
+
episode_id=85, seed=100085, result=Fail
|
| 90 |
+
episode_id=86, seed=100086, result=Success
|
| 91 |
+
episode_id=87, seed=100087, result=Fail
|
| 92 |
+
episode_id=88, seed=100088, result=Fail
|
| 93 |
+
episode_id=89, seed=100089, result=Fail
|
| 94 |
+
episode_id=90, seed=100090, result=Fail
|
| 95 |
+
episode_id=91, seed=100091, result=Fail
|
| 96 |
+
episode_id=92, seed=100092, result=Fail
|
| 97 |
+
episode_id=93, seed=100093, result=Fail
|
| 98 |
+
episode_id=94, seed=100094, result=Fail
|
| 99 |
+
episode_id=95, seed=100095, result=Fail
|
| 100 |
+
episode_id=96, seed=100096, result=Fail
|
| 101 |
+
episode_id=97, seed=100097, result=Fail
|
| 102 |
+
episode_id=98, seed=100098, result=Fail
|
| 103 |
+
episode_id=99, seed=100099, result=Fail
|
eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-15 19:32:34/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for rearrange_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-15 19:32:34
|
| 3 |
+
|
eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 02:28:17/eval_log.txt
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for rearrange_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 02:28:17
|
| 3 |
+
|
| 4 |
+
episode_id=0, seed=100000, result=Fail
|
| 5 |
+
episode_id=1, seed=100001, result=Fail
|
| 6 |
+
episode_id=2, seed=100002, result=Fail
|
| 7 |
+
episode_id=3, seed=100003, result=Fail
|
| 8 |
+
episode_id=4, seed=100004, result=Fail
|
| 9 |
+
episode_id=5, seed=100005, result=Fail
|
| 10 |
+
episode_id=6, seed=100006, result=Fail
|
| 11 |
+
episode_id=7, seed=100007, result=Fail
|
| 12 |
+
episode_id=8, seed=100008, result=Fail
|
| 13 |
+
episode_id=9, seed=100009, result=Fail
|
| 14 |
+
episode_id=10, seed=100010, result=Fail
|
| 15 |
+
episode_id=11, seed=100011, result=Fail
|
| 16 |
+
episode_id=12, seed=100012, result=Fail
|
| 17 |
+
episode_id=13, seed=100013, result=Fail
|
| 18 |
+
episode_id=14, seed=100014, result=Fail
|
| 19 |
+
episode_id=15, seed=100015, result=Fail
|
| 20 |
+
episode_id=16, seed=100016, result=Fail
|
| 21 |
+
episode_id=17, seed=100017, result=Fail
|
| 22 |
+
episode_id=18, seed=100018, result=Fail
|
| 23 |
+
episode_id=19, seed=100019, result=Fail
|
| 24 |
+
episode_id=20, seed=100020, result=Fail
|
| 25 |
+
episode_id=21, seed=100021, result=Fail
|
| 26 |
+
episode_id=22, seed=100022, result=Fail
|
| 27 |
+
episode_id=23, seed=100023, result=Fail
|
| 28 |
+
episode_id=24, seed=100024, result=Fail
|
| 29 |
+
episode_id=25, seed=100025, result=Fail
|
| 30 |
+
episode_id=26, seed=100026, result=Fail
|
| 31 |
+
episode_id=27, seed=100027, result=Fail
|
| 32 |
+
episode_id=28, seed=100028, result=Fail
|
| 33 |
+
episode_id=29, seed=100029, result=Fail
|
| 34 |
+
episode_id=30, seed=100030, result=Fail
|
| 35 |
+
episode_id=31, seed=100031, result=Fail
|
| 36 |
+
episode_id=32, seed=100032, result=Fail
|
| 37 |
+
episode_id=33, seed=100033, result=Fail
|
| 38 |
+
episode_id=34, seed=100034, result=Fail
|
| 39 |
+
episode_id=35, seed=100035, result=Fail
|
| 40 |
+
episode_id=36, seed=100036, result=Fail
|
| 41 |
+
episode_id=37, seed=100037, result=Fail
|
| 42 |
+
episode_id=38, seed=100038, result=Fail
|
| 43 |
+
episode_id=39, seed=100039, result=Fail
|
| 44 |
+
episode_id=40, seed=100040, result=Success
|
| 45 |
+
episode_id=41, seed=100041, result=Fail
|
| 46 |
+
episode_id=42, seed=100042, result=Fail
|
| 47 |
+
episode_id=43, seed=100043, result=Success
|
| 48 |
+
episode_id=44, seed=100044, result=Success
|
| 49 |
+
episode_id=45, seed=100045, result=Fail
|
| 50 |
+
episode_id=46, seed=100046, result=Fail
|
| 51 |
+
episode_id=47, seed=100047, result=Fail
|
| 52 |
+
episode_id=48, seed=100048, result=Fail
|
| 53 |
+
episode_id=49, seed=100049, result=Fail
|
| 54 |
+
episode_id=50, seed=100050, result=Fail
|
| 55 |
+
episode_id=51, seed=100051, result=Fail
|
| 56 |
+
episode_id=52, seed=100052, result=Fail
|
| 57 |
+
episode_id=53, seed=100053, result=Success
|
| 58 |
+
episode_id=54, seed=100054, result=Fail
|
| 59 |
+
episode_id=55, seed=100055, result=Fail
|
| 60 |
+
episode_id=56, seed=100056, result=Success
|
| 61 |
+
episode_id=57, seed=100057, result=Fail
|
| 62 |
+
episode_id=58, seed=100058, result=Fail
|
| 63 |
+
episode_id=59, seed=100059, result=Fail
|
| 64 |
+
episode_id=60, seed=100060, result=Fail
|
| 65 |
+
episode_id=61, seed=100061, result=Fail
|
| 66 |
+
episode_id=62, seed=100062, result=Success
|
eval_result/rearrange_blocks/pi05/demo_clean/demo_clean/2026-03-17 from_log/_result.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Timestamp: 2026-03-17 (extracted from job 2971341 log)
|
| 2 |
+
|
| 3 |
+
Instruction Type: unseen
|
| 4 |
+
|
| 5 |
+
Success Rate: 0.06
|
| 6 |
+
|
| 7 |
+
Reward: 0.0
|
eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-17 11:33:35/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for storage_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-17 11:33:35
|
| 3 |
+
|
eval_result/storage_blocks/pi05/demo_clean/demo_clean/2026-03-19 06:45:04/eval_log.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval log for storage_blocks | pi05 | demo_clean | demo_clean
|
| 2 |
+
Timestamp: 2026-03-19 06:45:04
|
| 3 |
+
|