GnanaPraveen commited on
Commit
299b0de
·
verified ·
1 Parent(s): b76fd98

Upload verified evaluation/full-suite-manifest.json

Browse files
Files changed (1) hide show
  1. evaluation/full-suite-manifest.json +146 -0
evaluation/full-suite-manifest.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "baseline": {
3
+ "checkpoint": 55,
4
+ "episodes": 400,
5
+ "mean_partial_score": 0.39425,
6
+ "source_url": "https://app.notion.com/p/40ded7607a4081f48d77c47f8549784c",
7
+ "successes": 122
8
+ },
9
+ "checkpoint": 1000,
10
+ "decision_rule": "Finish all400 checkpoint1000 Precision episodes, then Memory, Generalization, Long Horizon and Open regardless of success rate or partial score; checkpoint950 cancelled by user.",
11
+ "execution_sources": {
12
+ "generalization.sbatch": "d6fc7abb1b6170704fa60e4ca75bb574952253316f59ca4ffc85d83bfdeff6ca",
13
+ "long_horizon.sbatch": "bdf112f24eb2fa5c85567731046544277cd209a561f50d65f54a07bb03a2a7e0",
14
+ "memory.sbatch": "efc073d50f80bb115c41cc9b8988c1afab1010e6c047f330cd71f12d8c3b1175",
15
+ "open.sbatch": "5dfd7afdcf8f4b5b97c5fd688b980f58bd61a1a4101a37c825005b55f2ed051c",
16
+ "precision_handoff.py": "9a783d94112f12542c6715aac55f802e66d392367c1c72cd8f9aa93f65374378",
17
+ "prepare_followup.py": "c2e457fdea0f9ef3a33f5c233ea019aea31ff89fb2982a5032cc4cadac2d01ac",
18
+ "suite_common.py": "157988d7033ea528b2dc9200359a4edfbb41e5d2f692da6487108669abf11b1f",
19
+ "suite_driver.py": "d4fc61af349bd499eddd5d061675405dedede1cda918765b1954d2ec85a55d8e",
20
+ "test_followup.py": "106e26b1be0059be2444054628000e1dee482ba315adec2ce0b9a46ba371941e"
21
+ },
22
+ "id": "c62f853a713ce9200730a1b937a619358a9c146f2d914ddddfe8988b27ae47d6",
23
+ "input_hashes": {
24
+ "inputs/authorization.json": "23aba269d4c3f71508be5fdc44e45fbfda7c358fef1ac4b761690f25cbbace45",
25
+ "inputs/generalization.json": "de5a880e127039c689082262619791f26eb66ae5ed1fe929b8308f93a818f6b5",
26
+ "inputs/long_horizon.json": "26a9c66ed3082a59ccbb11c1c43d5bc2ad0123ab66a3ffd27750e834c9de2d20",
27
+ "inputs/memory.json": "b961cfc82459c2a394922903cc6d275aaf647d8cb4561ebafc7dc259bc73928b",
28
+ "inputs/open.json": "3daaf3e86b2f7dacad8fbe063efc23aa06d805a5c50a60cac347395fec87f4a7",
29
+ "inputs/unconditional-authorization.json": "a33af04a144b2d59a15c8fe4a74fd93a6b5b94ab7539316abc09b553226bf43a"
30
+ },
31
+ "performance_condition": "none",
32
+ "precision_protocol": "266df4b5d9b8eac16145600a8c4f9223d15e03285d61473c3bbd8c43b694f211",
33
+ "precision_root": "/home/praveen/experiments/vpp2-recovery1000-950-precision-20261103",
34
+ "precision_tasks": [
35
+ "build_tower",
36
+ "insert_tubes",
37
+ "deposit_coin",
38
+ "fasten_screws",
39
+ "insert_key",
40
+ "play_Xylophone",
41
+ "plug_in_charger",
42
+ "pour_balls_into_vase"
43
+ ],
44
+ "replacements": [],
45
+ "revision_of": "f5491d41dd847cc86f52a9f9b8d7ffc9b8aa9642a595372aa20d51f5026b534f",
46
+ "schema": "checkpoint1000-unconditional-followup-v2",
47
+ "selection": "original",
48
+ "suite_order": [
49
+ "memory",
50
+ "generalization",
51
+ "long_horizon",
52
+ "open"
53
+ ],
54
+ "suites": {
55
+ "generalization": {
56
+ "episodes_file": "inputs/generalization.json",
57
+ "expected": 600,
58
+ "name": "generalization",
59
+ "overrides": {},
60
+ "reporting_holds": {},
61
+ "runtime": {
62
+ "protocol": "4d705e28dc3ee7b401ea3f851cfa2b205981a5009d65cc01f3bd467489d50ab6",
63
+ "root": "/data/praveen/vpp2-recovery1000-followup-20261104/generalization/runtime",
64
+ "update": 1000
65
+ },
66
+ "task_order": [
67
+ "stack_bowls",
68
+ "push_T",
69
+ "pack_objects_into_box",
70
+ "fold_clothes",
71
+ "hang_mugs",
72
+ "sweep_blocks",
73
+ "pour_liquid_into_cup",
74
+ "make_toast",
75
+ "arrange_largest_number",
76
+ "sort_nesting_dolls_by_size",
77
+ "store_laptop_and_headphones",
78
+ "stack_blocks"
79
+ ]
80
+ },
81
+ "long_horizon": {
82
+ "episodes_file": "inputs/long_horizon.json",
83
+ "expected": 400,
84
+ "name": "long_horizon",
85
+ "overrides": {},
86
+ "reporting_holds": {},
87
+ "runtime": {
88
+ "protocol": "c2867b1bb38b88d54cbe92103a5cf6d2020c3d44f67c89412182265c4bac8256",
89
+ "root": "/data/praveen/vpp2-recovery1000-followup-20261104/long_horizon/runtime",
90
+ "update": 1000
91
+ },
92
+ "task_order": [
93
+ "put_bottles_into_dustbin",
94
+ "fill_pen_holder",
95
+ "classify_objects",
96
+ "play_tic_tac_toe",
97
+ "fill_egg_holder",
98
+ "organize_table",
99
+ "make_kong",
100
+ "play_stacking_toy"
101
+ ]
102
+ },
103
+ "memory": {
104
+ "episodes_file": "inputs/memory.json",
105
+ "expected": 300,
106
+ "name": "memory",
107
+ "overrides": {},
108
+ "reporting_holds": {},
109
+ "runtime": {
110
+ "protocol": "35ef508554aee3ce8b89ddc3826fb6eda60bd022db79d6d91a60f6f37e7014f8",
111
+ "root": "/data/praveen/vpp2-recovery1000-followup-20261104/memory/runtime",
112
+ "update": 1000
113
+ },
114
+ "task_order": [
115
+ "cover_blocks",
116
+ "match_and_pick_from_conveyor",
117
+ "swap_blocks",
118
+ "swap_T",
119
+ "press_by_number",
120
+ "imitate_sorting_sequence"
121
+ ]
122
+ },
123
+ "open": {
124
+ "episodes_file": "inputs/open.json",
125
+ "expected": 400,
126
+ "name": "open",
127
+ "overrides": {},
128
+ "reporting_holds": {},
129
+ "runtime": {
130
+ "protocol": "92558f946ce17044692364bcb3515da3925bcf3c646266c8dc9ce1f38771384e",
131
+ "root": "/data/praveen/vpp2-recovery1000-followup-20261104/open/runtime",
132
+ "update": 1000
133
+ },
134
+ "task_order": [
135
+ "align_blocks",
136
+ "general_pickup",
137
+ "stack_blocks_by_language",
138
+ "solve_equation",
139
+ "classify_objects_by_language",
140
+ "pick_from_conveyor_by_image",
141
+ "store_tools_in_toolbox",
142
+ "pour_by_language"
143
+ ]
144
+ }
145
+ }
146
+ }