Hugging Face's logo

anhtld
/
vla

Model card Files
xet
 Community
anhtld commited on
Commit
9b85a25
·
verified ·
1 Parent(s): 6f15887

targeted sync runs/utility_energy_smoke

Browse files
Files changed (11) hide show
  1. workspace/runs/utility_energy_smoke/command.txt +1 -0
  2. workspace/runs/utility_energy_smoke/config.yaml +11 -0
  3. workspace/runs/utility_energy_smoke/data_hash.txt +1 -0
  4. workspace/runs/utility_energy_smoke/eval.log +1 -0
  5. workspace/runs/utility_energy_smoke/git_hash.txt +1 -0
  6. workspace/runs/utility_energy_smoke/metrics_by_seed.json +176 -0
  7. workspace/runs/utility_energy_smoke/metrics_by_task.json +32 -0
  8. workspace/runs/utility_energy_smoke/model.pt +3 -0
  9. workspace/runs/utility_energy_smoke/split_hash.txt +1 -0
  10. workspace/runs/utility_energy_smoke/table.tex +11 -0
  11. workspace/runs/utility_energy_smoke/train.log +2 -0
workspace/runs/utility_energy_smoke/command.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ python scripts/train_utility_energy.py --dataset data/cil_charts/train/index.json --out-dir runs/utility_energy_smoke --epochs 1 --max-charts 32 --lr 0.001 --seed 0
workspace/runs/utility_energy_smoke/config.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dataset: data/cil_charts/train/index.json
2
+ epochs: 1
3
+ listwise_rank: 1.0
4
+ lr: 0.001
5
+ margin: 0.5
6
+ max_charts: 32
7
+ out_dir: runs/utility_energy_smoke
8
+ outcome: 1.0
9
+ pairwise_rank: 2.0
10
+ seed: 0
11
+ temperature: 1.0
workspace/runs/utility_energy_smoke/data_hash.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 90b431047a1f35cec095cbafa7de5bc0126cb0d0f4db3ff31843dca369977957
workspace/runs/utility_energy_smoke/eval.log ADDED
@@ -0,0 +1 @@
 
 
1
+ evaluated on train charts for smoke calibration diagnostics
workspace/runs/utility_energy_smoke/git_hash.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 14e81292e2004925f81e0bb4810f6f144bfd87b7
workspace/runs/utility_energy_smoke/metrics_by_seed.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1054295834": {
3
+ "mean_abs_outcome_error": 0.06449826061725616,
4
+ "mean_abs_utility_error": 0.7696523666381836,
5
+ "pairwise_accuracy": 0.7692307692307693,
6
+ "pairwise_causal_calibration_ece": 0.2578268755856008
7
+ },
8
+ "111895951": {
9
+ "mean_abs_outcome_error": 0.05422291159629822,
10
+ "mean_abs_utility_error": 0.4873132109642029,
11
+ "pairwise_accuracy": 0.7333333333333333,
12
+ "pairwise_causal_calibration_ece": 0.21221080849778506
13
+ },
14
+ "1148327469": {
15
+ "mean_abs_outcome_error": 0.046550530940294266,
16
+ "mean_abs_utility_error": 0.7782812714576721,
17
+ "pairwise_accuracy": 0.7,
18
+ "pairwise_causal_calibration_ece": 0.17109290430604018
19
+ },
20
+ "1151410346": {
21
+ "mean_abs_outcome_error": 0.06774069368839264,
22
+ "mean_abs_utility_error": 0.8256913423538208,
23
+ "pairwise_accuracy": 0.6638655462184874,
24
+ "pairwise_causal_calibration_ece": 0.140139987278719
25
+ },
26
+ "1231384138": {
27
+ "mean_abs_outcome_error": 0.04421722888946533,
28
+ "mean_abs_utility_error": 0.7255164980888367,
29
+ "pairwise_accuracy": 0.6416666666666667,
30
+ "pairwise_causal_calibration_ece": 0.1155098143008102
31
+ },
32
+ "1369129094": {
33
+ "mean_abs_outcome_error": 0.07047047466039658,
34
+ "mean_abs_utility_error": 0.8302875757217407,
35
+ "pairwise_accuracy": 0.7226890756302521,
36
+ "pairwise_causal_calibration_ece": 0.19875563809574193
37
+ },
38
+ "1461069713": {
39
+ "mean_abs_outcome_error": 0.04733149707317352,
40
+ "mean_abs_utility_error": 0.6884127557277679,
41
+ "pairwise_accuracy": 0.6654815772462831,
42
+ "pairwise_causal_calibration_ece": 0.14060988241804512
43
+ },
44
+ "1671659352": {
45
+ "mean_abs_outcome_error": 0.06975866109132767,
46
+ "mean_abs_utility_error": 0.8692922592163086,
47
+ "pairwise_accuracy": 0.5966386554621849,
48
+ "pairwise_causal_calibration_ece": 0.07345783732768185
49
+ },
50
+ "1676419878": {
51
+ "mean_abs_outcome_error": 0.03491806238889694,
52
+ "mean_abs_utility_error": 0.5755202770233154,
53
+ "pairwise_accuracy": 0.6083333333333333,
54
+ "pairwise_causal_calibration_ece": 0.08908094932807686
55
+ },
56
+ "1753014417": {
57
+ "mean_abs_outcome_error": 0.03609073907136917,
58
+ "mean_abs_utility_error": 0.5264366865158081,
59
+ "pairwise_accuracy": 0.5833333333333334,
60
+ "pairwise_causal_calibration_ece": 0.07226753454553303
61
+ },
62
+ "1754115693": {
63
+ "mean_abs_outcome_error": 0.03463064506649971,
64
+ "mean_abs_utility_error": 0.5596855878829956,
65
+ "pairwise_accuracy": 0.5916666666666667,
66
+ "pairwise_causal_calibration_ece": 0.04994094741586674
67
+ },
68
+ "1824746139": {
69
+ "mean_abs_outcome_error": 0.0978042408823967,
70
+ "mean_abs_utility_error": 0.9380365610122681,
71
+ "pairwise_accuracy": 0.4818181818181818,
72
+ "pairwise_causal_calibration_ece": 0.02412205504980458
73
+ },
74
+ "1867746099": {
75
+ "mean_abs_outcome_error": 0.039407987147569656,
76
+ "mean_abs_utility_error": 0.6002693772315979,
77
+ "pairwise_accuracy": 0.6,
78
+ "pairwise_causal_calibration_ece": 0.077571216040902
79
+ },
80
+ "1894022513": {
81
+ "mean_abs_outcome_error": 0.05661546066403389,
82
+ "mean_abs_utility_error": 0.7380750775337219,
83
+ "pairwise_accuracy": 0.6333333333333333,
84
+ "pairwise_causal_calibration_ece": 0.10660925539691046
85
+ },
86
+ "1982046304": {
87
+ "mean_abs_outcome_error": 0.05973448604345322,
88
+ "mean_abs_utility_error": 0.6622100472450256,
89
+ "pairwise_accuracy": 0.6916666666666667,
90
+ "pairwise_causal_calibration_ece": 0.17267163927357554
91
+ },
92
+ "2015956957": {
93
+ "mean_abs_outcome_error": 0.03562131151556969,
94
+ "mean_abs_utility_error": 0.5002692937850952,
95
+ "pairwise_accuracy": 0.725,
96
+ "pairwise_causal_calibration_ece": 0.2107236792507069
97
+ },
98
+ "2061635888": {
99
+ "mean_abs_outcome_error": 0.040086567401885986,
100
+ "mean_abs_utility_error": 0.6989057660102844,
101
+ "pairwise_accuracy": 0.625,
102
+ "pairwise_causal_calibration_ece": 0.09649891842648839
103
+ },
104
+ "2099816463": {
105
+ "mean_abs_outcome_error": 0.07301713526248932,
106
+ "mean_abs_utility_error": 0.8979111313819885,
107
+ "pairwise_accuracy": 0.7983193277310925,
108
+ "pairwise_causal_calibration_ece": 0.2748533906818609
109
+ },
110
+ "278008524": {
111
+ "mean_abs_outcome_error": 0.016714444383978844,
112
+ "mean_abs_utility_error": 0.513826847076416,
113
+ "pairwise_accuracy": 0.375,
114
+ "pairwise_causal_calibration_ece": 0.13848124754891455
115
+ },
116
+ "451255434": {
117
+ "mean_abs_outcome_error": 0.025612499564886093,
118
+ "mean_abs_utility_error": 0.4249221086502075,
119
+ "pairwise_accuracy": 0.6916666666666667,
120
+ "pairwise_causal_calibration_ece": 0.16814035014460327
121
+ },
122
+ "460988816": {
123
+ "mean_abs_outcome_error": 0.055287424474954605,
124
+ "mean_abs_utility_error": 0.7063317894935608,
125
+ "pairwise_accuracy": 0.7,
126
+ "pairwise_causal_calibration_ece": 0.1735221201437922
127
+ },
128
+ "500109393": {
129
+ "mean_abs_outcome_error": 0.06238825246691704,
130
+ "mean_abs_utility_error": 0.9378910660743713,
131
+ "pairwise_accuracy": 0.4957983193277311,
132
+ "pairwise_causal_calibration_ece": 0.019596244022319853
133
+ },
134
+ "565369392": {
135
+ "mean_abs_outcome_error": 0.017789587378501892,
136
+ "mean_abs_utility_error": 0.401470422744751,
137
+ "pairwise_accuracy": 0.5333333333333333,
138
+ "pairwise_causal_calibration_ece": 0.023225169087835784
139
+ },
140
+ "585904130": {
141
+ "mean_abs_outcome_error": 0.041935949275890984,
142
+ "mean_abs_utility_error": 0.5876917441685995,
143
+ "pairwise_accuracy": 0.6565527065527065,
144
+ "pairwise_causal_calibration_ece": 0.15108333112758962
145
+ },
146
+ "626486813": {
147
+ "mean_abs_outcome_error": 0.029401155188679695,
148
+ "mean_abs_utility_error": 0.26239433884620667,
149
+ "pairwise_accuracy": 0.7,
150
+ "pairwise_causal_calibration_ece": 0.19213148845615236
151
+ },
152
+ "645859527": {
153
+ "mean_abs_outcome_error": 0.04072529077529907,
154
+ "mean_abs_utility_error": 0.7450370788574219,
155
+ "pairwise_accuracy": 0.6666666666666666,
156
+ "pairwise_causal_calibration_ece": 0.14993840550534232
157
+ },
158
+ "692998894": {
159
+ "mean_abs_outcome_error": 0.04164355993270874,
160
+ "mean_abs_utility_error": 0.7494800090789795,
161
+ "pairwise_accuracy": 0.75,
162
+ "pairwise_causal_calibration_ece": 0.22331983511205478
163
+ },
164
+ "750448296": {
165
+ "mean_abs_outcome_error": 0.02126285433769226,
166
+ "mean_abs_utility_error": 0.394942045211792,
167
+ "pairwise_accuracy": 0.55,
168
+ "pairwise_causal_calibration_ece": 0.040736455972501195
169
+ },
170
+ "848613296": {
171
+ "mean_abs_outcome_error": 0.04095236584544182,
172
+ "mean_abs_utility_error": 0.5620254874229431,
173
+ "pairwise_accuracy": 0.525,
174
+ "pairwise_causal_calibration_ece": 0.0034121474393626894
175
+ }
176
+ }
workspace/runs/utility_energy_smoke/metrics_by_task.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "LiftPegUpright-v1": {
3
+ "mean_abs_outcome_error": 0.04782690852880478,
4
+ "mean_abs_utility_error": 0.8026723563671112,
5
+ "pairwise_accuracy": 0.6531162464985995,
6
+ "pairwise_causal_calibration_ece": 0.14098684723643928
7
+ },
8
+ "PickCube-v1": {
9
+ "mean_abs_outcome_error": 0.05697869881987572,
10
+ "mean_abs_utility_error": 0.5747616291046143,
11
+ "pairwise_accuracy": 0.7124999999999999,
12
+ "pairwise_causal_calibration_ece": 0.1924412238856803
13
+ },
14
+ "PullCube-v1": {
15
+ "mean_abs_outcome_error": 0.03398542168239752,
16
+ "mean_abs_utility_error": 0.5166459406415621,
17
+ "pairwise_accuracy": 0.616718439512557,
18
+ "pairwise_causal_calibration_ece": 0.12594335800991133
19
+ },
20
+ "PushCube-v1": {
21
+ "mean_abs_outcome_error": 0.058327825739979744,
22
+ "mean_abs_utility_error": 0.7024114727973938,
23
+ "pairwise_accuracy": 0.6106789044289045,
24
+ "pairwise_causal_calibration_ece": 0.11082435362725382
25
+ },
26
+ "StackCube-v1": {
27
+ "mean_abs_outcome_error": 0.05512322783470154,
28
+ "mean_abs_utility_error": 0.7451966404914856,
29
+ "pairwise_accuracy": 0.6573179271708683,
30
+ "pairwise_causal_calibration_ece": 0.13068591251087736
31
+ }
32
+ }
workspace/runs/utility_energy_smoke/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445b8f7d3b9e601c6ee7de09b9d022abcd40dfe7fbbe4e638c3af06bca60f643
3
+ size 277319
workspace/runs/utility_energy_smoke/split_hash.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 867a94a1c67686c082765671a7bf8d74a9d633085e1b2619c83197c60bf58372
workspace/runs/utility_energy_smoke/table.tex ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ % Auto-generated by scripts/train_utility_energy.py
2
+ \begin{tabular}{lrr}
3
+ \toprule
4
+ Metric & N & Micro mean \\
5
+ \midrule
6
+ mean\_abs\_outcome\_error & 32 & 0.0468 \\
7
+ mean\_abs\_utility\_error & 32 & 0.6507 \\
8
+ pairwise\_accuracy & 32 & 0.6392 \\
9
+ pairwise\_causal\_calibration\_ece & 32 & 0.1316 \\
10
+ \bottomrule
11
+ \end{tabular}
workspace/runs/utility_energy_smoke/train.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ charts=32 epochs=1
2
+ epoch=1 mean_loss=1.687917