Hugging Face's logo

cccat6
/
FlowMo-WM

Robotics
PyTorch
world-model
visual-world-model
model-based-control
surface-vehicle
hidden-drift
Model card Files
xet
 Community
cccat6 commited on
Commit
23157ad
·
verified ·
1 Parent(s): 38965f7

Sync LeWorldModel training metadata

Browse files
Files changed (3) hide show
  1. experiments/leworldmodel/result/paper_training.json +43 -0
  2. experiments/leworldmodel/result/paper_training_trace.jsonl +100 -0
  3. experiments/leworldmodel/result/parameter_count.json +7 -0
experiments/leworldmodel/result/paper_training.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "method": "leworldmodel",
3
+ "steps": 20000,
4
+ "batch_size": 256,
5
+ "train_samples": 5120000,
6
+ "final_train_loss": 0.009550545364618301,
7
+ "total_parameters": 664612,
8
+ "target_mode": "absolute_normalized",
9
+ "position_scale": 5.0,
10
+ "heading_weight": 2.0,
11
+ "current_pose_weight": 1.0,
12
+ "motion_weight": 0.5,
13
+ "precision": "bf16",
14
+ "checkpoint_name": "paper.pt",
15
+ "final_checkpoint": "paper.pt",
16
+ "intermediate_checkpoints": [
17
+ "paper_step_002000.pt",
18
+ "paper_step_004000.pt",
19
+ "paper_step_006000.pt",
20
+ "paper_step_008000.pt",
21
+ "paper_step_010000.pt",
22
+ "paper_step_012000.pt",
23
+ "paper_step_014000.pt",
24
+ "paper_step_016000.pt",
25
+ "paper_step_018000.pt",
26
+ "paper_step_020000.pt"
27
+ ],
28
+ "checkpoint_interval": 2000,
29
+ "prediction": {
30
+ "pos1": 0.10077927494421601,
31
+ "heading1": 0.06080058395552138,
32
+ "pos3": 0.11628980577612917,
33
+ "heading3": 0.06710875616408885,
34
+ "pos6": 0.1408975877178212,
35
+ "heading6": 0.07597423201271643,
36
+ "pos8": 0.1572956770348052,
37
+ "heading8": 0.08126062775651614,
38
+ "pos10": 0.1729999102341632,
39
+ "heading10": 0.08616231808749338,
40
+ "pos20": 0.24561361921951175,
41
+ "heading20": 0.10545591303768258
42
+ }
43
+ }
experiments/leworldmodel/result/paper_training_trace.jsonl ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"method": "leworldmodel", "step": 200, "loss": 2.5742640495300293}
2
+ {"method": "leworldmodel", "step": 400, "loss": 2.4169535636901855}
3
+ {"method": "leworldmodel", "step": 600, "loss": 1.8758043050765991}
4
+ {"method": "leworldmodel", "step": 800, "loss": 1.8124264478683472}
5
+ {"method": "leworldmodel", "step": 1000, "loss": 1.7737553119659424}
6
+ {"method": "leworldmodel", "step": 1200, "loss": 1.7550112009048462}
7
+ {"method": "leworldmodel", "step": 1400, "loss": 1.7295875549316406}
8
+ {"method": "leworldmodel", "step": 1600, "loss": 1.6969983577728271}
9
+ {"method": "leworldmodel", "step": 1800, "loss": 1.5487231016159058}
10
+ {"method": "leworldmodel", "step": 2000, "loss": 1.2113735675811768}
11
+ {"method": "leworldmodel", "step": 2200, "loss": 0.4899616241455078}
12
+ {"method": "leworldmodel", "step": 2400, "loss": 0.25269925594329834}
13
+ {"method": "leworldmodel", "step": 2600, "loss": 0.1280742734670639}
14
+ {"method": "leworldmodel", "step": 2800, "loss": 0.0893140360713005}
15
+ {"method": "leworldmodel", "step": 3000, "loss": 0.06826942414045334}
16
+ {"method": "leworldmodel", "step": 3200, "loss": 0.055358901619911194}
17
+ {"method": "leworldmodel", "step": 3400, "loss": 0.04870389774441719}
18
+ {"method": "leworldmodel", "step": 3600, "loss": 0.042951736599206924}
19
+ {"method": "leworldmodel", "step": 3800, "loss": 0.04117833822965622}
20
+ {"method": "leworldmodel", "step": 4000, "loss": 0.033998213708400726}
21
+ {"method": "leworldmodel", "step": 4200, "loss": 0.03558700159192085}
22
+ {"method": "leworldmodel", "step": 4400, "loss": 0.04493999481201172}
23
+ {"method": "leworldmodel", "step": 4600, "loss": 0.02836284041404724}
24
+ {"method": "leworldmodel", "step": 4800, "loss": 0.02604031004011631}
25
+ {"method": "leworldmodel", "step": 5000, "loss": 0.028076427057385445}
26
+ {"method": "leworldmodel", "step": 5200, "loss": 0.025749407708644867}
27
+ {"method": "leworldmodel", "step": 5400, "loss": 0.025793232023715973}
28
+ {"method": "leworldmodel", "step": 5600, "loss": 0.023315150290727615}
29
+ {"method": "leworldmodel", "step": 5800, "loss": 0.02298635244369507}
30
+ {"method": "leworldmodel", "step": 6000, "loss": 0.023151235654950142}
31
+ {"method": "leworldmodel", "step": 6200, "loss": 0.022326592355966568}
32
+ {"method": "leworldmodel", "step": 6400, "loss": 0.020633624866604805}
33
+ {"method": "leworldmodel", "step": 6600, "loss": 0.02105795033276081}
34
+ {"method": "leworldmodel", "step": 6800, "loss": 0.019601183012127876}
35
+ {"method": "leworldmodel", "step": 7000, "loss": 0.029469886794686317}
36
+ {"method": "leworldmodel", "step": 7200, "loss": 0.019266480579972267}
37
+ {"method": "leworldmodel", "step": 7400, "loss": 0.01855972222983837}
38
+ {"method": "leworldmodel", "step": 7600, "loss": 0.01827949285507202}
39
+ {"method": "leworldmodel", "step": 7800, "loss": 0.01778957061469555}
40
+ {"method": "leworldmodel", "step": 8000, "loss": 0.018047360703349113}
41
+ {"method": "leworldmodel", "step": 8200, "loss": 0.018618818372488022}
42
+ {"method": "leworldmodel", "step": 8400, "loss": 0.0228111669421196}
43
+ {"method": "leworldmodel", "step": 8600, "loss": 0.01890629343688488}
44
+ {"method": "leworldmodel", "step": 8800, "loss": 0.01719030551612377}
45
+ {"method": "leworldmodel", "step": 9000, "loss": 0.016841214150190353}
46
+ {"method": "leworldmodel", "step": 9200, "loss": 0.01635475642979145}
47
+ {"method": "leworldmodel", "step": 9400, "loss": 0.015605655498802662}
48
+ {"method": "leworldmodel", "step": 9600, "loss": 0.01590617746114731}
49
+ {"method": "leworldmodel", "step": 9800, "loss": 0.016368960961699486}
50
+ {"method": "leworldmodel", "step": 10000, "loss": 0.016230706125497818}
51
+ {"method": "leworldmodel", "step": 10200, "loss": 0.0163402259349823}
52
+ {"method": "leworldmodel", "step": 10400, "loss": 0.015337882563471794}
53
+ {"method": "leworldmodel", "step": 10600, "loss": 0.015909960493445396}
54
+ {"method": "leworldmodel", "step": 10800, "loss": 0.015303711406886578}
55
+ {"method": "leworldmodel", "step": 11000, "loss": 0.013970066793262959}
56
+ {"method": "leworldmodel", "step": 11200, "loss": 0.014467062428593636}
57
+ {"method": "leworldmodel", "step": 11400, "loss": 0.013989393599331379}
58
+ {"method": "leworldmodel", "step": 11600, "loss": 0.014300663955509663}
59
+ {"method": "leworldmodel", "step": 11800, "loss": 0.027328936383128166}
60
+ {"method": "leworldmodel", "step": 12000, "loss": 0.034941356629133224}
61
+ {"method": "leworldmodel", "step": 12200, "loss": 0.013367080129683018}
62
+ {"method": "leworldmodel", "step": 12400, "loss": 0.012932437472045422}
63
+ {"method": "leworldmodel", "step": 12600, "loss": 0.012863457202911377}
64
+ {"method": "leworldmodel", "step": 12800, "loss": 0.012907395139336586}
65
+ {"method": "leworldmodel", "step": 13000, "loss": 0.013107913546264172}
66
+ {"method": "leworldmodel", "step": 13200, "loss": 0.012407218106091022}
67
+ {"method": "leworldmodel", "step": 13400, "loss": 0.012583350762724876}
68
+ {"method": "leworldmodel", "step": 13600, "loss": 0.013376313261687756}
69
+ {"method": "leworldmodel", "step": 13800, "loss": 0.012498993426561356}
70
+ {"method": "leworldmodel", "step": 14000, "loss": 0.012320655398070812}
71
+ {"method": "leworldmodel", "step": 14200, "loss": 0.011742516420781612}
72
+ {"method": "leworldmodel", "step": 14400, "loss": 0.011880998499691486}
73
+ {"method": "leworldmodel", "step": 14600, "loss": 0.013969209045171738}
74
+ {"method": "leworldmodel", "step": 14800, "loss": 0.01202570553869009}
75
+ {"method": "leworldmodel", "step": 15000, "loss": 0.011475014500319958}
76
+ {"method": "leworldmodel", "step": 15200, "loss": 0.011551539413630962}
77
+ {"method": "leworldmodel", "step": 15400, "loss": 0.0120136933401227}
78
+ {"method": "leworldmodel", "step": 15600, "loss": 0.011068976484239101}
79
+ {"method": "leworldmodel", "step": 15800, "loss": 0.011243877932429314}
80
+ {"method": "leworldmodel", "step": 16000, "loss": 0.011036578565835953}
81
+ {"method": "leworldmodel", "step": 16200, "loss": 0.010840185917913914}
82
+ {"method": "leworldmodel", "step": 16400, "loss": 0.010748428292572498}
83
+ {"method": "leworldmodel", "step": 16600, "loss": 0.011091048829257488}
84
+ {"method": "leworldmodel", "step": 16800, "loss": 0.010863492265343666}
85
+ {"method": "leworldmodel", "step": 17000, "loss": 0.010376963764429092}
86
+ {"method": "leworldmodel", "step": 17200, "loss": 0.010241455398499966}
87
+ {"method": "leworldmodel", "step": 17400, "loss": 0.01020446140319109}
88
+ {"method": "leworldmodel", "step": 17600, "loss": 0.010238328948616982}
89
+ {"method": "leworldmodel", "step": 17800, "loss": 0.011849394999444485}
90
+ {"method": "leworldmodel", "step": 18000, "loss": 0.010143092833459377}
91
+ {"method": "leworldmodel", "step": 18200, "loss": 0.010145328007638454}
92
+ {"method": "leworldmodel", "step": 18400, "loss": 0.00964964646846056}
93
+ {"method": "leworldmodel", "step": 18600, "loss": 0.009553018026053905}
94
+ {"method": "leworldmodel", "step": 18800, "loss": 0.008979679085314274}
95
+ {"method": "leworldmodel", "step": 19000, "loss": 0.009366254322230816}
96
+ {"method": "leworldmodel", "step": 19200, "loss": 0.00921623595058918}
97
+ {"method": "leworldmodel", "step": 19400, "loss": 0.009519802406430244}
98
+ {"method": "leworldmodel", "step": 19600, "loss": 0.009120199829339981}
99
+ {"method": "leworldmodel", "step": 19800, "loss": 0.02061399444937706}
100
+ {"method": "leworldmodel", "step": 20000, "loss": 0.009550545364618301}
experiments/leworldmodel/result/parameter_count.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "encoder": 471584,
3
+ "to_z": 43328,
4
+ "transition": 87104,
5
+ "decoder": 62596,
6
+ "total": 664612
7
+ }