Hugging Face's logo

AugustRushG123
/
TOTNet

Model card Files
xet
 Community
AugustRushG123 commited on
Commit
cf90c40
ยท
verified ยท
1 Parent(s): 9e1ad3b

Upload 6 files

Browse files
Files changed (6) hide show
  1. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32_eval.txt +0 -0
  2. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32_train.txt +1734 -0
  3. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_best.pth +3 -0
  4. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_latest.pth +3 -0
  5. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_params.json +9 -0
  6. TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/training_args.json +46 -0
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32_eval.txt ADDED
The diff for this file is too large to render. See raw diff
 
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32_train.txt ADDED
@@ -0,0 +1,1734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Log file created at Tue Mar 31 09:11:51 2026
2
+ Logs and model checkpoints will be saved to: ../logs/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32
3
+ Running on 1 GPU(s)
4
+ Seed: 2024
5
+ CPUs available for DataLoader workers: 10
6
+ num workers for DataLoader: 8
7
+ Total samples: 10
8
+ Training samples: 8
9
+ Validation samples: 2
10
+ Image size: (512, 512)
11
+ Building model: TOTNet
12
+ Training arguments saved to: ../logs/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/training_args.json
13
+ Model parameters saved to: ../logs/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_params.json
14
+ Val Epoch 0 | Batch 0/210 | RMSE: 193.9077 | F1: 0.0000
15
+ Val Epoch 0 | Batch 10/210 | RMSE: 94.4009 | F1: 0.0000
16
+ Val Epoch 0 | Batch 20/210 | RMSE: 89.2247 | F1: 0.4000
17
+ Val Epoch 0 | Batch 30/210 | RMSE: 121.6323 | F1: 0.4000
18
+ Val Epoch 0 | Batch 40/210 | RMSE: 96.8995 | F1: 0.0000
19
+ Val Epoch 0 | Batch 50/210 | RMSE: 77.7449 | F1: 0.0000
20
+ Val Epoch 0 | Batch 60/210 | RMSE: 151.9101 | F1: 0.0000
21
+ Val Epoch 0 | Batch 70/210 | RMSE: 134.0302 | F1: 0.0000
22
+ Val Epoch 0 | Batch 80/210 | RMSE: 1.1453 | F1: 1.0000
23
+ Val Epoch 0 | Batch 90/210 | RMSE: 0.7488 | F1: 1.0000
24
+ Val Epoch 0 | Batch 100/210 | RMSE: 34.6533 | F1: 0.8571
25
+ Val Epoch 0 | Batch 110/210 | RMSE: 85.1940 | F1: 0.0000
26
+ Val Epoch 0 | Batch 120/210 | RMSE: 58.9341 | F1: 0.4000
27
+ Val Epoch 0 | Batch 130/210 | RMSE: 1.6327 | F1: 0.8571
28
+ Val Epoch 0 | Batch 140/210 | RMSE: 0.7071 | F1: 1.0000
29
+ Val Epoch 0 | Batch 150/210 | RMSE: 76.3931 | F1: 0.0000
30
+ Val Epoch 0 | Batch 160/210 | RMSE: 38.6500 | F1: 0.4000
31
+ Val Epoch 0 | Batch 170/210 | RMSE: 9.1175 | F1: 0.0000
32
+ Val Epoch 0 | Batch 180/210 | RMSE: 1.1453 | F1: 1.0000
33
+ Val Epoch 0 | Batch 190/210 | RMSE: 5.4653 | F1: 0.4000
34
+ Val Epoch 0 | Batch 200/210 | RMSE: 0.5000 | F1: 1.0000
35
+
36
+ Val Epoch 0 Results:
37
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
38
+ โ”‚ Metric โ”‚ Value โ”‚
39
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
40
+ โ”‚ Loss โ”‚ 15.9999 โ”‚
41
+ โ”‚ RMSE โ”‚ 54.5788 โ”‚
42
+ โ”‚ Precision โ”‚ 0.4 โ”‚
43
+ โ”‚ Recall โ”‚ 0.6762 โ”‚
44
+ โ”‚ F1 โ”‚ 0.4737 โ”‚
45
+ โ”‚ Accuracy โ”‚ 0.4 โ”‚
46
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
47
+ Epoch 0 | Train Loss: 5.0375 | F1: 0.4737 | RMSE: 54.5788 | LR: 0.001000
48
+ New best checkpoint saved โ€” F1: 0.4737 at epoch 0
49
+ Val Epoch 1 | Batch 0/210 | RMSE: 173.7897 | F1: 0.0000
50
+ Val Epoch 1 | Batch 10/210 | RMSE: 91.1199 | F1: 0.0000
51
+ Val Epoch 1 | Batch 20/210 | RMSE: 172.9638 | F1: 0.0000
52
+ Val Epoch 1 | Batch 30/210 | RMSE: 95.0565 | F1: 0.0000
53
+ Val Epoch 1 | Batch 40/210 | RMSE: 151.1152 | F1: 0.0000
54
+ Val Epoch 1 | Batch 50/210 | RMSE: 37.1653 | F1: 0.6667
55
+ Val Epoch 1 | Batch 60/210 | RMSE: 98.2757 | F1: 0.6667
56
+ Val Epoch 1 | Batch 70/210 | RMSE: 140.9175 | F1: 0.0000
57
+ Val Epoch 1 | Batch 80/210 | RMSE: 1.4543 | F1: 0.8571
58
+ Val Epoch 1 | Batch 90/210 | RMSE: 1.4126 | F1: 0.8571
59
+ Val Epoch 1 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
60
+ Val Epoch 1 | Batch 110/210 | RMSE: 94.2057 | F1: 0.0000
61
+ Val Epoch 1 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
62
+ Val Epoch 1 | Batch 130/210 | RMSE: 2.7622 | F1: 0.6667
63
+ Val Epoch 1 | Batch 140/210 | RMSE: 1.0406 | F1: 1.0000
64
+ Val Epoch 1 | Batch 150/210 | RMSE: 81.3632 | F1: 0.0000
65
+ Val Epoch 1 | Batch 160/210 | RMSE: 2.6913 | F1: 0.6667
66
+ Val Epoch 1 | Batch 170/210 | RMSE: 145.0546 | F1: 0.0000
67
+ Val Epoch 1 | Batch 180/210 | RMSE: 0.9126 | F1: 0.8571
68
+ Val Epoch 1 | Batch 190/210 | RMSE: 4.1546 | F1: 0.6667
69
+ Val Epoch 1 | Batch 200/210 | RMSE: 1.1036 | F1: 1.0000
70
+
71
+ Val Epoch 1 Results:
72
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
73
+ โ”‚ Metric โ”‚ Value โ”‚
74
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
75
+ โ”‚ Loss โ”‚ 16.0645 โ”‚
76
+ โ”‚ RMSE โ”‚ 51.8085 โ”‚
77
+ โ”‚ Precision โ”‚ 0.4405 โ”‚
78
+ โ”‚ Recall โ”‚ 0.7143 โ”‚
79
+ โ”‚ F1 โ”‚ 0.5195 โ”‚
80
+ โ”‚ Accuracy โ”‚ 0.4405 โ”‚
81
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
82
+ Epoch 1 | Train Loss: 4.2050 | F1: 0.5195 | RMSE: 51.8085 | LR: 0.000999
83
+ New best checkpoint saved โ€” F1: 0.5195 at epoch 1
84
+ Val Epoch 2 | Batch 0/210 | RMSE: 185.1575 | F1: 0.0000
85
+ Val Epoch 2 | Batch 10/210 | RMSE: 100.6010 | F1: 0.0000
86
+ Val Epoch 2 | Batch 20/210 | RMSE: 144.0426 | F1: 0.4000
87
+ Val Epoch 2 | Batch 30/210 | RMSE: 75.4591 | F1: 0.4000
88
+ Val Epoch 2 | Batch 40/210 | RMSE: 109.6650 | F1: 0.0000
89
+ Val Epoch 2 | Batch 50/210 | RMSE: 2.0306 | F1: 0.4000
90
+ Val Epoch 2 | Batch 60/210 | RMSE: 31.8764 | F1: 0.6667
91
+ Val Epoch 2 | Batch 70/210 | RMSE: 140.5264 | F1: 0.0000
92
+ Val Epoch 2 | Batch 80/210 | RMSE: 0.7803 | F1: 1.0000
93
+ Val Epoch 2 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
94
+ Val Epoch 2 | Batch 100/210 | RMSE: 1.2071 | F1: 1.0000
95
+ Val Epoch 2 | Batch 110/210 | RMSE: 85.3570 | F1: 0.0000
96
+ Val Epoch 2 | Batch 120/210 | RMSE: 24.9229 | F1: 0.6667
97
+ Val Epoch 2 | Batch 130/210 | RMSE: 23.9923 | F1: 0.6667
98
+ Val Epoch 2 | Batch 140/210 | RMSE: 0.8536 | F1: 1.0000
99
+ Val Epoch 2 | Batch 150/210 | RMSE: 76.0743 | F1: 0.0000
100
+ Val Epoch 2 | Batch 160/210 | RMSE: 2.4268 | F1: 0.6667
101
+ Val Epoch 2 | Batch 170/210 | RMSE: 145.1915 | F1: 0.0000
102
+ Val Epoch 2 | Batch 180/210 | RMSE: 0.6453 | F1: 1.0000
103
+ Val Epoch 2 | Batch 190/210 | RMSE: 5.3346 | F1: 0.4000
104
+ Val Epoch 2 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
105
+
106
+ Val Epoch 2 Results:
107
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
108
+ โ”‚ Metric โ”‚ Value โ”‚
109
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
110
+ โ”‚ Loss โ”‚ 14.2178 โ”‚
111
+ โ”‚ RMSE โ”‚ 50.7938 โ”‚
112
+ โ”‚ Precision โ”‚ 0.4798 โ”‚
113
+ โ”‚ Recall โ”‚ 0.8 โ”‚
114
+ โ”‚ F1 โ”‚ 0.5671 โ”‚
115
+ โ”‚ Accuracy โ”‚ 0.4798 โ”‚
116
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
117
+ Epoch 2 | Train Loss: 4.0438 | F1: 0.5671 | RMSE: 50.7938 | LR: 0.000996
118
+ New best checkpoint saved โ€” F1: 0.5671 at epoch 2
119
+ Val Epoch 3 | Batch 0/210 | RMSE: 107.6111 | F1: 0.4000
120
+ Val Epoch 3 | Batch 10/210 | RMSE: 87.1618 | F1: 0.4000
121
+ Val Epoch 3 | Batch 20/210 | RMSE: 1.6545 | F1: 0.8571
122
+ Val Epoch 3 | Batch 30/210 | RMSE: 1.8536 | F1: 0.8571
123
+ Val Epoch 3 | Batch 40/210 | RMSE: 6.8157 | F1: 0.0000
124
+ Val Epoch 3 | Batch 50/210 | RMSE: 2.0150 | F1: 0.6667
125
+ Val Epoch 3 | Batch 60/210 | RMSE: 56.3151 | F1: 0.4000
126
+ Val Epoch 3 | Batch 70/210 | RMSE: 64.0104 | F1: 0.6667
127
+ Val Epoch 3 | Batch 80/210 | RMSE: 0.9988 | F1: 1.0000
128
+ Val Epoch 3 | Batch 90/210 | RMSE: 1.0721 | F1: 1.0000
129
+ Val Epoch 3 | Batch 100/210 | RMSE: 1.2488 | F1: 1.0000
130
+ Val Epoch 3 | Batch 110/210 | RMSE: 43.4887 | F1: 0.0000
131
+ Val Epoch 3 | Batch 120/210 | RMSE: 1.1024 | F1: 1.0000
132
+ Val Epoch 3 | Batch 130/210 | RMSE: 2.5678 | F1: 0.6667
133
+ Val Epoch 3 | Batch 140/210 | RMSE: 0.9988 | F1: 1.0000
134
+ Val Epoch 3 | Batch 150/210 | RMSE: 76.4804 | F1: 0.0000
135
+ Val Epoch 3 | Batch 160/210 | RMSE: 3.0595 | F1: 0.6667
136
+ Val Epoch 3 | Batch 170/210 | RMSE: 82.2621 | F1: 0.4000
137
+ Val Epoch 3 | Batch 180/210 | RMSE: 1.0303 | F1: 1.0000
138
+ Val Epoch 3 | Batch 190/210 | RMSE: 4.0607 | F1: 0.4000
139
+ Val Epoch 3 | Batch 200/210 | RMSE: 0.6768 | F1: 1.0000
140
+
141
+ Val Epoch 3 Results:
142
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
143
+ โ”‚ Metric โ”‚ Value โ”‚
144
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
145
+ โ”‚ Loss โ”‚ 12.8925 โ”‚
146
+ โ”‚ RMSE โ”‚ 28.504 โ”‚
147
+ โ”‚ Precision โ”‚ 0.5702 โ”‚
148
+ โ”‚ Recall โ”‚ 0.8952 โ”‚
149
+ โ”‚ F1 โ”‚ 0.6656 โ”‚
150
+ โ”‚ Accuracy โ”‚ 0.5702 โ”‚
151
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
152
+ Epoch 3 | Train Loss: 3.9029 | F1: 0.6656 | RMSE: 28.5040 | LR: 0.000992
153
+ New best checkpoint saved โ€” F1: 0.6656 at epoch 3
154
+ Val Epoch 4 | Batch 0/210 | RMSE: 2.7555 | F1: 0.6667
155
+ Val Epoch 4 | Batch 10/210 | RMSE: 104.7981 | F1: 0.4000
156
+ Val Epoch 4 | Batch 20/210 | RMSE: 55.7637 | F1: 0.6667
157
+ Val Epoch 4 | Batch 30/210 | RMSE: 2.5303 | F1: 0.8571
158
+ Val Epoch 4 | Batch 40/210 | RMSE: 6.9312 | F1: 0.0000
159
+ Val Epoch 4 | Batch 50/210 | RMSE: 2.1431 | F1: 0.8571
160
+ Val Epoch 4 | Batch 60/210 | RMSE: 3.0957 | F1: 0.4000
161
+ Val Epoch 4 | Batch 70/210 | RMSE: 2.2381 | F1: 0.8571
162
+ Val Epoch 4 | Batch 80/210 | RMSE: 1.0721 | F1: 1.0000
163
+ Val Epoch 4 | Batch 90/210 | RMSE: 0.4268 | F1: 1.0000
164
+ Val Epoch 4 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
165
+ Val Epoch 4 | Batch 110/210 | RMSE: 24.5255 | F1: 0.6667
166
+ Val Epoch 4 | Batch 120/210 | RMSE: 0.8839 | F1: 1.0000
167
+ Val Epoch 4 | Batch 130/210 | RMSE: 1.7713 | F1: 0.6667
168
+ Val Epoch 4 | Batch 140/210 | RMSE: 0.6036 | F1: 1.0000
169
+ Val Epoch 4 | Batch 150/210 | RMSE: 58.5122 | F1: 0.0000
170
+ Val Epoch 4 | Batch 160/210 | RMSE: 2.9559 | F1: 0.6667
171
+ Val Epoch 4 | Batch 170/210 | RMSE: 81.5200 | F1: 0.6667
172
+ Val Epoch 4 | Batch 180/210 | RMSE: 0.7906 | F1: 1.0000
173
+ Val Epoch 4 | Batch 190/210 | RMSE: 4.0376 | F1: 0.6667
174
+ Val Epoch 4 | Batch 200/210 | RMSE: 0.6768 | F1: 1.0000
175
+
176
+ Val Epoch 4 Results:
177
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
178
+ โ”‚ Metric โ”‚ Value โ”‚
179
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
180
+ โ”‚ Loss โ”‚ 12.5134 โ”‚
181
+ โ”‚ RMSE โ”‚ 26.4969 โ”‚
182
+ โ”‚ Precision โ”‚ 0.6 โ”‚
183
+ โ”‚ Recall โ”‚ 0.9048 โ”‚
184
+ โ”‚ F1 โ”‚ 0.6931 โ”‚
185
+ โ”‚ Accuracy โ”‚ 0.6 โ”‚
186
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
187
+ Epoch 4 | Train Loss: 3.8701 | F1: 0.6931 | RMSE: 26.4969 | LR: 0.000986
188
+ New best checkpoint saved โ€” F1: 0.6931 at epoch 4
189
+ Val Epoch 5 | Batch 0/210 | RMSE: 194.8885 | F1: 0.0000
190
+ Val Epoch 5 | Batch 10/210 | RMSE: 102.6006 | F1: 0.4000
191
+ Val Epoch 5 | Batch 20/210 | RMSE: 63.7408 | F1: 0.6667
192
+ Val Epoch 5 | Batch 30/210 | RMSE: 40.9322 | F1: 0.8571
193
+ Val Epoch 5 | Batch 40/210 | RMSE: 37.0739 | F1: 0.0000
194
+ Val Epoch 5 | Batch 50/210 | RMSE: 2.4924 | F1: 0.6667
195
+ Val Epoch 5 | Batch 60/210 | RMSE: 3.3725 | F1: 0.4000
196
+ Val Epoch 5 | Batch 70/210 | RMSE: 135.7661 | F1: 0.0000
197
+ Val Epoch 5 | Batch 80/210 | RMSE: 1.0721 | F1: 1.0000
198
+ Val Epoch 5 | Batch 90/210 | RMSE: 0.8953 | F1: 1.0000
199
+ Val Epoch 5 | Batch 100/210 | RMSE: 0.8536 | F1: 1.0000
200
+ Val Epoch 5 | Batch 110/210 | RMSE: 3.6681 | F1: 0.4000
201
+ Val Epoch 5 | Batch 120/210 | RMSE: 0.8839 | F1: 1.0000
202
+ Val Epoch 5 | Batch 130/210 | RMSE: 2.0949 | F1: 0.6667
203
+ Val Epoch 5 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
204
+ Val Epoch 5 | Batch 150/210 | RMSE: 75.9369 | F1: 0.0000
205
+ Val Epoch 5 | Batch 160/210 | RMSE: 2.5587 | F1: 0.6667
206
+ Val Epoch 5 | Batch 170/210 | RMSE: 81.6534 | F1: 0.6667
207
+ Val Epoch 5 | Batch 180/210 | RMSE: 0.8090 | F1: 0.8571
208
+ Val Epoch 5 | Batch 190/210 | RMSE: 2.6940 | F1: 0.6667
209
+ Val Epoch 5 | Batch 200/210 | RMSE: 0.7803 | F1: 1.0000
210
+
211
+ Val Epoch 5 Results:
212
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
213
+ โ”‚ Metric โ”‚ Value โ”‚
214
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
215
+ โ”‚ Loss โ”‚ 13.2502 โ”‚
216
+ โ”‚ RMSE โ”‚ 34.6333 โ”‚
217
+ โ”‚ Precision โ”‚ 0.5536 โ”‚
218
+ โ”‚ Recall โ”‚ 0.8619 โ”‚
219
+ โ”‚ F1 โ”‚ 0.6417 โ”‚
220
+ โ”‚ Accuracy โ”‚ 0.5536 โ”‚
221
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
222
+ Epoch 5 | Train Loss: 3.7506 | F1: 0.6417 | RMSE: 34.6333 | LR: 0.000978
223
+ Val Epoch 6 | Batch 0/210 | RMSE: 182.6042 | F1: 0.0000
224
+ Val Epoch 6 | Batch 10/210 | RMSE: 91.4276 | F1: 0.4000
225
+ Val Epoch 6 | Batch 20/210 | RMSE: 52.7222 | F1: 0.6667
226
+ Val Epoch 6 | Batch 30/210 | RMSE: 21.9110 | F1: 0.6667
227
+ Val Epoch 6 | Batch 40/210 | RMSE: 118.9882 | F1: 0.0000
228
+ Val Epoch 6 | Batch 50/210 | RMSE: 1.9663 | F1: 0.6667
229
+ Val Epoch 6 | Batch 60/210 | RMSE: 43.4965 | F1: 0.4000
230
+ Val Epoch 6 | Batch 70/210 | RMSE: 123.5578 | F1: 0.0000
231
+ Val Epoch 6 | Batch 80/210 | RMSE: 1.2173 | F1: 1.0000
232
+ Val Epoch 6 | Batch 90/210 | RMSE: 0.7803 | F1: 1.0000
233
+ Val Epoch 6 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
234
+ Val Epoch 6 | Batch 110/210 | RMSE: 2.7361 | F1: 0.6667
235
+ Val Epoch 6 | Batch 120/210 | RMSE: 1.0607 | F1: 1.0000
236
+ Val Epoch 6 | Batch 130/210 | RMSE: 1.7827 | F1: 0.8571
237
+ Val Epoch 6 | Batch 140/210 | RMSE: 1.0406 | F1: 1.0000
238
+ Val Epoch 6 | Batch 150/210 | RMSE: 62.0326 | F1: 0.0000
239
+ Val Epoch 6 | Batch 160/210 | RMSE: 2.5146 | F1: 0.6667
240
+ Val Epoch 6 | Batch 170/210 | RMSE: 54.1850 | F1: 0.8571
241
+ Val Epoch 6 | Batch 180/210 | RMSE: 0.5721 | F1: 1.0000
242
+ Val Epoch 6 | Batch 190/210 | RMSE: 1.1339 | F1: 0.8571
243
+ Val Epoch 6 | Batch 200/210 | RMSE: 0.8953 | F1: 1.0000
244
+
245
+ Val Epoch 6 Results:
246
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
247
+ โ”‚ Metric โ”‚ Value โ”‚
248
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
249
+ โ”‚ Loss โ”‚ 13.5951 โ”‚
250
+ โ”‚ RMSE โ”‚ 34.9201 โ”‚
251
+ โ”‚ Precision โ”‚ 0.55 โ”‚
252
+ โ”‚ Recall โ”‚ 0.8381 โ”‚
253
+ โ”‚ F1 โ”‚ 0.6322 โ”‚
254
+ โ”‚ Accuracy โ”‚ 0.55 โ”‚
255
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
256
+ Epoch 6 | Train Loss: 3.7536 | F1: 0.6322 | RMSE: 34.9201 | LR: 0.000968
257
+ Val Epoch 7 | Batch 0/210 | RMSE: 92.2271 | F1: 0.4000
258
+ Val Epoch 7 | Batch 10/210 | RMSE: 103.8224 | F1: 0.4000
259
+ Val Epoch 7 | Batch 20/210 | RMSE: 8.5352 | F1: 0.8571
260
+ Val Epoch 7 | Batch 30/210 | RMSE: 2.4571 | F1: 0.6667
261
+ Val Epoch 7 | Batch 40/210 | RMSE: 74.5550 | F1: 0.6667
262
+ Val Epoch 7 | Batch 50/210 | RMSE: 2.4496 | F1: 0.6667
263
+ Val Epoch 7 | Batch 60/210 | RMSE: 56.5956 | F1: 0.4000
264
+ Val Epoch 7 | Batch 70/210 | RMSE: 64.0295 | F1: 0.6667
265
+ Val Epoch 7 | Batch 80/210 | RMSE: 1.1024 | F1: 1.0000
266
+ Val Epoch 7 | Batch 90/210 | RMSE: 0.8221 | F1: 1.0000
267
+ Val Epoch 7 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
268
+ Val Epoch 7 | Batch 110/210 | RMSE: 5.1140 | F1: 0.4000
269
+ Val Epoch 7 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
270
+ Val Epoch 7 | Batch 130/210 | RMSE: 2.6712 | F1: 0.6667
271
+ Val Epoch 7 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
272
+ Val Epoch 7 | Batch 150/210 | RMSE: 75.9320 | F1: 0.0000
273
+ Val Epoch 7 | Batch 160/210 | RMSE: 3.0272 | F1: 0.6667
274
+ Val Epoch 7 | Batch 170/210 | RMSE: 2.6119 | F1: 0.6667
275
+ Val Epoch 7 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
276
+ Val Epoch 7 | Batch 190/210 | RMSE: 2.3221 | F1: 0.8571
277
+ Val Epoch 7 | Batch 200/210 | RMSE: 0.6036 | F1: 1.0000
278
+
279
+ Val Epoch 7 Results:
280
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
281
+ โ”‚ Metric โ”‚ Value โ”‚
282
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
283
+ โ”‚ Loss โ”‚ 12.6436 โ”‚
284
+ โ”‚ RMSE โ”‚ 25.3946 โ”‚
285
+ โ”‚ Precision โ”‚ 0.5929 โ”‚
286
+ โ”‚ Recall โ”‚ 0.8905 โ”‚
287
+ โ”‚ F1 โ”‚ 0.682 โ”‚
288
+ โ”‚ Accuracy โ”‚ 0.5929 โ”‚
289
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
290
+ Epoch 7 | Train Loss: 3.7115 | F1: 0.6820 | RMSE: 25.3946 | LR: 0.000957
291
+ Val Epoch 8 | Batch 0/210 | RMSE: 80.0079 | F1: 0.4000
292
+ Val Epoch 8 | Batch 10/210 | RMSE: 73.2660 | F1: 0.0000
293
+ Val Epoch 8 | Batch 20/210 | RMSE: 13.7330 | F1: 0.8571
294
+ Val Epoch 8 | Batch 30/210 | RMSE: 40.6991 | F1: 0.0000
295
+ Val Epoch 8 | Batch 40/210 | RMSE: 69.7284 | F1: 0.6667
296
+ Val Epoch 8 | Batch 50/210 | RMSE: 2.5430 | F1: 0.6667
297
+ Val Epoch 8 | Batch 60/210 | RMSE: 25.0118 | F1: 0.4000
298
+ Val Epoch 8 | Batch 70/210 | RMSE: 158.2393 | F1: 0.0000
299
+ Val Epoch 8 | Batch 80/210 | RMSE: 1.2374 | F1: 1.0000
300
+ Val Epoch 8 | Batch 90/210 | RMSE: 1.1036 | F1: 1.0000
301
+ Val Epoch 8 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
302
+ Val Epoch 8 | Batch 110/210 | RMSE: 3.4515 | F1: 0.4000
303
+ Val Epoch 8 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
304
+ Val Epoch 8 | Batch 130/210 | RMSE: 3.3003 | F1: 0.6667
305
+ Val Epoch 8 | Batch 140/210 | RMSE: 1.0406 | F1: 1.0000
306
+ Val Epoch 8 | Batch 150/210 | RMSE: 51.8429 | F1: 0.0000
307
+ Val Epoch 8 | Batch 160/210 | RMSE: 3.1570 | F1: 0.6667
308
+ Val Epoch 8 | Batch 170/210 | RMSE: 82.5876 | F1: 0.0000
309
+ Val Epoch 8 | Batch 180/210 | RMSE: 0.7358 | F1: 0.8571
310
+ Val Epoch 8 | Batch 190/210 | RMSE: 2.0566 | F1: 0.8571
311
+ Val Epoch 8 | Batch 200/210 | RMSE: 1.0303 | F1: 1.0000
312
+
313
+ Val Epoch 8 Results:
314
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
315
+ โ”‚ Metric โ”‚ Value โ”‚
316
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
317
+ โ”‚ Loss โ”‚ 13.5427 โ”‚
318
+ โ”‚ RMSE โ”‚ 30.053 โ”‚
319
+ โ”‚ Precision โ”‚ 0.556 โ”‚
320
+ โ”‚ Recall โ”‚ 0.8571 โ”‚
321
+ โ”‚ F1 โ”‚ 0.6429 โ”‚
322
+ โ”‚ Accuracy โ”‚ 0.556 โ”‚
323
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
324
+ Epoch 8 | Train Loss: 3.6870 | F1: 0.6429 | RMSE: 30.0530 | LR: 0.000944
325
+ Val Epoch 9 | Batch 0/210 | RMSE: 29.7349 | F1: 0.4000
326
+ Val Epoch 9 | Batch 10/210 | RMSE: 57.1407 | F1: 0.0000
327
+ Val Epoch 9 | Batch 20/210 | RMSE: 4.2498 | F1: 0.8571
328
+ Val Epoch 9 | Batch 30/210 | RMSE: 2.3362 | F1: 0.6667
329
+ Val Epoch 9 | Batch 40/210 | RMSE: 4.9614 | F1: 0.6667
330
+ Val Epoch 9 | Batch 50/210 | RMSE: 1.9863 | F1: 0.8571
331
+ Val Epoch 9 | Batch 60/210 | RMSE: 5.2573 | F1: 0.4000
332
+ Val Epoch 9 | Batch 70/210 | RMSE: 40.2793 | F1: 0.6667
333
+ Val Epoch 9 | Batch 80/210 | RMSE: 1.2488 | F1: 1.0000
334
+ Val Epoch 9 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
335
+ Val Epoch 9 | Batch 100/210 | RMSE: 1.3839 | F1: 1.0000
336
+ Val Epoch 9 | Batch 110/210 | RMSE: 5.3847 | F1: 0.4000
337
+ Val Epoch 9 | Batch 120/210 | RMSE: 0.8839 | F1: 1.0000
338
+ Val Epoch 9 | Batch 130/210 | RMSE: 2.2748 | F1: 0.8571
339
+ Val Epoch 9 | Batch 140/210 | RMSE: 0.9571 | F1: 1.0000
340
+ Val Epoch 9 | Batch 150/210 | RMSE: 76.2555 | F1: 0.0000
341
+ Val Epoch 9 | Batch 160/210 | RMSE: 2.6598 | F1: 0.6667
342
+ Val Epoch 9 | Batch 170/210 | RMSE: 26.0742 | F1: 0.6667
343
+ Val Epoch 9 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
344
+ Val Epoch 9 | Batch 190/210 | RMSE: 2.2334 | F1: 0.8571
345
+ Val Epoch 9 | Batch 200/210 | RMSE: 0.8536 | F1: 1.0000
346
+
347
+ Val Epoch 9 Results:
348
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
349
+ โ”‚ Metric โ”‚ Value โ”‚
350
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
351
+ โ”‚ Loss โ”‚ 12.1993 โ”‚
352
+ โ”‚ RMSE โ”‚ 20.0678 โ”‚
353
+ โ”‚ Precision โ”‚ 0.6131 โ”‚
354
+ โ”‚ Recall โ”‚ 0.9048 โ”‚
355
+ โ”‚ F1 โ”‚ 0.6988 โ”‚
356
+ โ”‚ Accuracy โ”‚ 0.6131 โ”‚
357
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
358
+ Epoch 9 | Train Loss: 3.6825 | F1: 0.6988 | RMSE: 20.0678 | LR: 0.000930
359
+ New best checkpoint saved โ€” F1: 0.6988 at epoch 9
360
+ Val Epoch 10 | Batch 0/210 | RMSE: 91.6944 | F1: 0.4000
361
+ Val Epoch 10 | Batch 10/210 | RMSE: 104.7651 | F1: 0.4000
362
+ Val Epoch 10 | Batch 20/210 | RMSE: 55.7030 | F1: 0.8571
363
+ Val Epoch 10 | Batch 30/210 | RMSE: 2.2071 | F1: 0.8571
364
+ Val Epoch 10 | Batch 40/210 | RMSE: 5.3724 | F1: 0.4000
365
+ Val Epoch 10 | Batch 50/210 | RMSE: 1.6745 | F1: 1.0000
366
+ Val Epoch 10 | Batch 60/210 | RMSE: 44.8915 | F1: 0.4000
367
+ Val Epoch 10 | Batch 70/210 | RMSE: 45.1040 | F1: 0.6667
368
+ Val Epoch 10 | Batch 80/210 | RMSE: 1.1453 | F1: 1.0000
369
+ Val Epoch 10 | Batch 90/210 | RMSE: 0.6768 | F1: 1.0000
370
+ Val Epoch 10 | Batch 100/210 | RMSE: 0.9673 | F1: 1.0000
371
+ Val Epoch 10 | Batch 110/210 | RMSE: 2.7268 | F1: 0.6667
372
+ Val Epoch 10 | Batch 120/210 | RMSE: 1.3107 | F1: 1.0000
373
+ Val Epoch 10 | Batch 130/210 | RMSE: 1.8808 | F1: 0.8571
374
+ Val Epoch 10 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
375
+ Val Epoch 10 | Batch 150/210 | RMSE: 75.9203 | F1: 0.0000
376
+ Val Epoch 10 | Batch 160/210 | RMSE: 2.5587 | F1: 0.6667
377
+ Val Epoch 10 | Batch 170/210 | RMSE: 1.0721 | F1: 1.0000
378
+ Val Epoch 10 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
379
+ Val Epoch 10 | Batch 190/210 | RMSE: 3.3066 | F1: 0.6667
380
+ Val Epoch 10 | Batch 200/210 | RMSE: 0.6036 | F1: 1.0000
381
+
382
+ Val Epoch 10 Results:
383
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
384
+ โ”‚ Metric โ”‚ Value โ”‚
385
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
386
+ โ”‚ Loss โ”‚ 12.1817 โ”‚
387
+ โ”‚ RMSE โ”‚ 28.996 โ”‚
388
+ โ”‚ Precision โ”‚ 0.625 โ”‚
389
+ โ”‚ Recall โ”‚ 0.9238 โ”‚
390
+ โ”‚ F1 โ”‚ 0.714 โ”‚
391
+ โ”‚ Accuracy โ”‚ 0.625 โ”‚
392
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
393
+ Epoch 10 | Train Loss: 3.6670 | F1: 0.7140 | RMSE: 28.9960 | LR: 0.000914
394
+ New best checkpoint saved โ€” F1: 0.7140 at epoch 10
395
+ Val Epoch 11 | Batch 0/210 | RMSE: 1.9988 | F1: 0.8571
396
+ Val Epoch 11 | Batch 10/210 | RMSE: 65.9938 | F1: 0.4000
397
+ Val Epoch 11 | Batch 20/210 | RMSE: 1.4846 | F1: 0.8571
398
+ Val Epoch 11 | Batch 30/210 | RMSE: 1.8536 | F1: 0.8571
399
+ Val Epoch 11 | Batch 40/210 | RMSE: 4.5532 | F1: 0.4000
400
+ Val Epoch 11 | Batch 50/210 | RMSE: 2.1431 | F1: 0.6667
401
+ Val Epoch 11 | Batch 60/210 | RMSE: 4.5463 | F1: 0.4000
402
+ Val Epoch 11 | Batch 70/210 | RMSE: 33.0270 | F1: 0.8571
403
+ Val Epoch 11 | Batch 80/210 | RMSE: 1.2071 | F1: 1.0000
404
+ Val Epoch 11 | Batch 90/210 | RMSE: 0.8953 | F1: 1.0000
405
+ Val Epoch 11 | Batch 100/210 | RMSE: 0.9256 | F1: 1.0000
406
+ Val Epoch 11 | Batch 110/210 | RMSE: 2.8001 | F1: 0.6667
407
+ Val Epoch 11 | Batch 120/210 | RMSE: 1.2374 | F1: 1.0000
408
+ Val Epoch 11 | Batch 130/210 | RMSE: 24.2661 | F1: 0.6667
409
+ Val Epoch 11 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
410
+ Val Epoch 11 | Batch 150/210 | RMSE: 77.1105 | F1: 0.0000
411
+ Val Epoch 11 | Batch 160/210 | RMSE: 2.5292 | F1: 0.6667
412
+ Val Epoch 11 | Batch 170/210 | RMSE: 26.2510 | F1: 0.6667
413
+ Val Epoch 11 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
414
+ Val Epoch 11 | Batch 190/210 | RMSE: 1.9855 | F1: 0.8571
415
+ Val Epoch 11 | Batch 200/210 | RMSE: 0.7803 | F1: 1.0000
416
+
417
+ Val Epoch 11 Results:
418
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
419
+ โ”‚ Metric โ”‚ Value โ”‚
420
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
421
+ โ”‚ Loss โ”‚ 11.7892 โ”‚
422
+ โ”‚ RMSE โ”‚ 16.6694 โ”‚
423
+ โ”‚ Precision โ”‚ 0.6679 โ”‚
424
+ โ”‚ Recall โ”‚ 0.9667 โ”‚
425
+ โ”‚ F1 โ”‚ 0.7604 โ”‚
426
+ โ”‚ Accuracy โ”‚ 0.6679 โ”‚
427
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
428
+ Epoch 11 | Train Loss: 3.6147 | F1: 0.7604 | RMSE: 16.6694 | LR: 0.000897
429
+ New best checkpoint saved โ€” F1: 0.7604 at epoch 11
430
+ Val Epoch 12 | Batch 0/210 | RMSE: 44.8807 | F1: 0.4000
431
+ Val Epoch 12 | Batch 10/210 | RMSE: 40.6425 | F1: 0.4000
432
+ Val Epoch 12 | Batch 20/210 | RMSE: 4.1766 | F1: 0.6667
433
+ Val Epoch 12 | Batch 30/210 | RMSE: 1.9716 | F1: 0.6667
434
+ Val Epoch 12 | Batch 40/210 | RMSE: 5.4134 | F1: 0.4000
435
+ Val Epoch 12 | Batch 50/210 | RMSE: 1.9445 | F1: 0.8571
436
+ Val Epoch 12 | Batch 60/210 | RMSE: 4.0653 | F1: 0.6667
437
+ Val Epoch 12 | Batch 70/210 | RMSE: 70.7054 | F1: 0.6667
438
+ Val Epoch 12 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
439
+ Val Epoch 12 | Batch 90/210 | RMSE: 0.9988 | F1: 1.0000
440
+ Val Epoch 12 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
441
+ Val Epoch 12 | Batch 110/210 | RMSE: 2.8001 | F1: 0.6667
442
+ Val Epoch 12 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
443
+ Val Epoch 12 | Batch 130/210 | RMSE: 24.1847 | F1: 0.8571
444
+ Val Epoch 12 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
445
+ Val Epoch 12 | Batch 150/210 | RMSE: 76.1109 | F1: 0.0000
446
+ Val Epoch 12 | Batch 160/210 | RMSE: 2.5146 | F1: 0.6667
447
+ Val Epoch 12 | Batch 170/210 | RMSE: 27.1305 | F1: 0.4000
448
+ Val Epoch 12 | Batch 180/210 | RMSE: 0.8090 | F1: 0.8571
449
+ Val Epoch 12 | Batch 190/210 | RMSE: 2.0587 | F1: 0.8571
450
+ Val Epoch 12 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
451
+
452
+ Val Epoch 12 Results:
453
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
454
+ โ”‚ Metric โ”‚ Value โ”‚
455
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
456
+ โ”‚ Loss โ”‚ 12.2655 โ”‚
457
+ โ”‚ RMSE โ”‚ 18.3338 โ”‚
458
+ โ”‚ Precision โ”‚ 0.656 โ”‚
459
+ โ”‚ Recall โ”‚ 0.9524 โ”‚
460
+ โ”‚ F1 โ”‚ 0.746 โ”‚
461
+ โ”‚ Accuracy โ”‚ 0.656 โ”‚
462
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
463
+ Epoch 12 | Train Loss: 3.6252 | F1: 0.7460 | RMSE: 18.3338 | LR: 0.000878
464
+ Val Epoch 13 | Batch 0/210 | RMSE: 1.8241 | F1: 0.8571
465
+ Val Epoch 13 | Batch 10/210 | RMSE: 7.3831 | F1: 0.4000
466
+ Val Epoch 13 | Batch 20/210 | RMSE: 3.6419 | F1: 0.8571
467
+ Val Epoch 13 | Batch 30/210 | RMSE: 1.7803 | F1: 0.8571
468
+ Val Epoch 13 | Batch 40/210 | RMSE: 5.2026 | F1: 0.4000
469
+ Val Epoch 13 | Batch 50/210 | RMSE: 2.3616 | F1: 0.6667
470
+ Val Epoch 13 | Batch 60/210 | RMSE: 4.4877 | F1: 0.4000
471
+ Val Epoch 13 | Batch 70/210 | RMSE: 1.5021 | F1: 0.8571
472
+ Val Epoch 13 | Batch 80/210 | RMSE: 1.3524 | F1: 1.0000
473
+ Val Epoch 13 | Batch 90/210 | RMSE: 0.9988 | F1: 1.0000
474
+ Val Epoch 13 | Batch 100/210 | RMSE: 0.9256 | F1: 1.0000
475
+ Val Epoch 13 | Batch 110/210 | RMSE: 1.1626 | F1: 0.8571
476
+ Val Epoch 13 | Batch 120/210 | RMSE: 1.0607 | F1: 1.0000
477
+ Val Epoch 13 | Batch 130/210 | RMSE: 24.1704 | F1: 0.8571
478
+ Val Epoch 13 | Batch 140/210 | RMSE: 0.9571 | F1: 1.0000
479
+ Val Epoch 13 | Batch 150/210 | RMSE: 63.7248 | F1: 0.0000
480
+ Val Epoch 13 | Batch 160/210 | RMSE: 2.8382 | F1: 0.6667
481
+ Val Epoch 13 | Batch 170/210 | RMSE: 26.2510 | F1: 0.6667
482
+ Val Epoch 13 | Batch 180/210 | RMSE: 0.5721 | F1: 1.0000
483
+ Val Epoch 13 | Batch 190/210 | RMSE: 2.8352 | F1: 0.8571
484
+ Val Epoch 13 | Batch 200/210 | RMSE: 0.6036 | F1: 1.0000
485
+
486
+ Val Epoch 13 Results:
487
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
488
+ โ”‚ Metric โ”‚ Value โ”‚
489
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
490
+ โ”‚ Loss โ”‚ 11.2038 โ”‚
491
+ โ”‚ RMSE โ”‚ 14.3957 โ”‚
492
+ โ”‚ Precision โ”‚ 0.6917 โ”‚
493
+ โ”‚ Recall โ”‚ 0.9714 โ”‚
494
+ โ”‚ F1 โ”‚ 0.7788 โ”‚
495
+ โ”‚ Accuracy โ”‚ 0.6917 โ”‚
496
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
497
+ Epoch 13 | Train Loss: 3.5958 | F1: 0.7788 | RMSE: 14.3957 | LR: 0.000858
498
+ New best checkpoint saved โ€” F1: 0.7788 at epoch 13
499
+ Val Epoch 14 | Batch 0/210 | RMSE: 2.1741 | F1: 0.8571
500
+ Val Epoch 14 | Batch 10/210 | RMSE: 7.1562 | F1: 0.4000
501
+ Val Epoch 14 | Batch 20/210 | RMSE: 3.5229 | F1: 0.8571
502
+ Val Epoch 14 | Batch 30/210 | RMSE: 1.8410 | F1: 0.8571
503
+ Val Epoch 14 | Batch 40/210 | RMSE: 5.2398 | F1: 0.4000
504
+ Val Epoch 14 | Batch 50/210 | RMSE: 2.1848 | F1: 0.8571
505
+ Val Epoch 14 | Batch 60/210 | RMSE: 3.4385 | F1: 0.4000
506
+ Val Epoch 14 | Batch 70/210 | RMSE: 38.3823 | F1: 0.8571
507
+ Val Epoch 14 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
508
+ Val Epoch 14 | Batch 90/210 | RMSE: 1.0721 | F1: 1.0000
509
+ Val Epoch 14 | Batch 100/210 | RMSE: 1.0303 | F1: 1.0000
510
+ Val Epoch 14 | Batch 110/210 | RMSE: 1.2358 | F1: 0.8571
511
+ Val Epoch 14 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
512
+ Val Epoch 14 | Batch 130/210 | RMSE: 24.5986 | F1: 0.6667
513
+ Val Epoch 14 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
514
+ Val Epoch 14 | Batch 150/210 | RMSE: 64.5951 | F1: 0.0000
515
+ Val Epoch 14 | Batch 160/210 | RMSE: 2.3839 | F1: 0.6667
516
+ Val Epoch 14 | Batch 170/210 | RMSE: 26.3242 | F1: 0.6667
517
+ Val Epoch 14 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
518
+ Val Epoch 14 | Batch 190/210 | RMSE: 0.6036 | F1: 1.0000
519
+ Val Epoch 14 | Batch 200/210 | RMSE: 0.7803 | F1: 1.0000
520
+
521
+ Val Epoch 14 Results:
522
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
523
+ โ”‚ Metric โ”‚ Value โ”‚
524
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
525
+ โ”‚ Loss โ”‚ 11.6739 โ”‚
526
+ โ”‚ RMSE โ”‚ 14.1653 โ”‚
527
+ โ”‚ Precision โ”‚ 0.6738 โ”‚
528
+ โ”‚ Recall โ”‚ 0.9571 โ”‚
529
+ โ”‚ F1 โ”‚ 0.7616 โ”‚
530
+ โ”‚ Accuracy โ”‚ 0.6738 โ”‚
531
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
532
+ Epoch 14 | Train Loss: 3.5796 | F1: 0.7616 | RMSE: 14.1653 | LR: 0.000837
533
+ Val Epoch 15 | Batch 0/210 | RMSE: 2.2066 | F1: 0.8571
534
+ Val Epoch 15 | Batch 10/210 | RMSE: 6.5142 | F1: 0.4000
535
+ Val Epoch 15 | Batch 20/210 | RMSE: 4.5217 | F1: 0.6667
536
+ Val Epoch 15 | Batch 30/210 | RMSE: 2.3221 | F1: 0.8571
537
+ Val Epoch 15 | Batch 40/210 | RMSE: 5.3115 | F1: 0.6667
538
+ Val Epoch 15 | Batch 50/210 | RMSE: 2.0280 | F1: 0.8571
539
+ Val Epoch 15 | Batch 60/210 | RMSE: 3.3585 | F1: 0.4000
540
+ Val Epoch 15 | Batch 70/210 | RMSE: 71.8364 | F1: 0.6667
541
+ Val Epoch 15 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
542
+ Val Epoch 15 | Batch 90/210 | RMSE: 0.7803 | F1: 1.0000
543
+ Val Epoch 15 | Batch 100/210 | RMSE: 0.6768 | F1: 1.0000
544
+ Val Epoch 15 | Batch 110/210 | RMSE: 3.4515 | F1: 0.4000
545
+ Val Epoch 15 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
546
+ Val Epoch 15 | Batch 130/210 | RMSE: 24.0419 | F1: 0.8571
547
+ Val Epoch 15 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
548
+ Val Epoch 15 | Batch 150/210 | RMSE: 64.3442 | F1: 0.0000
549
+ Val Epoch 15 | Batch 160/210 | RMSE: 2.5895 | F1: 0.6667
550
+ Val Epoch 15 | Batch 170/210 | RMSE: 1.8645 | F1: 0.6667
551
+ Val Epoch 15 | Batch 180/210 | RMSE: 0.9858 | F1: 0.8571
552
+ Val Epoch 15 | Batch 190/210 | RMSE: 0.4268 | F1: 1.0000
553
+ Val Epoch 15 | Batch 200/210 | RMSE: 0.8221 | F1: 1.0000
554
+
555
+ Val Epoch 15 Results:
556
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
557
+ โ”‚ Metric โ”‚ Value โ”‚
558
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
559
+ โ”‚ Loss โ”‚ 11.5875 โ”‚
560
+ โ”‚ RMSE โ”‚ 13.2342 โ”‚
561
+ โ”‚ Precision โ”‚ 0.7083 โ”‚
562
+ โ”‚ Recall โ”‚ 0.9667 โ”‚
563
+ โ”‚ F1 โ”‚ 0.789 โ”‚
564
+ โ”‚ Accuracy โ”‚ 0.7083 โ”‚
565
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
566
+ Epoch 15 | Train Loss: 3.5637 | F1: 0.7890 | RMSE: 13.2342 | LR: 0.000815
567
+ New best checkpoint saved โ€” F1: 0.7890 at epoch 15
568
+ Val Epoch 16 | Batch 0/210 | RMSE: 2.0705 | F1: 0.8571
569
+ Val Epoch 16 | Batch 10/210 | RMSE: 6.0381 | F1: 0.4000
570
+ Val Epoch 16 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
571
+ Val Epoch 16 | Batch 30/210 | RMSE: 2.5890 | F1: 0.6667
572
+ Val Epoch 16 | Batch 40/210 | RMSE: 4.9233 | F1: 0.6667
573
+ Val Epoch 16 | Batch 50/210 | RMSE: 2.3685 | F1: 0.4000
574
+ Val Epoch 16 | Batch 60/210 | RMSE: 4.5412 | F1: 0.4000
575
+ Val Epoch 16 | Batch 70/210 | RMSE: 35.5153 | F1: 0.6667
576
+ Val Epoch 16 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
577
+ Val Epoch 16 | Batch 90/210 | RMSE: 0.9571 | F1: 1.0000
578
+ Val Epoch 16 | Batch 100/210 | RMSE: 0.8221 | F1: 1.0000
579
+ Val Epoch 16 | Batch 110/210 | RMSE: 3.6254 | F1: 0.4000
580
+ Val Epoch 16 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
581
+ Val Epoch 16 | Batch 130/210 | RMSE: 23.7322 | F1: 0.8571
582
+ Val Epoch 16 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
583
+ Val Epoch 16 | Batch 150/210 | RMSE: 59.5718 | F1: 0.0000
584
+ Val Epoch 16 | Batch 160/210 | RMSE: 2.5308 | F1: 0.6667
585
+ Val Epoch 16 | Batch 170/210 | RMSE: 25.5738 | F1: 0.8571
586
+ Val Epoch 16 | Batch 180/210 | RMSE: 1.0303 | F1: 1.0000
587
+ Val Epoch 16 | Batch 190/210 | RMSE: 0.5303 | F1: 1.0000
588
+ Val Epoch 16 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
589
+
590
+ Val Epoch 16 Results:
591
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
592
+ โ”‚ Metric โ”‚ Value โ”‚
593
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
594
+ โ”‚ Loss โ”‚ 11.4496 โ”‚
595
+ โ”‚ RMSE โ”‚ 10.9122 โ”‚
596
+ โ”‚ Precision โ”‚ 0.7095 โ”‚
597
+ โ”‚ Recall โ”‚ 0.9762 โ”‚
598
+ โ”‚ F1 โ”‚ 0.7936 โ”‚
599
+ โ”‚ Accuracy โ”‚ 0.7095 โ”‚
600
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
601
+ Epoch 16 | Train Loss: 3.5608 | F1: 0.7936 | RMSE: 10.9122 | LR: 0.000791
602
+ New best checkpoint saved โ€” F1: 0.7936 at epoch 16
603
+ Val Epoch 17 | Batch 0/210 | RMSE: 1.9973 | F1: 0.8571
604
+ Val Epoch 17 | Batch 10/210 | RMSE: 22.6536 | F1: 0.4000
605
+ Val Epoch 17 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
606
+ Val Epoch 17 | Batch 30/210 | RMSE: 49.0863 | F1: 0.6667
607
+ Val Epoch 17 | Batch 40/210 | RMSE: 38.9974 | F1: 0.4000
608
+ Val Epoch 17 | Batch 50/210 | RMSE: 42.6681 | F1: 0.6667
609
+ Val Epoch 17 | Batch 60/210 | RMSE: 4.6589 | F1: 0.4000
610
+ Val Epoch 17 | Batch 70/210 | RMSE: 34.9855 | F1: 0.6667
611
+ Val Epoch 17 | Batch 80/210 | RMSE: 1.2488 | F1: 1.0000
612
+ Val Epoch 17 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
613
+ Val Epoch 17 | Batch 100/210 | RMSE: 0.6768 | F1: 1.0000
614
+ Val Epoch 17 | Batch 110/210 | RMSE: 3.6254 | F1: 0.4000
615
+ Val Epoch 17 | Batch 120/210 | RMSE: 1.2071 | F1: 1.0000
616
+ Val Epoch 17 | Batch 130/210 | RMSE: 24.1337 | F1: 0.8571
617
+ Val Epoch 17 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
618
+ Val Epoch 17 | Batch 150/210 | RMSE: 63.4144 | F1: 0.0000
619
+ Val Epoch 17 | Batch 160/210 | RMSE: 1.7355 | F1: 0.8571
620
+ Val Epoch 17 | Batch 170/210 | RMSE: 26.0213 | F1: 0.4000
621
+ Val Epoch 17 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
622
+ Val Epoch 17 | Batch 190/210 | RMSE: 0.5303 | F1: 1.0000
623
+ Val Epoch 17 | Batch 200/210 | RMSE: 0.8536 | F1: 1.0000
624
+
625
+ Val Epoch 17 Results:
626
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
627
+ โ”‚ Metric โ”‚ Value โ”‚
628
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
629
+ โ”‚ Loss โ”‚ 11.7289 โ”‚
630
+ โ”‚ RMSE โ”‚ 16.8124 โ”‚
631
+ โ”‚ Precision โ”‚ 0.6726 โ”‚
632
+ โ”‚ Recall โ”‚ 0.9619 โ”‚
633
+ โ”‚ F1 โ”‚ 0.7599 โ”‚
634
+ โ”‚ Accuracy โ”‚ 0.6726 โ”‚
635
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
636
+ Epoch 17 | Train Loss: 3.5304 | F1: 0.7599 | RMSE: 16.8124 | LR: 0.000767
637
+ Val Epoch 18 | Batch 0/210 | RMSE: 1.9988 | F1: 0.8571
638
+ Val Epoch 18 | Batch 10/210 | RMSE: 7.5745 | F1: 0.4000
639
+ Val Epoch 18 | Batch 20/210 | RMSE: 41.4816 | F1: 0.8571
640
+ Val Epoch 18 | Batch 30/210 | RMSE: 48.8450 | F1: 0.6667
641
+ Val Epoch 18 | Batch 40/210 | RMSE: 2.5814 | F1: 0.6667
642
+ Val Epoch 18 | Batch 50/210 | RMSE: 2.1787 | F1: 0.6667
643
+ Val Epoch 18 | Batch 60/210 | RMSE: 4.2969 | F1: 0.4000
644
+ Val Epoch 18 | Batch 70/210 | RMSE: 2.0303 | F1: 0.8571
645
+ Val Epoch 18 | Batch 80/210 | RMSE: 1.2906 | F1: 1.0000
646
+ Val Epoch 18 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
647
+ Val Epoch 18 | Batch 100/210 | RMSE: 1.3626 | F1: 1.0000
648
+ Val Epoch 18 | Batch 110/210 | RMSE: 3.3947 | F1: 0.4000
649
+ Val Epoch 18 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
650
+ Val Epoch 18 | Batch 130/210 | RMSE: 24.1847 | F1: 0.8571
651
+ Val Epoch 18 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
652
+ Val Epoch 18 | Batch 150/210 | RMSE: 59.0365 | F1: 0.0000
653
+ Val Epoch 18 | Batch 160/210 | RMSE: 2.4874 | F1: 0.6667
654
+ Val Epoch 18 | Batch 170/210 | RMSE: 54.9924 | F1: 0.4000
655
+ Val Epoch 18 | Batch 180/210 | RMSE: 1.0303 | F1: 1.0000
656
+ Val Epoch 18 | Batch 190/210 | RMSE: 3.5423 | F1: 0.6667
657
+ Val Epoch 18 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
658
+
659
+ Val Epoch 18 Results:
660
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
661
+ โ”‚ Metric โ”‚ Value โ”‚
662
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
663
+ โ”‚ Loss โ”‚ 11.1761 โ”‚
664
+ โ”‚ RMSE โ”‚ 8.9068 โ”‚
665
+ โ”‚ Precision โ”‚ 0.7083 โ”‚
666
+ โ”‚ Recall โ”‚ 0.9714 โ”‚
667
+ โ”‚ F1 โ”‚ 0.79 โ”‚
668
+ โ”‚ Accuracy โ”‚ 0.7083 โ”‚
669
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
670
+ Epoch 18 | Train Loss: 3.5320 | F1: 0.7900 | RMSE: 8.9068 | LR: 0.000742
671
+ Val Epoch 19 | Batch 0/210 | RMSE: 1.8221 | F1: 0.8571
672
+ Val Epoch 19 | Batch 10/210 | RMSE: 23.2601 | F1: 0.4000
673
+ Val Epoch 19 | Batch 20/210 | RMSE: 1.4559 | F1: 1.0000
674
+ Val Epoch 19 | Batch 30/210 | RMSE: 2.2071 | F1: 0.8571
675
+ Val Epoch 19 | Batch 40/210 | RMSE: 5.2026 | F1: 0.4000
676
+ Val Epoch 19 | Batch 50/210 | RMSE: 2.0150 | F1: 0.6667
677
+ Val Epoch 19 | Batch 60/210 | RMSE: 3.3585 | F1: 0.4000
678
+ Val Epoch 19 | Batch 70/210 | RMSE: 6.1084 | F1: 0.8571
679
+ Val Epoch 19 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
680
+ Val Epoch 19 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
681
+ Val Epoch 19 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
682
+ Val Epoch 19 | Batch 110/210 | RMSE: 3.3875 | F1: 0.4000
683
+ Val Epoch 19 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
684
+ Val Epoch 19 | Batch 130/210 | RMSE: 24.2579 | F1: 0.8571
685
+ Val Epoch 19 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
686
+ Val Epoch 19 | Batch 150/210 | RMSE: 63.2694 | F1: 0.0000
687
+ Val Epoch 19 | Batch 160/210 | RMSE: 2.5607 | F1: 0.6667
688
+ Val Epoch 19 | Batch 170/210 | RMSE: 1.7666 | F1: 0.6667
689
+ Val Epoch 19 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
690
+ Val Epoch 19 | Batch 190/210 | RMSE: 3.4388 | F1: 0.6667
691
+ Val Epoch 19 | Batch 200/210 | RMSE: 1.1756 | F1: 1.0000
692
+
693
+ Val Epoch 19 Results:
694
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
695
+ โ”‚ Metric โ”‚ Value โ”‚
696
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
697
+ โ”‚ Loss โ”‚ 11.0672 โ”‚
698
+ โ”‚ RMSE โ”‚ 10.5703 โ”‚
699
+ โ”‚ Precision โ”‚ 0.719 โ”‚
700
+ โ”‚ Recall โ”‚ 0.981 โ”‚
701
+ โ”‚ F1 โ”‚ 0.8015 โ”‚
702
+ โ”‚ Accuracy โ”‚ 0.719 โ”‚
703
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
704
+ Epoch 19 | Train Loss: 3.5430 | F1: 0.8015 | RMSE: 10.5703 | LR: 0.000716
705
+ New best checkpoint saved โ€” F1: 0.8015 at epoch 19
706
+ Val Epoch 20 | Batch 0/210 | RMSE: 1.5021 | F1: 0.8571
707
+ Val Epoch 20 | Batch 10/210 | RMSE: 2.1220 | F1: 0.6667
708
+ Val Epoch 20 | Batch 20/210 | RMSE: 3.4651 | F1: 0.8571
709
+ Val Epoch 20 | Batch 30/210 | RMSE: 1.6642 | F1: 0.8571
710
+ Val Epoch 20 | Batch 40/210 | RMSE: 2.4177 | F1: 0.8571
711
+ Val Epoch 20 | Batch 50/210 | RMSE: 1.9863 | F1: 0.8571
712
+ Val Epoch 20 | Batch 60/210 | RMSE: 2.6665 | F1: 0.8571
713
+ Val Epoch 20 | Batch 70/210 | RMSE: 1.9268 | F1: 0.8571
714
+ Val Epoch 20 | Batch 80/210 | RMSE: 1.2488 | F1: 1.0000
715
+ Val Epoch 20 | Batch 90/210 | RMSE: 1.0721 | F1: 1.0000
716
+ Val Epoch 20 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
717
+ Val Epoch 20 | Batch 110/210 | RMSE: 1.2358 | F1: 0.8571
718
+ Val Epoch 20 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
719
+ Val Epoch 20 | Batch 130/210 | RMSE: 2.4425 | F1: 0.6667
720
+ Val Epoch 20 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
721
+ Val Epoch 20 | Batch 150/210 | RMSE: 63.7062 | F1: 0.0000
722
+ Val Epoch 20 | Batch 160/210 | RMSE: 2.3839 | F1: 0.6667
723
+ Val Epoch 20 | Batch 170/210 | RMSE: 1.7796 | F1: 0.8571
724
+ Val Epoch 20 | Batch 180/210 | RMSE: 0.5303 | F1: 1.0000
725
+ Val Epoch 20 | Batch 190/210 | RMSE: 0.4268 | F1: 1.0000
726
+ Val Epoch 20 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
727
+
728
+ Val Epoch 20 Results:
729
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
730
+ โ”‚ Metric โ”‚ Value โ”‚
731
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
732
+ โ”‚ Loss โ”‚ 10.98 โ”‚
733
+ โ”‚ RMSE โ”‚ 10.4091 โ”‚
734
+ โ”‚ Precision โ”‚ 0.7286 โ”‚
735
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
736
+ โ”‚ F1 โ”‚ 0.8133 โ”‚
737
+ โ”‚ Accuracy โ”‚ 0.7286 โ”‚
738
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
739
+ Epoch 20 | Train Loss: 3.5170 | F1: 0.8133 | RMSE: 10.4091 | LR: 0.000689
740
+ New best checkpoint saved โ€” F1: 0.8133 at epoch 20
741
+ Val Epoch 21 | Batch 0/210 | RMSE: 1.5021 | F1: 0.8571
742
+ Val Epoch 21 | Batch 10/210 | RMSE: 2.2291 | F1: 0.4000
743
+ Val Epoch 21 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
744
+ Val Epoch 21 | Batch 30/210 | RMSE: 2.2358 | F1: 0.6667
745
+ Val Epoch 21 | Batch 40/210 | RMSE: 2.3759 | F1: 0.8571
746
+ Val Epoch 21 | Batch 50/210 | RMSE: 2.1848 | F1: 0.6667
747
+ Val Epoch 21 | Batch 60/210 | RMSE: 4.2968 | F1: 0.4000
748
+ Val Epoch 21 | Batch 70/210 | RMSE: 1.8845 | F1: 0.8571
749
+ Val Epoch 21 | Batch 80/210 | RMSE: 1.3524 | F1: 1.0000
750
+ Val Epoch 21 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
751
+ Val Epoch 21 | Batch 100/210 | RMSE: 1.1024 | F1: 1.0000
752
+ Val Epoch 21 | Batch 110/210 | RMSE: 3.8844 | F1: 0.6667
753
+ Val Epoch 21 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
754
+ Val Epoch 21 | Batch 130/210 | RMSE: 24.1704 | F1: 0.8571
755
+ Val Epoch 21 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
756
+ Val Epoch 21 | Batch 150/210 | RMSE: 63.9991 | F1: 0.0000
757
+ Val Epoch 21 | Batch 160/210 | RMSE: 3.2040 | F1: 0.6667
758
+ Val Epoch 21 | Batch 170/210 | RMSE: 1.3524 | F1: 1.0000
759
+ Val Epoch 21 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
760
+ Val Epoch 21 | Batch 190/210 | RMSE: 3.4763 | F1: 0.8571
761
+ Val Epoch 21 | Batch 200/210 | RMSE: 1.2906 | F1: 1.0000
762
+
763
+ Val Epoch 21 Results:
764
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
765
+ โ”‚ Metric โ”‚ Value โ”‚
766
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
767
+ โ”‚ Loss โ”‚ 11.0379 โ”‚
768
+ โ”‚ RMSE โ”‚ 8.3933 โ”‚
769
+ โ”‚ Precision โ”‚ 0.7369 โ”‚
770
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
771
+ โ”‚ F1 โ”‚ 0.8176 โ”‚
772
+ โ”‚ Accuracy โ”‚ 0.7369 โ”‚
773
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
774
+ Epoch 21 | Train Loss: 3.4888 | F1: 0.8176 | RMSE: 8.3933 | LR: 0.000662
775
+ New best checkpoint saved โ€” F1: 0.8176 at epoch 21
776
+ Val Epoch 22 | Batch 0/210 | RMSE: 3.4048 | F1: 0.6667
777
+ Val Epoch 22 | Batch 10/210 | RMSE: 2.4398 | F1: 0.6667
778
+ Val Epoch 22 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
779
+ Val Epoch 22 | Batch 30/210 | RMSE: 48.8363 | F1: 0.4000
780
+ Val Epoch 22 | Batch 40/210 | RMSE: 2.6529 | F1: 0.6667
781
+ Val Epoch 22 | Batch 50/210 | RMSE: 2.0465 | F1: 0.6667
782
+ Val Epoch 22 | Batch 60/210 | RMSE: 3.2853 | F1: 0.4000
783
+ Val Epoch 22 | Batch 70/210 | RMSE: 1.7500 | F1: 0.8571
784
+ Val Epoch 22 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
785
+ Val Epoch 22 | Batch 90/210 | RMSE: 1.1626 | F1: 0.8571
786
+ Val Epoch 22 | Batch 100/210 | RMSE: 36.8101 | F1: 0.6667
787
+ Val Epoch 22 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
788
+ Val Epoch 22 | Batch 120/210 | RMSE: 1.1024 | F1: 1.0000
789
+ Val Epoch 22 | Batch 130/210 | RMSE: 23.9570 | F1: 0.8571
790
+ Val Epoch 22 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
791
+ Val Epoch 22 | Batch 150/210 | RMSE: 47.2936 | F1: 0.0000
792
+ Val Epoch 22 | Batch 160/210 | RMSE: 42.0705 | F1: 0.6667
793
+ Val Epoch 22 | Batch 170/210 | RMSE: 26.2347 | F1: 0.6667
794
+ Val Epoch 22 | Batch 180/210 | RMSE: 1.0893 | F1: 0.8571
795
+ Val Epoch 22 | Batch 190/210 | RMSE: 0.3536 | F1: 1.0000
796
+ Val Epoch 22 | Batch 200/210 | RMSE: 0.6036 | F1: 1.0000
797
+
798
+ Val Epoch 22 Results:
799
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
800
+ โ”‚ Metric โ”‚ Value โ”‚
801
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€๏ฟฝ๏ฟฝโ”€โ”€โ”€โ”ค
802
+ โ”‚ Loss โ”‚ 11.3621 โ”‚
803
+ โ”‚ RMSE โ”‚ 10.1739 โ”‚
804
+ โ”‚ Precision โ”‚ 0.7238 โ”‚
805
+ โ”‚ Recall โ”‚ 0.9762 โ”‚
806
+ โ”‚ F1 โ”‚ 0.807 โ”‚
807
+ โ”‚ Accuracy โ”‚ 0.7238 โ”‚
808
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
809
+ Epoch 22 | Train Loss: 3.4896 | F1: 0.8070 | RMSE: 10.1739 | LR: 0.000634
810
+ Val Epoch 23 | Batch 0/210 | RMSE: 3.9339 | F1: 0.6667
811
+ Val Epoch 23 | Batch 10/210 | RMSE: 103.3315 | F1: 0.4000
812
+ Val Epoch 23 | Batch 20/210 | RMSE: 41.9206 | F1: 0.8571
813
+ Val Epoch 23 | Batch 30/210 | RMSE: 1.9571 | F1: 0.8571
814
+ Val Epoch 23 | Batch 40/210 | RMSE: 2.5746 | F1: 0.6667
815
+ Val Epoch 23 | Batch 50/210 | RMSE: 2.0280 | F1: 0.8571
816
+ Val Epoch 23 | Batch 60/210 | RMSE: 3.1141 | F1: 0.4000
817
+ Val Epoch 23 | Batch 70/210 | RMSE: 32.6387 | F1: 0.8571
818
+ Val Epoch 23 | Batch 80/210 | RMSE: 1.2374 | F1: 1.0000
819
+ Val Epoch 23 | Batch 90/210 | RMSE: 1.0721 | F1: 1.0000
820
+ Val Epoch 23 | Batch 100/210 | RMSE: 0.9256 | F1: 1.0000
821
+ Val Epoch 23 | Batch 110/210 | RMSE: 2.1343 | F1: 0.6667
822
+ Val Epoch 23 | Batch 120/210 | RMSE: 1.0607 | F1: 1.0000
823
+ Val Epoch 23 | Batch 130/210 | RMSE: 24.1049 | F1: 0.8571
824
+ Val Epoch 23 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
825
+ Val Epoch 23 | Batch 150/210 | RMSE: 46.3542 | F1: 0.0000
826
+ Val Epoch 23 | Batch 160/210 | RMSE: 2.9079 | F1: 0.6667
827
+ Val Epoch 23 | Batch 170/210 | RMSE: 1.8528 | F1: 0.8571
828
+ Val Epoch 23 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
829
+ Val Epoch 23 | Batch 190/210 | RMSE: 2.6584 | F1: 0.8571
830
+ Val Epoch 23 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
831
+
832
+ Val Epoch 23 Results:
833
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
834
+ โ”‚ Metric โ”‚ Value โ”‚
835
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
836
+ โ”‚ Loss โ”‚ 11.3643 โ”‚
837
+ โ”‚ RMSE โ”‚ 14.167 โ”‚
838
+ โ”‚ Precision โ”‚ 0.7095 โ”‚
839
+ โ”‚ Recall โ”‚ 0.981 โ”‚
840
+ โ”‚ F1 โ”‚ 0.7939 โ”‚
841
+ โ”‚ Accuracy โ”‚ 0.7095 โ”‚
842
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
843
+ Epoch 23 | Train Loss: 3.5259 | F1: 0.7939 | RMSE: 14.1670 | LR: 0.000606
844
+ Val Epoch 24 | Batch 0/210 | RMSE: 1.6474 | F1: 0.8571
845
+ Val Epoch 24 | Batch 10/210 | RMSE: 6.8734 | F1: 0.0000
846
+ Val Epoch 24 | Batch 20/210 | RMSE: 1.5910 | F1: 1.0000
847
+ Val Epoch 24 | Batch 30/210 | RMSE: 46.8323 | F1: 0.6667
848
+ Val Epoch 24 | Batch 40/210 | RMSE: 2.2409 | F1: 0.8571
849
+ Val Epoch 24 | Batch 50/210 | RMSE: 1.8930 | F1: 0.8571
850
+ Val Epoch 24 | Batch 60/210 | RMSE: 4.4680 | F1: 0.4000
851
+ Val Epoch 24 | Batch 70/210 | RMSE: 1.6768 | F1: 0.8571
852
+ Val Epoch 24 | Batch 80/210 | RMSE: 1.4359 | F1: 1.0000
853
+ Val Epoch 24 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
854
+ Val Epoch 24 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
855
+ Val Epoch 24 | Batch 110/210 | RMSE: 2.8396 | F1: 0.6667
856
+ Val Epoch 24 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
857
+ Val Epoch 24 | Batch 130/210 | RMSE: 24.2802 | F1: 0.8571
858
+ Val Epoch 24 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
859
+ Val Epoch 24 | Batch 150/210 | RMSE: 61.9048 | F1: 0.4000
860
+ Val Epoch 24 | Batch 160/210 | RMSE: 1.4874 | F1: 0.8571
861
+ Val Epoch 24 | Batch 170/210 | RMSE: 26.2510 | F1: 0.6667
862
+ Val Epoch 24 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
863
+ Val Epoch 24 | Batch 190/210 | RMSE: 0.5303 | F1: 1.0000
864
+ Val Epoch 24 | Batch 200/210 | RMSE: 0.9571 | F1: 1.0000
865
+
866
+ Val Epoch 24 Results:
867
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
868
+ โ”‚ Metric โ”‚ Value โ”‚
869
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
870
+ โ”‚ Loss โ”‚ 10.9317 โ”‚
871
+ โ”‚ RMSE โ”‚ 8.6918 โ”‚
872
+ โ”‚ Precision โ”‚ 0.7643 โ”‚
873
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
874
+ โ”‚ F1 โ”‚ 0.8392 โ”‚
875
+ โ”‚ Accuracy โ”‚ 0.7643 โ”‚
876
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
877
+ Epoch 24 | Train Loss: 3.5105 | F1: 0.8392 | RMSE: 8.6918 | LR: 0.000578
878
+ New best checkpoint saved โ€” F1: 0.8392 at epoch 24
879
+ Val Epoch 25 | Batch 0/210 | RMSE: 1.6642 | F1: 0.8571
880
+ Val Epoch 25 | Batch 10/210 | RMSE: 4.1412 | F1: 0.4000
881
+ Val Epoch 25 | Batch 20/210 | RMSE: 1.4559 | F1: 1.0000
882
+ Val Epoch 25 | Batch 30/210 | RMSE: 1.4571 | F1: 0.8571
883
+ Val Epoch 25 | Batch 40/210 | RMSE: 2.7153 | F1: 0.6667
884
+ Val Epoch 25 | Batch 50/210 | RMSE: 2.1917 | F1: 0.6667
885
+ Val Epoch 25 | Batch 60/210 | RMSE: 3.3585 | F1: 0.4000
886
+ Val Epoch 25 | Batch 70/210 | RMSE: 1.7206 | F1: 0.8571
887
+ Val Epoch 25 | Batch 80/210 | RMSE: 1.2906 | F1: 1.0000
888
+ Val Epoch 25 | Batch 90/210 | RMSE: 0.9571 | F1: 1.0000
889
+ Val Epoch 25 | Batch 100/210 | RMSE: 0.4268 | F1: 1.0000
890
+ Val Epoch 25 | Batch 110/210 | RMSE: 2.6314 | F1: 0.6667
891
+ Val Epoch 25 | Batch 120/210 | RMSE: 1.1024 | F1: 1.0000
892
+ Val Epoch 25 | Batch 130/210 | RMSE: 24.0240 | F1: 0.8571
893
+ Val Epoch 25 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
894
+ Val Epoch 25 | Batch 150/210 | RMSE: 63.1618 | F1: 0.0000
895
+ Val Epoch 25 | Batch 160/210 | RMSE: 1.8111 | F1: 0.8571
896
+ Val Epoch 25 | Batch 170/210 | RMSE: 1.6591 | F1: 0.8571
897
+ Val Epoch 25 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
898
+ Val Epoch 25 | Batch 190/210 | RMSE: 3.1326 | F1: 0.8571
899
+ Val Epoch 25 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
900
+
901
+ Val Epoch 25 Results:
902
+ ๏ฟฝ๏ฟฝโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
903
+ โ”‚ Metric โ”‚ Value โ”‚
904
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
905
+ โ”‚ Loss โ”‚ 11.0707 โ”‚
906
+ โ”‚ RMSE โ”‚ 9.5269 โ”‚
907
+ โ”‚ Precision โ”‚ 0.7607 โ”‚
908
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
909
+ โ”‚ F1 โ”‚ 0.8391 โ”‚
910
+ โ”‚ Accuracy โ”‚ 0.7607 โ”‚
911
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
912
+ Epoch 25 | Train Loss: 3.4609 | F1: 0.8391 | RMSE: 9.5269 | LR: 0.000550
913
+ Val Epoch 26 | Batch 0/210 | RMSE: 1.9973 | F1: 0.8571
914
+ Val Epoch 26 | Batch 10/210 | RMSE: 4.0603 | F1: 0.0000
915
+ Val Epoch 26 | Batch 20/210 | RMSE: 3.5229 | F1: 0.8571
916
+ Val Epoch 26 | Batch 30/210 | RMSE: 2.3732 | F1: 0.4000
917
+ Val Epoch 26 | Batch 40/210 | RMSE: 2.0956 | F1: 0.8571
918
+ Val Epoch 26 | Batch 50/210 | RMSE: 2.0150 | F1: 0.6667
919
+ Val Epoch 26 | Batch 60/210 | RMSE: 3.2142 | F1: 0.4000
920
+ Val Epoch 26 | Batch 70/210 | RMSE: 35.2459 | F1: 0.6667
921
+ Val Epoch 26 | Batch 80/210 | RMSE: 1.5709 | F1: 1.0000
922
+ Val Epoch 26 | Batch 90/210 | RMSE: 0.9571 | F1: 1.0000
923
+ Val Epoch 26 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
924
+ Val Epoch 26 | Batch 110/210 | RMSE: 3.4881 | F1: 0.4000
925
+ Val Epoch 26 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
926
+ Val Epoch 26 | Batch 130/210 | RMSE: 24.1991 | F1: 0.8571
927
+ Val Epoch 26 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
928
+ Val Epoch 26 | Batch 150/210 | RMSE: 46.1578 | F1: 0.0000
929
+ Val Epoch 26 | Batch 160/210 | RMSE: 1.6343 | F1: 0.8571
930
+ Val Epoch 26 | Batch 170/210 | RMSE: 26.0678 | F1: 0.6667
931
+ Val Epoch 26 | Batch 180/210 | RMSE: 1.1311 | F1: 0.8571
932
+ Val Epoch 26 | Batch 190/210 | RMSE: 0.4268 | F1: 1.0000
933
+ Val Epoch 26 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
934
+
935
+ Val Epoch 26 Results:
936
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
937
+ โ”‚ Metric โ”‚ Value โ”‚
938
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
939
+ โ”‚ Loss โ”‚ 11.1617 โ”‚
940
+ โ”‚ RMSE โ”‚ 11.8618 โ”‚
941
+ โ”‚ Precision โ”‚ 0.7417 โ”‚
942
+ โ”‚ Recall โ”‚ 0.981 โ”‚
943
+ โ”‚ F1 โ”‚ 0.819 โ”‚
944
+ โ”‚ Accuracy โ”‚ 0.7417 โ”‚
945
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
946
+ Epoch 26 | Train Loss: 3.4739 | F1: 0.8190 | RMSE: 11.8618 | LR: 0.000522
947
+ Val Epoch 27 | Batch 0/210 | RMSE: 1.4874 | F1: 0.8571
948
+ Val Epoch 27 | Batch 10/210 | RMSE: 3.8966 | F1: 0.4000
949
+ Val Epoch 27 | Batch 20/210 | RMSE: 3.4192 | F1: 0.8571
950
+ Val Epoch 27 | Batch 30/210 | RMSE: 2.4858 | F1: 0.4000
951
+ Val Epoch 27 | Batch 40/210 | RMSE: 3.0065 | F1: 0.6667
952
+ Val Epoch 27 | Batch 50/210 | RMSE: 2.0567 | F1: 0.6667
953
+ Val Epoch 27 | Batch 60/210 | RMSE: 4.4680 | F1: 0.4000
954
+ Val Epoch 27 | Batch 70/210 | RMSE: 2.0595 | F1: 0.8571
955
+ Val Epoch 27 | Batch 80/210 | RMSE: 1.1024 | F1: 1.0000
956
+ Val Epoch 27 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
957
+ Val Epoch 27 | Batch 100/210 | RMSE: 0.5303 | F1: 1.0000
958
+ Val Epoch 27 | Batch 110/210 | RMSE: 3.4881 | F1: 0.4000
959
+ Val Epoch 27 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
960
+ Val Epoch 27 | Batch 130/210 | RMSE: 1.4988 | F1: 1.0000
961
+ Val Epoch 27 | Batch 140/210 | RMSE: 0.9571 | F1: 1.0000
962
+ Val Epoch 27 | Batch 150/210 | RMSE: 63.4144 | F1: 0.0000
963
+ Val Epoch 27 | Batch 160/210 | RMSE: 2.9394 | F1: 0.6667
964
+ Val Epoch 27 | Batch 170/210 | RMSE: 26.2769 | F1: 0.6667
965
+ Val Epoch 27 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
966
+ Val Epoch 27 | Batch 190/210 | RMSE: 3.1948 | F1: 0.8571
967
+ Val Epoch 27 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
968
+
969
+ Val Epoch 27 Results:
970
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
971
+ โ”‚ Metric โ”‚ Value โ”‚
972
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
973
+ โ”‚ Loss โ”‚ 10.8477 โ”‚
974
+ โ”‚ RMSE โ”‚ 10.2951 โ”‚
975
+ โ”‚ Precision โ”‚ 0.7655 โ”‚
976
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
977
+ โ”‚ F1 โ”‚ 0.837 โ”‚
978
+ โ”‚ Accuracy โ”‚ 0.7655 โ”‚
979
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
980
+ Epoch 27 | Train Loss: 3.4802 | F1: 0.8370 | RMSE: 10.2951 | LR: 0.000494
981
+ Val Epoch 28 | Batch 0/210 | RMSE: 2.0276 | F1: 0.8571
982
+ Val Epoch 28 | Batch 10/210 | RMSE: 6.2153 | F1: 0.4000
983
+ Val Epoch 28 | Batch 20/210 | RMSE: 3.1200 | F1: 0.8571
984
+ Val Epoch 28 | Batch 30/210 | RMSE: 20.3325 | F1: 0.6667
985
+ Val Epoch 28 | Batch 40/210 | RMSE: 2.5814 | F1: 0.6667
986
+ Val Epoch 28 | Batch 50/210 | RMSE: 1.6327 | F1: 1.0000
987
+ Val Epoch 28 | Batch 60/210 | RMSE: 3.2853 | F1: 0.4000
988
+ Val Epoch 28 | Batch 70/210 | RMSE: 2.0613 | F1: 0.8571
989
+ Val Epoch 28 | Batch 80/210 | RMSE: 1.1453 | F1: 1.0000
990
+ Val Epoch 28 | Batch 90/210 | RMSE: 1.0721 | F1: 1.0000
991
+ Val Epoch 28 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
992
+ Val Epoch 28 | Batch 110/210 | RMSE: 3.4881 | F1: 0.4000
993
+ Val Epoch 28 | Batch 120/210 | RMSE: 1.1024 | F1: 1.0000
994
+ Val Epoch 28 | Batch 130/210 | RMSE: 1.4988 | F1: 1.0000
995
+ Val Epoch 28 | Batch 140/210 | RMSE: 1.0607 | F1: 1.0000
996
+ Val Epoch 28 | Batch 150/210 | RMSE: 62.9133 | F1: 0.0000
997
+ Val Epoch 28 | Batch 160/210 | RMSE: 2.5146 | F1: 0.6667
998
+ Val Epoch 28 | Batch 170/210 | RMSE: 82.6374 | F1: 0.4000
999
+ Val Epoch 28 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
1000
+ Val Epoch 28 | Batch 190/210 | RMSE: 2.8352 | F1: 0.8571
1001
+ Val Epoch 28 | Batch 200/210 | RMSE: 0.8536 | F1: 1.0000
1002
+
1003
+ Val Epoch 28 Results:
1004
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1005
+ โ”‚ Metric โ”‚ Value โ”‚
1006
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1007
+ โ”‚ Loss โ”‚ 11.0101 โ”‚
1008
+ โ”‚ RMSE โ”‚ 7.915 โ”‚
1009
+ โ”‚ Precision โ”‚ 0.7714 โ”‚
1010
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
1011
+ โ”‚ F1 โ”‚ 0.8421 โ”‚
1012
+ โ”‚ Accuracy โ”‚ 0.7714 โ”‚
1013
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1014
+ Epoch 28 | Train Loss: 3.4303 | F1: 0.8421 | RMSE: 7.9150 | LR: 0.000466
1015
+ New best checkpoint saved โ€” F1: 0.8421 at epoch 28
1016
+ Val Epoch 29 | Batch 0/210 | RMSE: 1.5021 | F1: 0.8571
1017
+ Val Epoch 29 | Batch 10/210 | RMSE: 4.3709 | F1: 0.6667
1018
+ Val Epoch 29 | Batch 20/210 | RMSE: 1.5910 | F1: 1.0000
1019
+ Val Epoch 29 | Batch 30/210 | RMSE: 48.8649 | F1: 0.4000
1020
+ Val Epoch 29 | Batch 40/210 | RMSE: 2.2296 | F1: 0.8571
1021
+ Val Epoch 29 | Batch 50/210 | RMSE: 2.0150 | F1: 0.6667
1022
+ Val Epoch 29 | Batch 60/210 | RMSE: 4.4680 | F1: 0.4000
1023
+ Val Epoch 29 | Batch 70/210 | RMSE: 1.9577 | F1: 0.8571
1024
+ Val Epoch 29 | Batch 80/210 | RMSE: 1.5394 | F1: 1.0000
1025
+ Val Epoch 29 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1026
+ Val Epoch 29 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1027
+ Val Epoch 29 | Batch 110/210 | RMSE: 3.4339 | F1: 0.4000
1028
+ Val Epoch 29 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1029
+ Val Epoch 29 | Batch 130/210 | RMSE: 23.9570 | F1: 0.8571
1030
+ Val Epoch 29 | Batch 140/210 | RMSE: 0.9571 | F1: 1.0000
1031
+ Val Epoch 29 | Batch 150/210 | RMSE: 63.9319 | F1: 0.0000
1032
+ Val Epoch 29 | Batch 160/210 | RMSE: 2.9394 | F1: 0.6667
1033
+ Val Epoch 29 | Batch 170/210 | RMSE: 2.3780 | F1: 0.6667
1034
+ Val Epoch 29 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
1035
+ Val Epoch 29 | Batch 190/210 | RMSE: 0.7803 | F1: 1.0000
1036
+ Val Epoch 29 | Batch 200/210 | RMSE: 0.9988 | F1: 1.0000
1037
+
1038
+ Val Epoch 29 Results:
1039
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1040
+ โ”‚ Metric โ”‚ Value โ”‚
1041
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1042
+ โ”‚ Loss โ”‚ 10.9657 โ”‚
1043
+ โ”‚ RMSE โ”‚ 8.7878 โ”‚
1044
+ โ”‚ Precision โ”‚ 0.7821 โ”‚
1045
+ โ”‚ Recall โ”‚ 0.981 โ”‚
1046
+ โ”‚ F1 โ”‚ 0.8506 โ”‚
1047
+ โ”‚ Accuracy โ”‚ 0.7821 โ”‚
1048
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1049
+ Epoch 29 | Train Loss: 3.4773 | F1: 0.8506 | RMSE: 8.7878 | LR: 0.000438
1050
+ New best checkpoint saved โ€” F1: 0.8506 at epoch 29
1051
+ Val Epoch 30 | Batch 0/210 | RMSE: 1.8221 | F1: 0.8571
1052
+ Val Epoch 30 | Batch 10/210 | RMSE: 6.3815 | F1: 0.4000
1053
+ Val Epoch 30 | Batch 20/210 | RMSE: 3.4609 | F1: 0.8571
1054
+ Val Epoch 30 | Batch 30/210 | RMSE: 21.5190 | F1: 0.4000
1055
+ Val Epoch 30 | Batch 40/210 | RMSE: 5.1665 | F1: 0.4000
1056
+ Val Epoch 30 | Batch 50/210 | RMSE: 2.0150 | F1: 0.6667
1057
+ Val Epoch 30 | Batch 60/210 | RMSE: 4.4680 | F1: 0.4000
1058
+ Val Epoch 30 | Batch 70/210 | RMSE: 1.8520 | F1: 0.8571
1059
+ Val Epoch 30 | Batch 80/210 | RMSE: 1.7162 | F1: 1.0000
1060
+ Val Epoch 30 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1061
+ Val Epoch 30 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1062
+ Val Epoch 30 | Batch 110/210 | RMSE: 3.5614 | F1: 0.4000
1063
+ Val Epoch 30 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1064
+ Val Epoch 30 | Batch 130/210 | RMSE: 24.2802 | F1: 0.8571
1065
+ Val Epoch 30 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1066
+ Val Epoch 30 | Batch 150/210 | RMSE: 48.8964 | F1: 0.4000
1067
+ Val Epoch 30 | Batch 160/210 | RMSE: 2.9394 | F1: 0.6667
1068
+ Val Epoch 30 | Batch 170/210 | RMSE: 26.1722 | F1: 0.6667
1069
+ Val Epoch 30 | Batch 180/210 | RMSE: 0.9126 | F1: 0.8571
1070
+ Val Epoch 30 | Batch 190/210 | RMSE: 0.7071 | F1: 1.0000
1071
+ Val Epoch 30 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
1072
+
1073
+ Val Epoch 30 Results:
1074
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1075
+ โ”‚ Metric โ”‚ Value โ”‚
1076
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1077
+ โ”‚ Loss โ”‚ 11.1419 โ”‚
1078
+ โ”‚ RMSE โ”‚ 8.6951 โ”‚
1079
+ โ”‚ Precision โ”‚ 0.7464 โ”‚
1080
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1081
+ โ”‚ F1 โ”‚ 0.8252 โ”‚
1082
+ โ”‚ Accuracy โ”‚ 0.7464 โ”‚
1083
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1084
+ Epoch 30 | Train Loss: 3.4226 | F1: 0.8252 | RMSE: 8.6951 | LR: 0.000411
1085
+ Val Epoch 31 | Batch 0/210 | RMSE: 1.8221 | F1: 0.8571
1086
+ Val Epoch 31 | Batch 10/210 | RMSE: 2.0723 | F1: 0.4000
1087
+ Val Epoch 31 | Batch 20/210 | RMSE: 3.5646 | F1: 0.8571
1088
+ Val Epoch 31 | Batch 30/210 | RMSE: 2.3628 | F1: 0.4000
1089
+ Val Epoch 31 | Batch 40/210 | RMSE: 2.3748 | F1: 0.8571
1090
+ Val Epoch 31 | Batch 50/210 | RMSE: 1.8512 | F1: 0.8571
1091
+ Val Epoch 31 | Batch 60/210 | RMSE: 2.8771 | F1: 0.6667
1092
+ Val Epoch 31 | Batch 70/210 | RMSE: 2.1345 | F1: 0.8571
1093
+ Val Epoch 31 | Batch 80/210 | RMSE: 1.1024 | F1: 1.0000
1094
+ Val Epoch 31 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1095
+ Val Epoch 31 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1096
+ Val Epoch 31 | Batch 110/210 | RMSE: 2.3831 | F1: 0.6667
1097
+ Val Epoch 31 | Batch 120/210 | RMSE: 1.1024 | F1: 1.0000
1098
+ Val Epoch 31 | Batch 130/210 | RMSE: 24.1755 | F1: 0.8571
1099
+ Val Epoch 31 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1100
+ Val Epoch 31 | Batch 150/210 | RMSE: 60.3693 | F1: 0.0000
1101
+ Val Epoch 31 | Batch 160/210 | RMSE: 1.7772 | F1: 0.8571
1102
+ Val Epoch 31 | Batch 170/210 | RMSE: 1.9981 | F1: 0.8571
1103
+ Val Epoch 31 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1104
+ Val Epoch 31 | Batch 190/210 | RMSE: 2.9084 | F1: 0.8571
1105
+ Val Epoch 31 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
1106
+
1107
+ Val Epoch 31 Results:
1108
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1109
+ โ”‚ Metric โ”‚ Value โ”‚
1110
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1111
+ โ”‚ Loss โ”‚ 11.1638 โ”‚
1112
+ โ”‚ RMSE โ”‚ 13.1871 โ”‚
1113
+ โ”‚ Precision โ”‚ 0.725 โ”‚
1114
+ โ”‚ Recall โ”‚ 0.9762 โ”‚
1115
+ โ”‚ F1 โ”‚ 0.8065 โ”‚
1116
+ โ”‚ Accuracy โ”‚ 0.725 โ”‚
1117
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1118
+ Epoch 31 | Train Loss: 3.4370 | F1: 0.8065 | RMSE: 13.1871 | LR: 0.000384
1119
+ Val Epoch 32 | Batch 0/210 | RMSE: 2.3496 | F1: 0.8571
1120
+ Val Epoch 32 | Batch 10/210 | RMSE: 3.0233 | F1: 0.8571
1121
+ Val Epoch 32 | Batch 20/210 | RMSE: 3.2090 | F1: 0.8571
1122
+ Val Epoch 32 | Batch 30/210 | RMSE: 48.5863 | F1: 0.6667
1123
+ Val Epoch 32 | Batch 40/210 | RMSE: 2.2462 | F1: 0.6667
1124
+ Val Epoch 32 | Batch 50/210 | RMSE: 1.8697 | F1: 0.6667
1125
+ Val Epoch 32 | Batch 60/210 | RMSE: 3.0409 | F1: 0.4000
1126
+ Val Epoch 32 | Batch 70/210 | RMSE: 1.8536 | F1: 0.8571
1127
+ Val Epoch 32 | Batch 80/210 | RMSE: 1.2906 | F1: 1.0000
1128
+ Val Epoch 32 | Batch 90/210 | RMSE: 0.7803 | F1: 1.0000
1129
+ Val Epoch 32 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1130
+ Val Epoch 32 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1131
+ Val Epoch 32 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1132
+ Val Epoch 32 | Batch 130/210 | RMSE: 1.3941 | F1: 1.0000
1133
+ Val Epoch 32 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1134
+ Val Epoch 32 | Batch 150/210 | RMSE: 110.0108 | F1: 0.0000
1135
+ Val Epoch 32 | Batch 160/210 | RMSE: 0.6768 | F1: 1.0000
1136
+ Val Epoch 32 | Batch 170/210 | RMSE: 2.8080 | F1: 0.6667
1137
+ Val Epoch 32 | Batch 180/210 | RMSE: 0.9673 | F1: 1.0000
1138
+ Val Epoch 32 | Batch 190/210 | RMSE: 1.0000 | F1: 1.0000
1139
+ Val Epoch 32 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1140
+
1141
+ Val Epoch 32 Results:
1142
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1143
+ โ”‚ Metric โ”‚ Value โ”‚
1144
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1145
+ โ”‚ Loss โ”‚ 10.8307 โ”‚
1146
+ โ”‚ RMSE โ”‚ 9.0525 โ”‚
1147
+ โ”‚ Precision โ”‚ 0.781 โ”‚
1148
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1149
+ โ”‚ F1 โ”‚ 0.8529 โ”‚
1150
+ โ”‚ Accuracy โ”‚ 0.781 โ”‚
1151
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1152
+ Epoch 32 | Train Loss: 3.4249 | F1: 0.8529 | RMSE: 9.0525 | LR: 0.000358
1153
+ New best checkpoint saved โ€” F1: 0.8529 at epoch 32
1154
+ Val Epoch 33 | Batch 0/210 | RMSE: 1.5000 | F1: 0.8571
1155
+ Val Epoch 33 | Batch 10/210 | RMSE: 3.2728 | F1: 0.8571
1156
+ Val Epoch 33 | Batch 20/210 | RMSE: 3.3858 | F1: 0.8571
1157
+ Val Epoch 33 | Batch 30/210 | RMSE: 48.6150 | F1: 0.4000
1158
+ Val Epoch 33 | Batch 40/210 | RMSE: 2.5944 | F1: 0.8571
1159
+ Val Epoch 33 | Batch 50/210 | RMSE: 1.8410 | F1: 0.8571
1160
+ Val Epoch 33 | Batch 60/210 | RMSE: 4.2235 | F1: 0.4000
1161
+ Val Epoch 33 | Batch 70/210 | RMSE: 1.7521 | F1: 0.8571
1162
+ Val Epoch 33 | Batch 80/210 | RMSE: 1.3524 | F1: 1.0000
1163
+ Val Epoch 33 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1164
+ Val Epoch 33 | Batch 100/210 | RMSE: 22.8948 | F1: 0.8571
1165
+ Val Epoch 33 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1166
+ Val Epoch 33 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1167
+ Val Epoch 33 | Batch 130/210 | RMSE: 1.3209 | F1: 1.0000
1168
+ Val Epoch 33 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1169
+ Val Epoch 33 | Batch 150/210 | RMSE: 58.8842 | F1: 0.0000
1170
+ Val Epoch 33 | Batch 160/210 | RMSE: 1.5308 | F1: 0.8571
1171
+ Val Epoch 33 | Batch 170/210 | RMSE: 26.3242 | F1: 0.6667
1172
+ Val Epoch 33 | Batch 180/210 | RMSE: 0.7488 | F1: 1.0000
1173
+ Val Epoch 33 | Batch 190/210 | RMSE: 0.8221 | F1: 1.0000
1174
+ Val Epoch 33 | Batch 200/210 | RMSE: 0.9571 | F1: 1.0000
1175
+
1176
+ Val Epoch 33 Results:
1177
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1178
+ โ”‚ Metric โ”‚ Value โ”‚
1179
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1180
+ โ”‚ Loss โ”‚ 10.8201 โ”‚
1181
+ โ”‚ RMSE โ”‚ 8.9698 โ”‚
1182
+ โ”‚ Precision โ”‚ 0.769 โ”‚
1183
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1184
+ โ”‚ F1 โ”‚ 0.8431 โ”‚
1185
+ โ”‚ Accuracy โ”‚ 0.769 โ”‚
1186
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1187
+ Epoch 33 | Train Loss: 3.4322 | F1: 0.8431 | RMSE: 8.9698 | LR: 0.000333
1188
+ Val Epoch 34 | Batch 0/210 | RMSE: 1.8221 | F1: 0.8571
1189
+ Val Epoch 34 | Batch 10/210 | RMSE: 3.8138 | F1: 0.8571
1190
+ Val Epoch 34 | Batch 20/210 | RMSE: 3.3858 | F1: 0.8571
1191
+ Val Epoch 34 | Batch 30/210 | RMSE: 48.6469 | F1: 0.4000
1192
+ Val Epoch 34 | Batch 40/210 | RMSE: 2.2491 | F1: 0.8571
1193
+ Val Epoch 34 | Batch 50/210 | RMSE: 1.8697 | F1: 0.6667
1194
+ Val Epoch 34 | Batch 60/210 | RMSE: 3.1141 | F1: 0.4000
1195
+ Val Epoch 34 | Batch 70/210 | RMSE: 1.7521 | F1: 0.8571
1196
+ Val Epoch 34 | Batch 80/210 | RMSE: 1.2488 | F1: 1.0000
1197
+ Val Epoch 34 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1198
+ Val Epoch 34 | Batch 100/210 | RMSE: 0.7803 | F1: 1.0000
1199
+ Val Epoch 34 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1200
+ Val Epoch 34 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1201
+ Val Epoch 34 | Batch 130/210 | RMSE: 24.1022 | F1: 0.8571
1202
+ Val Epoch 34 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1203
+ Val Epoch 34 | Batch 150/210 | RMSE: 58.5939 | F1: 0.0000
1204
+ Val Epoch 34 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1205
+ Val Epoch 34 | Batch 170/210 | RMSE: 2.5331 | F1: 0.6667
1206
+ Val Epoch 34 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1207
+ Val Epoch 34 | Batch 190/210 | RMSE: 2.7317 | F1: 0.8571
1208
+ Val Epoch 34 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
1209
+
1210
+ Val Epoch 34 Results:
1211
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1212
+ โ”‚ Metric โ”‚ Value โ”‚
1213
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1214
+ โ”‚ Loss โ”‚ 10.831 โ”‚
1215
+ โ”‚ RMSE โ”‚ 8.9611 โ”‚
1216
+ โ”‚ Precision โ”‚ 0.781 โ”‚
1217
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1218
+ โ”‚ F1 โ”‚ 0.8521 โ”‚
1219
+ โ”‚ Accuracy โ”‚ 0.781 โ”‚
1220
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1221
+ Epoch 34 | Train Loss: 3.4539 | F1: 0.8521 | RMSE: 8.9611 | LR: 0.000309
1222
+ Val Epoch 35 | Batch 0/210 | RMSE: 1.9973 | F1: 0.8571
1223
+ Val Epoch 35 | Batch 10/210 | RMSE: 4.0636 | F1: 0.8571
1224
+ Val Epoch 35 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
1225
+ Val Epoch 35 | Batch 30/210 | RMSE: 5.6862 | F1: 0.4000
1226
+ Val Epoch 35 | Batch 40/210 | RMSE: 2.7582 | F1: 0.6667
1227
+ Val Epoch 35 | Batch 50/210 | RMSE: 2.0465 | F1: 0.6667
1228
+ Val Epoch 35 | Batch 60/210 | RMSE: 4.4680 | F1: 0.4000
1229
+ Val Epoch 35 | Batch 70/210 | RMSE: 1.5021 | F1: 0.8571
1230
+ Val Epoch 35 | Batch 80/210 | RMSE: 1.5394 | F1: 1.0000
1231
+ Val Epoch 35 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1232
+ Val Epoch 35 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1233
+ Val Epoch 35 | Batch 110/210 | RMSE: 2.0325 | F1: 0.6667
1234
+ Val Epoch 35 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1235
+ Val Epoch 35 | Batch 130/210 | RMSE: 1.4256 | F1: 1.0000
1236
+ Val Epoch 35 | Batch 140/210 | RMSE: 1.2173 | F1: 1.0000
1237
+ Val Epoch 35 | Batch 150/210 | RMSE: 45.6299 | F1: 0.0000
1238
+ Val Epoch 35 | Batch 160/210 | RMSE: 2.7626 | F1: 0.6667
1239
+ Val Epoch 35 | Batch 170/210 | RMSE: 26.0033 | F1: 0.6667
1240
+ Val Epoch 35 | Batch 180/210 | RMSE: 1.1024 | F1: 1.0000
1241
+ Val Epoch 35 | Batch 190/210 | RMSE: 2.9763 | F1: 0.8571
1242
+ Val Epoch 35 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1243
+
1244
+ Val Epoch 35 Results:
1245
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1246
+ โ”‚ Metric โ”‚ Value โ”‚
1247
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1248
+ โ”‚ Loss โ”‚ 11.0203 โ”‚
1249
+ โ”‚ RMSE โ”‚ 7.867 โ”‚
1250
+ โ”‚ Precision โ”‚ 0.7643 โ”‚
1251
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
1252
+ โ”‚ F1 โ”‚ 0.8375 โ”‚
1253
+ โ”‚ Accuracy โ”‚ 0.7643 โ”‚
1254
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1255
+ Epoch 35 | Train Loss: 3.4179 | F1: 0.8375 | RMSE: 7.8670 | LR: 0.000285
1256
+ Val Epoch 36 | Batch 0/210 | RMSE: 1.3282 | F1: 0.8571
1257
+ Val Epoch 36 | Batch 10/210 | RMSE: 2.5665 | F1: 0.8571
1258
+ Val Epoch 36 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
1259
+ Val Epoch 36 | Batch 30/210 | RMSE: 1.3445 | F1: 0.8571
1260
+ Val Epoch 36 | Batch 40/210 | RMSE: 2.6248 | F1: 0.8571
1261
+ Val Epoch 36 | Batch 50/210 | RMSE: 2.0178 | F1: 0.8571
1262
+ Val Epoch 36 | Batch 60/210 | RMSE: 1.5406 | F1: 1.0000
1263
+ Val Epoch 36 | Batch 70/210 | RMSE: 2.3845 | F1: 0.8571
1264
+ Val Epoch 36 | Batch 80/210 | RMSE: 1.2792 | F1: 1.0000
1265
+ Val Epoch 36 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1266
+ Val Epoch 36 | Batch 100/210 | RMSE: 1.0607 | F1: 1.0000
1267
+ Val Epoch 36 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1268
+ Val Epoch 36 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1269
+ Val Epoch 36 | Batch 130/210 | RMSE: 23.9570 | F1: 0.8571
1270
+ Val Epoch 36 | Batch 140/210 | RMSE: 1.1024 | F1: 1.0000
1271
+ Val Epoch 36 | Batch 150/210 | RMSE: 44.6333 | F1: 0.4000
1272
+ Val Epoch 36 | Batch 160/210 | RMSE: 1.5587 | F1: 0.8571
1273
+ Val Epoch 36 | Batch 170/210 | RMSE: 25.6610 | F1: 0.8571
1274
+ Val Epoch 36 | Batch 180/210 | RMSE: 1.1024 | F1: 1.0000
1275
+ Val Epoch 36 | Batch 190/210 | RMSE: 0.8536 | F1: 1.0000
1276
+ Val Epoch 36 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1277
+
1278
+ Val Epoch 36 Results:
1279
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1280
+ โ”‚ Metric โ”‚ Value โ”‚
1281
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1282
+ โ”‚ Loss โ”‚ 10.8273 โ”‚
1283
+ โ”‚ RMSE โ”‚ 11.9245 โ”‚
1284
+ โ”‚ Precision โ”‚ 0.7774 โ”‚
1285
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
1286
+ โ”‚ F1 โ”‚ 0.8475 โ”‚
1287
+ โ”‚ Accuracy โ”‚ 0.7774 โ”‚
1288
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1289
+ Epoch 36 | Train Loss: 3.4183 | F1: 0.8475 | RMSE: 11.9245 | LR: 0.000263
1290
+ Val Epoch 37 | Batch 0/210 | RMSE: 1.6474 | F1: 0.8571
1291
+ Val Epoch 37 | Batch 10/210 | RMSE: 2.3178 | F1: 0.8571
1292
+ Val Epoch 37 | Batch 20/210 | RMSE: 1.1339 | F1: 1.0000
1293
+ Val Epoch 37 | Batch 30/210 | RMSE: 1.5499 | F1: 0.6667
1294
+ Val Epoch 37 | Batch 40/210 | RMSE: 1.3009 | F1: 0.8571
1295
+ Val Epoch 37 | Batch 50/210 | RMSE: 43.0087 | F1: 0.4000
1296
+ Val Epoch 37 | Batch 60/210 | RMSE: 1.8417 | F1: 0.6667
1297
+ Val Epoch 37 | Batch 70/210 | RMSE: 1.7500 | F1: 0.8571
1298
+ Val Epoch 37 | Batch 80/210 | RMSE: 1.3209 | F1: 1.0000
1299
+ Val Epoch 37 | Batch 90/210 | RMSE: 1.0303 | F1: 1.0000
1300
+ Val Epoch 37 | Batch 100/210 | RMSE: 0.7803 | F1: 1.0000
1301
+ Val Epoch 37 | Batch 110/210 | RMSE: 2.0465 | F1: 0.6667
1302
+ Val Epoch 37 | Batch 120/210 | RMSE: 1.1756 | F1: 1.0000
1303
+ Val Epoch 37 | Batch 130/210 | RMSE: 1.3209 | F1: 1.0000
1304
+ Val Epoch 37 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1305
+ Val Epoch 37 | Batch 150/210 | RMSE: 44.3292 | F1: 0.4000
1306
+ Val Epoch 37 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1307
+ Val Epoch 37 | Batch 170/210 | RMSE: 26.2454 | F1: 0.6667
1308
+ Val Epoch 37 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
1309
+ Val Epoch 37 | Batch 190/210 | RMSE: 0.8536 | F1: 1.0000
1310
+ Val Epoch 37 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1311
+
1312
+ Val Epoch 37 Results:
1313
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1314
+ โ”‚ Metric โ”‚ Value โ”‚
1315
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1316
+ โ”‚ Loss โ”‚ 10.6627 โ”‚
1317
+ โ”‚ RMSE โ”‚ 7.2468 โ”‚
1318
+ โ”‚ Precision โ”‚ 0.8071 โ”‚
1319
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1320
+ โ”‚ F1 โ”‚ 0.8714 โ”‚
1321
+ โ”‚ Accuracy โ”‚ 0.8071 โ”‚
1322
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1323
+ Epoch 37 | Train Loss: 3.4166 | F1: 0.8714 | RMSE: 7.2468 | LR: 0.000242
1324
+ New best checkpoint saved โ€” F1: 0.8714 at epoch 37
1325
+ Val Epoch 38 | Batch 0/210 | RMSE: 1.1556 | F1: 0.8571
1326
+ Val Epoch 38 | Batch 10/210 | RMSE: 2.0697 | F1: 0.8571
1327
+ Val Epoch 38 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
1328
+ Val Epoch 38 | Batch 30/210 | RMSE: 1.1626 | F1: 0.8571
1329
+ Val Epoch 38 | Batch 40/210 | RMSE: 1.6901 | F1: 0.8571
1330
+ Val Epoch 38 | Batch 50/210 | RMSE: 42.8319 | F1: 0.4000
1331
+ Val Epoch 38 | Batch 60/210 | RMSE: 3.1148 | F1: 0.4000
1332
+ Val Epoch 38 | Batch 70/210 | RMSE: 1.5753 | F1: 0.8571
1333
+ Val Epoch 38 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
1334
+ Val Epoch 38 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1335
+ Val Epoch 38 | Batch 100/210 | RMSE: 0.8839 | F1: 1.0000
1336
+ Val Epoch 38 | Batch 110/210 | RMSE: 2.0296 | F1: 0.6667
1337
+ Val Epoch 38 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1338
+ Val Epoch 38 | Batch 130/210 | RMSE: 1.3209 | F1: 1.0000
1339
+ Val Epoch 38 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1340
+ Val Epoch 38 | Batch 150/210 | RMSE: 30.0398 | F1: 0.6667
1341
+ Val Epoch 38 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1342
+ Val Epoch 38 | Batch 170/210 | RMSE: 2.9047 | F1: 0.6667
1343
+ Val Epoch 38 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1344
+ Val Epoch 38 | Batch 190/210 | RMSE: 3.0080 | F1: 0.8571
1345
+ Val Epoch 38 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1346
+
1347
+ Val Epoch 38 Results:
1348
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1349
+ โ”‚ Metric โ”‚ Value โ”‚
1350
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1351
+ โ”‚ Loss โ”‚ 10.6786 โ”‚
1352
+ โ”‚ RMSE โ”‚ 8.265 โ”‚
1353
+ โ”‚ Precision โ”‚ 0.7976 โ”‚
1354
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1355
+ โ”‚ F1 โ”‚ 0.8653 โ”‚
1356
+ โ”‚ Accuracy โ”‚ 0.7976 โ”‚
1357
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1358
+ Epoch 38 | Train Loss: 3.3943 | F1: 0.8653 | RMSE: 8.2650 | LR: 0.000222
1359
+ Val Epoch 39 | Batch 0/210 | RMSE: 1.3107 | F1: 0.8571
1360
+ Val Epoch 39 | Batch 10/210 | RMSE: 1.9863 | F1: 0.8571
1361
+ Val Epoch 39 | Batch 20/210 | RMSE: 1.0607 | F1: 1.0000
1362
+ Val Epoch 39 | Batch 30/210 | RMSE: 1.9819 | F1: 0.4000
1363
+ Val Epoch 39 | Batch 40/210 | RMSE: 2.3639 | F1: 0.8571
1364
+ Val Epoch 39 | Batch 50/210 | RMSE: 2.1787 | F1: 0.4000
1365
+ Val Epoch 39 | Batch 60/210 | RMSE: 1.9322 | F1: 0.4000
1366
+ Val Epoch 39 | Batch 70/210 | RMSE: 2.3205 | F1: 0.8571
1367
+ Val Epoch 39 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
1368
+ Val Epoch 39 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1369
+ Val Epoch 39 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
1370
+ Val Epoch 39 | Batch 110/210 | RMSE: 2.0296 | F1: 0.6667
1371
+ Val Epoch 39 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
1372
+ Val Epoch 39 | Batch 130/210 | RMSE: 1.1441 | F1: 1.0000
1373
+ Val Epoch 39 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1374
+ Val Epoch 39 | Batch 150/210 | RMSE: 0.7803 | F1: 1.0000
1375
+ Val Epoch 39 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1376
+ Val Epoch 39 | Batch 170/210 | RMSE: 3.0826 | F1: 0.6667
1377
+ Val Epoch 39 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1378
+ Val Epoch 39 | Batch 190/210 | RMSE: 2.9817 | F1: 0.8571
1379
+ Val Epoch 39 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1380
+
1381
+ Val Epoch 39 Results:
1382
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1383
+ โ”‚ Metric โ”‚ Value โ”‚
1384
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1385
+ โ”‚ Loss โ”‚ 10.7036 โ”‚
1386
+ โ”‚ RMSE โ”‚ 6.8987 โ”‚
1387
+ โ”‚ Precision โ”‚ 0.7881 โ”‚
1388
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1389
+ โ”‚ F1 โ”‚ 0.8572 โ”‚
1390
+ โ”‚ Accuracy โ”‚ 0.7881 โ”‚
1391
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1392
+ Epoch 39 | Train Loss: 3.4239 | F1: 0.8572 | RMSE: 6.8987 | LR: 0.000203
1393
+ Val Epoch 40 | Batch 0/210 | RMSE: 1.6642 | F1: 0.8571
1394
+ Val Epoch 40 | Batch 10/210 | RMSE: 2.5248 | F1: 0.8571
1395
+ Val Epoch 40 | Batch 20/210 | RMSE: 1.5910 | F1: 1.0000
1396
+ Val Epoch 40 | Batch 30/210 | RMSE: 47.7631 | F1: 0.6667
1397
+ Val Epoch 40 | Batch 40/210 | RMSE: 2.5944 | F1: 0.8571
1398
+ Val Epoch 40 | Batch 50/210 | RMSE: 1.8697 | F1: 0.6667
1399
+ Val Epoch 40 | Batch 60/210 | RMSE: 1.9322 | F1: 0.4000
1400
+ Val Epoch 40 | Batch 70/210 | RMSE: 2.2798 | F1: 0.8571
1401
+ Val Epoch 40 | Batch 80/210 | RMSE: 1.3941 | F1: 1.0000
1402
+ Val Epoch 40 | Batch 90/210 | RMSE: 0.9571 | F1: 1.0000
1403
+ Val Epoch 40 | Batch 100/210 | RMSE: 23.0745 | F1: 0.8571
1404
+ Val Epoch 40 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1405
+ Val Epoch 40 | Batch 120/210 | RMSE: 1.0303 | F1: 1.0000
1406
+ Val Epoch 40 | Batch 130/210 | RMSE: 0.9988 | F1: 1.0000
1407
+ Val Epoch 40 | Batch 140/210 | RMSE: 1.1024 | F1: 1.0000
1408
+ Val Epoch 40 | Batch 150/210 | RMSE: 54.0498 | F1: 0.8571
1409
+ Val Epoch 40 | Batch 160/210 | RMSE: 1.7355 | F1: 0.8571
1410
+ Val Epoch 40 | Batch 170/210 | RMSE: 2.8595 | F1: 0.6667
1411
+ Val Epoch 40 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
1412
+ Val Epoch 40 | Batch 190/210 | RMSE: 3.0549 | F1: 0.8571
1413
+ Val Epoch 40 | Batch 200/210 | RMSE: 1.1756 | F1: 1.0000
1414
+
1415
+ Val Epoch 40 Results:
1416
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1417
+ โ”‚ Metric โ”‚ Value โ”‚
1418
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1419
+ โ”‚ Loss โ”‚ 10.7494 โ”‚
1420
+ โ”‚ RMSE โ”‚ 8.3104 โ”‚
1421
+ โ”‚ Precision โ”‚ 0.7964 โ”‚
1422
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1423
+ โ”‚ F1 โ”‚ 0.8655 โ”‚
1424
+ โ”‚ Accuracy โ”‚ 0.7964 โ”‚
1425
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1426
+ Epoch 40 | Train Loss: 3.3927 | F1: 0.8655 | RMSE: 8.3104 | LR: 0.000186
1427
+ Val Epoch 41 | Batch 0/210 | RMSE: 1.5021 | F1: 0.8571
1428
+ Val Epoch 41 | Batch 10/210 | RMSE: 2.1917 | F1: 0.6667
1429
+ Val Epoch 41 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
1430
+ Val Epoch 41 | Batch 30/210 | RMSE: 1.4559 | F1: 0.8571
1431
+ Val Epoch 41 | Batch 40/210 | RMSE: 2.4177 | F1: 0.8571
1432
+ Val Epoch 41 | Batch 50/210 | RMSE: 1.4874 | F1: 1.0000
1433
+ Val Epoch 41 | Batch 60/210 | RMSE: 1.7685 | F1: 0.6667
1434
+ Val Epoch 41 | Batch 70/210 | RMSE: 2.1020 | F1: 0.8571
1435
+ Val Epoch 41 | Batch 80/210 | RMSE: 0.9256 | F1: 1.0000
1436
+ Val Epoch 41 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1437
+ Val Epoch 41 | Batch 100/210 | RMSE: 0.7803 | F1: 1.0000
1438
+ Val Epoch 41 | Batch 110/210 | RMSE: 1.5264 | F1: 0.8571
1439
+ Val Epoch 41 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
1440
+ Val Epoch 41 | Batch 130/210 | RMSE: 0.9988 | F1: 1.0000
1441
+ Val Epoch 41 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1442
+ Val Epoch 41 | Batch 150/210 | RMSE: 29.7226 | F1: 0.6667
1443
+ Val Epoch 41 | Batch 160/210 | RMSE: 1.7355 | F1: 0.8571
1444
+ Val Epoch 41 | Batch 170/210 | RMSE: 86.3028 | F1: 0.6667
1445
+ Val Epoch 41 | Batch 180/210 | RMSE: 0.6768 | F1: 1.0000
1446
+ Val Epoch 41 | Batch 190/210 | RMSE: 3.0812 | F1: 0.8571
1447
+ Val Epoch 41 | Batch 200/210 | RMSE: 0.7488 | F1: 1.0000
1448
+
1449
+ Val Epoch 41 Results:
1450
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1451
+ โ”‚ Metric โ”‚ Value โ”‚
1452
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1453
+ โ”‚ Loss โ”‚ 10.6313 โ”‚
1454
+ โ”‚ RMSE โ”‚ 8.2577 โ”‚
1455
+ โ”‚ Precision โ”‚ 0.8143 โ”‚
1456
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1457
+ โ”‚ F1 โ”‚ 0.8783 โ”‚
1458
+ โ”‚ Accuracy โ”‚ 0.8143 โ”‚
1459
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1460
+ Epoch 41 | Train Loss: 3.4151 | F1: 0.8783 | RMSE: 8.2577 | LR: 0.000170
1461
+ New best checkpoint saved โ€” F1: 0.8783 at epoch 41
1462
+ Val Epoch 42 | Batch 0/210 | RMSE: 1.4874 | F1: 0.8571
1463
+ Val Epoch 42 | Batch 10/210 | RMSE: 2.1220 | F1: 0.6667
1464
+ Val Epoch 42 | Batch 20/210 | RMSE: 3.2424 | F1: 0.8571
1465
+ Val Epoch 42 | Batch 30/210 | RMSE: 1.5213 | F1: 0.6667
1466
+ Val Epoch 42 | Batch 40/210 | RMSE: 1.9716 | F1: 0.8571
1467
+ Val Epoch 42 | Batch 50/210 | RMSE: 42.8319 | F1: 0.4000
1468
+ Val Epoch 42 | Batch 60/210 | RMSE: 1.9322 | F1: 0.4000
1469
+ Val Epoch 42 | Batch 70/210 | RMSE: 1.8827 | F1: 0.8571
1470
+ Val Epoch 42 | Batch 80/210 | RMSE: 1.0721 | F1: 1.0000
1471
+ Val Epoch 42 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1472
+ Val Epoch 42 | Batch 100/210 | RMSE: 0.8839 | F1: 1.0000
1473
+ Val Epoch 42 | Batch 110/210 | RMSE: 1.4846 | F1: 0.8571
1474
+ Val Epoch 42 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1475
+ Val Epoch 42 | Batch 130/210 | RMSE: 1.1756 | F1: 1.0000
1476
+ Val Epoch 42 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1477
+ Val Epoch 42 | Batch 150/210 | RMSE: 31.1420 | F1: 0.4000
1478
+ Val Epoch 42 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1479
+ Val Epoch 42 | Batch 170/210 | RMSE: 26.3242 | F1: 0.6667
1480
+ Val Epoch 42 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1481
+ Val Epoch 42 | Batch 190/210 | RMSE: 2.9817 | F1: 0.8571
1482
+ Val Epoch 42 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1483
+
1484
+ Val Epoch 42 Results:
1485
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1486
+ โ”‚ Metric โ”‚ Value โ”‚
1487
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1488
+ โ”‚ Loss โ”‚ 10.7093 โ”‚
1489
+ โ”‚ RMSE โ”‚ 9.7462 โ”‚
1490
+ โ”‚ Precision โ”‚ 0.7798 โ”‚
1491
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1492
+ โ”‚ F1 โ”‚ 0.851 โ”‚
1493
+ โ”‚ Accuracy โ”‚ 0.7798 โ”‚
1494
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1495
+ Epoch 42 | Train Loss: 3.3951 | F1: 0.8510 | RMSE: 9.7462 | LR: 0.000156
1496
+ Val Epoch 43 | Batch 0/210 | RMSE: 1.6788 | F1: 0.8571
1497
+ Val Epoch 43 | Batch 10/210 | RMSE: 1.9165 | F1: 0.8571
1498
+ Val Epoch 43 | Batch 20/210 | RMSE: 3.2424 | F1: 0.8571
1499
+ Val Epoch 43 | Batch 30/210 | RMSE: 1.5213 | F1: 0.6667
1500
+ Val Epoch 43 | Batch 40/210 | RMSE: 1.5394 | F1: 0.8571
1501
+ Val Epoch 43 | Batch 50/210 | RMSE: 2.0751 | F1: 0.4000
1502
+ Val Epoch 43 | Batch 60/210 | RMSE: 1.8680 | F1: 0.6667
1503
+ Val Epoch 43 | Batch 70/210 | RMSE: 2.2798 | F1: 0.8571
1504
+ Val Epoch 43 | Batch 80/210 | RMSE: 1.5811 | F1: 1.0000
1505
+ Val Epoch 43 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1506
+ Val Epoch 43 | Batch 100/210 | RMSE: 0.7803 | F1: 1.0000
1507
+ Val Epoch 43 | Batch 110/210 | RMSE: 1.8557 | F1: 0.6667
1508
+ Val Epoch 43 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1509
+ Val Epoch 43 | Batch 130/210 | RMSE: 1.1756 | F1: 1.0000
1510
+ Val Epoch 43 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1511
+ Val Epoch 43 | Batch 150/210 | RMSE: 31.2084 | F1: 0.4000
1512
+ Val Epoch 43 | Batch 160/210 | RMSE: 0.5000 | F1: 1.0000
1513
+ Val Epoch 43 | Batch 170/210 | RMSE: 26.5325 | F1: 0.6667
1514
+ Val Epoch 43 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
1515
+ Val Epoch 43 | Batch 190/210 | RMSE: 3.1531 | F1: 0.8571
1516
+ Val Epoch 43 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1517
+
1518
+ Val Epoch 43 Results:
1519
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1520
+ โ”‚ Metric โ”‚ Value โ”‚
1521
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1522
+ โ”‚ Loss โ”‚ 10.7714 โ”‚
1523
+ โ”‚ RMSE โ”‚ 8.9663 โ”‚
1524
+ โ”‚ Precision โ”‚ 0.7833 โ”‚
1525
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1526
+ โ”‚ F1 โ”‚ 0.8549 โ”‚
1527
+ โ”‚ Accuracy โ”‚ 0.7833 โ”‚
1528
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1529
+ Epoch 43 | Train Loss: 3.4145 | F1: 0.8549 | RMSE: 8.9663 | LR: 0.000143
1530
+ Val Epoch 44 | Batch 0/210 | RMSE: 1.4874 | F1: 0.8571
1531
+ Val Epoch 44 | Batch 10/210 | RMSE: 2.1631 | F1: 0.8571
1532
+ Val Epoch 44 | Batch 20/210 | RMSE: 1.4142 | F1: 1.0000
1533
+ Val Epoch 44 | Batch 30/210 | RMSE: 1.5213 | F1: 0.6667
1534
+ Val Epoch 44 | Batch 40/210 | RMSE: 1.5394 | F1: 0.8571
1535
+ Val Epoch 44 | Batch 50/210 | RMSE: 1.6929 | F1: 0.8571
1536
+ Val Epoch 44 | Batch 60/210 | RMSE: 1.7685 | F1: 0.6667
1537
+ Val Epoch 44 | Batch 70/210 | RMSE: 2.2798 | F1: 0.8571
1538
+ Val Epoch 44 | Batch 80/210 | RMSE: 1.0303 | F1: 1.0000
1539
+ Val Epoch 44 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1540
+ Val Epoch 44 | Batch 100/210 | RMSE: 0.7803 | F1: 1.0000
1541
+ Val Epoch 44 | Batch 110/210 | RMSE: 1.4846 | F1: 0.8571
1542
+ Val Epoch 44 | Batch 120/210 | RMSE: 1.0607 | F1: 1.0000
1543
+ Val Epoch 44 | Batch 130/210 | RMSE: 1.0721 | F1: 1.0000
1544
+ Val Epoch 44 | Batch 140/210 | RMSE: 1.1756 | F1: 1.0000
1545
+ Val Epoch 44 | Batch 150/210 | RMSE: 15.8935 | F1: 0.8571
1546
+ Val Epoch 44 | Batch 160/210 | RMSE: 0.4268 | F1: 1.0000
1547
+ Val Epoch 44 | Batch 170/210 | RMSE: 54.7435 | F1: 0.6667
1548
+ Val Epoch 44 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
1549
+ Val Epoch 44 | Batch 190/210 | RMSE: 3.0812 | F1: 0.8571
1550
+ Val Epoch 44 | Batch 200/210 | RMSE: 0.8536 | F1: 1.0000
1551
+
1552
+ Val Epoch 44 Results:
1553
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1554
+ โ”‚ Metric โ”‚ Value โ”‚
1555
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1556
+ โ”‚ Loss โ”‚ 10.6315 โ”‚
1557
+ โ”‚ RMSE โ”‚ 7.1867 โ”‚
1558
+ โ”‚ Precision โ”‚ 0.8048 โ”‚
1559
+ โ”‚ Recall โ”‚ 0.9857 โ”‚
1560
+ โ”‚ F1 โ”‚ 0.8688 โ”‚
1561
+ โ”‚ Accuracy โ”‚ 0.8048 โ”‚
1562
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1563
+ Epoch 44 | Train Loss: 3.3981 | F1: 0.8688 | RMSE: 7.1867 | LR: 0.000132
1564
+ Val Epoch 45 | Batch 0/210 | RMSE: 1.6788 | F1: 0.8571
1565
+ Val Epoch 45 | Batch 10/210 | RMSE: 3.0233 | F1: 0.8571
1566
+ Val Epoch 45 | Batch 20/210 | RMSE: 1.0607 | F1: 1.0000
1567
+ Val Epoch 45 | Batch 30/210 | RMSE: 1.5213 | F1: 0.6667
1568
+ Val Epoch 45 | Batch 40/210 | RMSE: 2.5944 | F1: 0.8571
1569
+ Val Epoch 45 | Batch 50/210 | RMSE: 42.8319 | F1: 0.4000
1570
+ Val Epoch 45 | Batch 60/210 | RMSE: 1.7685 | F1: 0.6667
1571
+ Val Epoch 45 | Batch 70/210 | RMSE: 1.9559 | F1: 0.8571
1572
+ Val Epoch 45 | Batch 80/210 | RMSE: 1.3107 | F1: 1.0000
1573
+ Val Epoch 45 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1574
+ Val Epoch 45 | Batch 100/210 | RMSE: 0.7071 | F1: 1.0000
1575
+ Val Epoch 45 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1576
+ Val Epoch 45 | Batch 120/210 | RMSE: 1.1339 | F1: 1.0000
1577
+ Val Epoch 45 | Batch 130/210 | RMSE: 1.1756 | F1: 1.0000
1578
+ Val Epoch 45 | Batch 140/210 | RMSE: 1.1339 | F1: 1.0000
1579
+ Val Epoch 45 | Batch 150/210 | RMSE: 17.5961 | F1: 0.6667
1580
+ Val Epoch 45 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1581
+ Val Epoch 45 | Batch 170/210 | RMSE: 85.8134 | F1: 0.6667
1582
+ Val Epoch 45 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
1583
+ Val Epoch 45 | Batch 190/210 | RMSE: 2.9084 | F1: 0.8571
1584
+ Val Epoch 45 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
1585
+
1586
+ Val Epoch 45 Results:
1587
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1588
+ โ”‚ Metric โ”‚ Value โ”‚
1589
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1590
+ โ”‚ Loss โ”‚ 10.7075 โ”‚
1591
+ โ”‚ RMSE โ”‚ 8.1088 โ”‚
1592
+ โ”‚ Precision โ”‚ 0.7964 โ”‚
1593
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1594
+ โ”‚ F1 โ”‚ 0.8649 โ”‚
1595
+ โ”‚ Accuracy โ”‚ 0.7964 โ”‚
1596
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1597
+ Epoch 45 | Train Loss: 3.4067 | F1: 0.8649 | RMSE: 8.1088 | LR: 0.000122
1598
+ Val Epoch 46 | Batch 0/210 | RMSE: 1.6788 | F1: 0.8571
1599
+ Val Epoch 46 | Batch 10/210 | RMSE: 1.8232 | F1: 0.8571
1600
+ Val Epoch 46 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
1601
+ Val Epoch 46 | Batch 30/210 | RMSE: 1.1339 | F1: 0.8571
1602
+ Val Epoch 46 | Batch 40/210 | RMSE: 2.5944 | F1: 0.8571
1603
+ Val Epoch 46 | Batch 50/210 | RMSE: 2.0178 | F1: 0.8571
1604
+ Val Epoch 46 | Batch 60/210 | RMSE: 1.8417 | F1: 0.6667
1605
+ Val Epoch 46 | Batch 70/210 | RMSE: 2.2473 | F1: 0.8571
1606
+ Val Epoch 46 | Batch 80/210 | RMSE: 1.4977 | F1: 1.0000
1607
+ Val Epoch 46 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1608
+ Val Epoch 46 | Batch 100/210 | RMSE: 0.5303 | F1: 1.0000
1609
+ Val Epoch 46 | Batch 110/210 | RMSE: 2.0325 | F1: 0.6667
1610
+ Val Epoch 46 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
1611
+ Val Epoch 46 | Batch 130/210 | RMSE: 1.3536 | F1: 1.0000
1612
+ Val Epoch 46 | Batch 140/210 | RMSE: 1.3524 | F1: 1.0000
1613
+ Val Epoch 46 | Batch 150/210 | RMSE: 3.8328 | F1: 0.8571
1614
+ Val Epoch 46 | Batch 160/210 | RMSE: 1.6319 | F1: 0.8571
1615
+ Val Epoch 46 | Batch 170/210 | RMSE: 85.8520 | F1: 0.6667
1616
+ Val Epoch 46 | Batch 180/210 | RMSE: 0.9256 | F1: 1.0000
1617
+ Val Epoch 46 | Batch 190/210 | RMSE: 2.9817 | F1: 0.8571
1618
+ Val Epoch 46 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1619
+
1620
+ Val Epoch 46 Results:
1621
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1622
+ โ”‚ Metric โ”‚ Value โ”‚
1623
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1624
+ โ”‚ Loss โ”‚ 10.5792 โ”‚
1625
+ โ”‚ RMSE โ”‚ 8.4989 โ”‚
1626
+ โ”‚ Precision โ”‚ 0.8107 โ”‚
1627
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1628
+ โ”‚ F1 โ”‚ 0.8759 โ”‚
1629
+ โ”‚ Accuracy โ”‚ 0.8107 โ”‚
1630
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1631
+ Epoch 46 | Train Loss: 3.3745 | F1: 0.8759 | RMSE: 8.4989 | LR: 0.000114
1632
+ Val Epoch 47 | Batch 0/210 | RMSE: 1.6642 | F1: 0.8571
1633
+ Val Epoch 47 | Batch 10/210 | RMSE: 2.5665 | F1: 0.8571
1634
+ Val Epoch 47 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
1635
+ Val Epoch 47 | Batch 30/210 | RMSE: 1.1339 | F1: 0.8571
1636
+ Val Epoch 47 | Batch 40/210 | RMSE: 2.5944 | F1: 0.8571
1637
+ Val Epoch 47 | Batch 50/210 | RMSE: 10.6507 | F1: 0.6667
1638
+ Val Epoch 47 | Batch 60/210 | RMSE: 1.8417 | F1: 0.6667
1639
+ Val Epoch 47 | Batch 70/210 | RMSE: 2.1020 | F1: 0.8571
1640
+ Val Epoch 47 | Batch 80/210 | RMSE: 1.5394 | F1: 1.0000
1641
+ Val Epoch 47 | Batch 90/210 | RMSE: 0.8536 | F1: 1.0000
1642
+ Val Epoch 47 | Batch 100/210 | RMSE: 0.5303 | F1: 1.0000
1643
+ Val Epoch 47 | Batch 110/210 | RMSE: 2.2064 | F1: 0.6667
1644
+ Val Epoch 47 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
1645
+ Val Epoch 47 | Batch 130/210 | RMSE: 1.2803 | F1: 1.0000
1646
+ Val Epoch 47 | Batch 140/210 | RMSE: 1.3524 | F1: 1.0000
1647
+ Val Epoch 47 | Batch 150/210 | RMSE: 14.5671 | F1: 0.8571
1648
+ Val Epoch 47 | Batch 160/210 | RMSE: 1.8783 | F1: 0.8571
1649
+ Val Epoch 47 | Batch 170/210 | RMSE: 85.8520 | F1: 0.6667
1650
+ Val Epoch 47 | Batch 180/210 | RMSE: 1.1441 | F1: 1.0000
1651
+ Val Epoch 47 | Batch 190/210 | RMSE: 2.9084 | F1: 0.8571
1652
+ Val Epoch 47 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1653
+
1654
+ Val Epoch 47 Results:
1655
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1656
+ โ”‚ Metric โ”‚ Value โ”‚
1657
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1658
+ โ”‚ Loss โ”‚ 10.6392 โ”‚
1659
+ โ”‚ RMSE โ”‚ 7.0137 โ”‚
1660
+ โ”‚ Precision โ”‚ 0.8036 โ”‚
1661
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1662
+ โ”‚ F1 โ”‚ 0.8712 โ”‚
1663
+ โ”‚ Accuracy โ”‚ 0.8036 โ”‚
1664
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1665
+ Epoch 47 | Train Loss: 3.3930 | F1: 0.8712 | RMSE: 7.0137 | LR: 0.000108
1666
+ Val Epoch 48 | Batch 0/210 | RMSE: 1.8095 | F1: 0.8571
1667
+ Val Epoch 48 | Batch 10/210 | RMSE: 2.8941 | F1: 0.8571
1668
+ Val Epoch 48 | Batch 20/210 | RMSE: 1.2374 | F1: 1.0000
1669
+ Val Epoch 48 | Batch 30/210 | RMSE: 1.3839 | F1: 0.8571
1670
+ Val Epoch 48 | Batch 40/210 | RMSE: 2.2806 | F1: 0.8571
1671
+ Val Epoch 48 | Batch 50/210 | RMSE: 1.9445 | F1: 0.8571
1672
+ Val Epoch 48 | Batch 60/210 | RMSE: 1.9322 | F1: 0.4000
1673
+ Val Epoch 48 | Batch 70/210 | RMSE: 1.9559 | F1: 0.8571
1674
+ Val Epoch 48 | Batch 80/210 | RMSE: 1.5811 | F1: 1.0000
1675
+ Val Epoch 48 | Batch 90/210 | RMSE: 0.7803 | F1: 1.0000
1676
+ Val Epoch 48 | Batch 100/210 | RMSE: 0.6036 | F1: 1.0000
1677
+ Val Epoch 48 | Batch 110/210 | RMSE: 1.8557 | F1: 0.6667
1678
+ Val Epoch 48 | Batch 120/210 | RMSE: 1.0303 | F1: 1.0000
1679
+ Val Epoch 48 | Batch 130/210 | RMSE: 1.1756 | F1: 1.0000
1680
+ Val Epoch 48 | Batch 140/210 | RMSE: 1.1024 | F1: 1.0000
1681
+ Val Epoch 48 | Batch 150/210 | RMSE: 0.5303 | F1: 1.0000
1682
+ Val Epoch 48 | Batch 160/210 | RMSE: 0.4268 | F1: 1.0000
1683
+ Val Epoch 48 | Batch 170/210 | RMSE: 54.7182 | F1: 0.6667
1684
+ Val Epoch 48 | Batch 180/210 | RMSE: 0.8221 | F1: 1.0000
1685
+ Val Epoch 48 | Batch 190/210 | RMSE: 0.9268 | F1: 1.0000
1686
+ Val Epoch 48 | Batch 200/210 | RMSE: 0.9256 | F1: 1.0000
1687
+
1688
+ Val Epoch 48 Results:
1689
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1690
+ โ”‚ Metric โ”‚ Value โ”‚
1691
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1692
+ โ”‚ Loss โ”‚ 10.6588 โ”‚
1693
+ โ”‚ RMSE โ”‚ 7.3171 โ”‚
1694
+ โ”‚ Precision โ”‚ 0.806 โ”‚
1695
+ โ”‚ Recall โ”‚ 0.9952 โ”‚
1696
+ โ”‚ F1 โ”‚ 0.871 โ”‚
1697
+ โ”‚ Accuracy โ”‚ 0.806 โ”‚
1698
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1699
+ Epoch 48 | Train Loss: 3.3983 | F1: 0.8710 | RMSE: 7.3171 | LR: 0.000104
1700
+ Val Epoch 49 | Batch 0/210 | RMSE: 1.7059 | F1: 0.8571
1701
+ Val Epoch 49 | Batch 10/210 | RMSE: 1.8232 | F1: 0.8571
1702
+ Val Epoch 49 | Batch 20/210 | RMSE: 1.3107 | F1: 1.0000
1703
+ Val Epoch 49 | Batch 30/210 | RMSE: 1.5213 | F1: 0.6667
1704
+ Val Epoch 49 | Batch 40/210 | RMSE: 1.8669 | F1: 0.8571
1705
+ Val Epoch 49 | Batch 50/210 | RMSE: 1.2948 | F1: 0.6667
1706
+ Val Epoch 49 | Batch 60/210 | RMSE: 1.6311 | F1: 0.8571
1707
+ Val Epoch 49 | Batch 70/210 | RMSE: 1.8827 | F1: 0.8571
1708
+ Val Epoch 49 | Batch 80/210 | RMSE: 1.3626 | F1: 1.0000
1709
+ Val Epoch 49 | Batch 90/210 | RMSE: 0.6036 | F1: 1.0000
1710
+ Val Epoch 49 | Batch 100/210 | RMSE: 0.5303 | F1: 1.0000
1711
+ Val Epoch 49 | Batch 110/210 | RMSE: 2.0296 | F1: 0.6667
1712
+ Val Epoch 49 | Batch 120/210 | RMSE: 0.9571 | F1: 1.0000
1713
+ Val Epoch 49 | Batch 130/210 | RMSE: 1.1756 | F1: 1.0000
1714
+ Val Epoch 49 | Batch 140/210 | RMSE: 1.3524 | F1: 1.0000
1715
+ Val Epoch 49 | Batch 150/210 | RMSE: 0.7071 | F1: 1.0000
1716
+ Val Epoch 49 | Batch 160/210 | RMSE: 0.6036 | F1: 1.0000
1717
+ Val Epoch 49 | Batch 170/210 | RMSE: 34.2221 | F1: 0.6667
1718
+ Val Epoch 49 | Batch 180/210 | RMSE: 0.6768 | F1: 1.0000
1719
+ Val Epoch 49 | Batch 190/210 | RMSE: 0.9268 | F1: 1.0000
1720
+ Val Epoch 49 | Batch 200/210 | RMSE: 1.1024 | F1: 1.0000
1721
+
1722
+ Val Epoch 49 Results:
1723
+ โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
1724
+ โ”‚ Metric โ”‚ Value โ”‚
1725
+ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
1726
+ โ”‚ Loss โ”‚ 10.6741 โ”‚
1727
+ โ”‚ RMSE โ”‚ 6.1561 โ”‚
1728
+ โ”‚ Precision โ”‚ 0.7988 โ”‚
1729
+ โ”‚ Recall โ”‚ 0.9905 โ”‚
1730
+ โ”‚ F1 โ”‚ 0.8666 โ”‚
1731
+ โ”‚ Accuracy โ”‚ 0.7988 โ”‚
1732
+ โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
1733
+ Epoch 49 | Train Loss: 3.3902 | F1: 0.8666 | RMSE: 6.1561 | LR: 0.000101
1734
+ Training complete. Best F1: 0.8783 | Best checkpoint: ../logs/TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_best.pth
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794a2328bccafe9881c9685b6e28a9aad8ef53e9705ce2a8be80e23c59c2653d
3
+ size 23705262
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_latest.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825e296f7a5146f5d232cae9b0deed13c61d171c2eca687345adb4374a98573f
3
+ size 23706262
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/model_params.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_choice": "TOTNet",
3
+ "num_frames": 5,
4
+ "image_size": [
5
+ 512,
6
+ 512
7
+ ],
8
+ "num_channels": 32
9
+ }
TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32/training_args.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "seed": 2024,
3
+ "video_dir": "/home/s224705071/github/PhysicsInformedDeformableAttentionNetwork/data/tta_tracking/videos",
4
+ "labels_path": "/home/s224705071/github/PhysicsInformedDeformableAttentionNetwork/data/tta_tracking/train.json",
5
+ "logger_name": "TOTNet_TTA_(5)_Bidirect_(512,512)_BallMask_50epochs_WBCE[1,2,3,3]_bs_ch32",
6
+ "use_amp": false,
7
+ "val_split": 0.2,
8
+ "batch_size": 4,
9
+ "num_workers": 8,
10
+ "prefetch_factor": 4,
11
+ "disable_persistent_workers": false,
12
+ "print_freq": 100,
13
+ "checkpoint_freq": 1,
14
+ "earlystop_patience": null,
15
+ "pretrained_path": null,
16
+ "num_classes": 1,
17
+ "model_choice": "TOTNet",
18
+ "weighting_list": [
19
+ 1,
20
+ 2,
21
+ 3,
22
+ 3
23
+ ],
24
+ "num_channels": 32,
25
+ "num_frames": 5,
26
+ "interval": 1,
27
+ "start_epoch": 1,
28
+ "num_epochs": 50,
29
+ "lr": 0.001,
30
+ "minimum_lr": 1e-07,
31
+ "momentum": 0.9,
32
+ "weight_decay": 0.0001,
33
+ "optimizer_type": "adamw",
34
+ "loss_function": "WBCE",
35
+ "lr_type": "cosine",
36
+ "lr_factor": 0.5,
37
+ "lr_step_size": 5,
38
+ "lr_patience": 3,
39
+ "occluded_prob": 0.5,
40
+ "ball_size": 3,
41
+ "bidirectional": true,
42
+ "img_size": [
43
+ 512,
44
+ 512
45
+ ]
46
+ }