Hugging Face's logo

rickysk
/
videomae-base-ipm_all_videos

Video Classification
Transformers
PyTorch
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
1
rickysk commited on
Commit
1eea91d
•
1 Parent(s): 222d0a4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +119 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: videomae-base-ipm_all_videos
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # videomae-base-ipm_all_videos
16
+
17
+ This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4713
20
+ - Accuracy: 0.8559
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - training_steps: 3600
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 1.7831 | 0.02 | 60 | 1.8965 | 0.1186 |
53
+ | 1.7706 | 1.02 | 120 | 1.9115 | 0.1186 |
54
+ | 1.7497 | 2.02 | 180 | 1.8985 | 0.1356 |
55
+ | 1.5214 | 3.02 | 240 | 1.4807 | 0.3475 |
56
+ | 1.1458 | 4.02 | 300 | 1.7024 | 0.3559 |
57
+ | 1.1587 | 5.02 | 360 | 1.6771 | 0.2966 |
58
+ | 0.9256 | 6.02 | 420 | 1.6428 | 0.3814 |
59
+ | 1.265 | 7.02 | 480 | 1.5169 | 0.5 |
60
+ | 0.8271 | 8.02 | 540 | 1.0310 | 0.5847 |
61
+ | 0.6011 | 9.02 | 600 | 1.1739 | 0.5508 |
62
+ | 0.9542 | 10.02 | 660 | 1.3323 | 0.5424 |
63
+ | 1.1231 | 11.02 | 720 | 1.4279 | 0.4915 |
64
+ | 0.728 | 12.02 | 780 | 2.1913 | 0.4661 |
65
+ | 0.5991 | 13.02 | 840 | 1.1088 | 0.6271 |
66
+ | 1.0613 | 14.02 | 900 | 1.3781 | 0.5 |
67
+ | 0.9121 | 15.02 | 960 | 1.4224 | 0.5424 |
68
+ | 0.6083 | 16.02 | 1020 | 0.8779 | 0.6695 |
69
+ | 0.408 | 17.02 | 1080 | 0.8512 | 0.7119 |
70
+ | 0.3741 | 18.02 | 1140 | 0.8884 | 0.7034 |
71
+ | 0.8906 | 19.02 | 1200 | 1.1396 | 0.6017 |
72
+ | 0.568 | 20.02 | 1260 | 0.7380 | 0.6949 |
73
+ | 0.4135 | 21.02 | 1320 | 0.7966 | 0.6525 |
74
+ | 0.5492 | 22.02 | 1380 | 0.9815 | 0.6780 |
75
+ | 0.902 | 23.02 | 1440 | 0.9267 | 0.6441 |
76
+ | 0.6889 | 24.02 | 1500 | 1.4313 | 0.5763 |
77
+ | 0.788 | 25.02 | 1560 | 1.2156 | 0.5678 |
78
+ | 0.7324 | 26.02 | 1620 | 0.8015 | 0.6780 |
79
+ | 0.6733 | 27.02 | 1680 | 0.8682 | 0.6949 |
80
+ | 0.498 | 28.02 | 1740 | 0.8767 | 0.6949 |
81
+ | 0.5558 | 29.02 | 1800 | 0.9248 | 0.6780 |
82
+ | 0.5583 | 30.02 | 1860 | 1.1784 | 0.6356 |
83
+ | 0.3905 | 31.02 | 1920 | 1.0646 | 0.6864 |
84
+ | 0.3728 | 32.02 | 1980 | 0.8338 | 0.7797 |
85
+ | 0.5988 | 33.02 | 2040 | 0.8339 | 0.7542 |
86
+ | 0.3636 | 34.02 | 2100 | 0.7577 | 0.7627 |
87
+ | 0.505 | 35.02 | 2160 | 1.0310 | 0.6864 |
88
+ | 0.5344 | 36.02 | 2220 | 0.6345 | 0.7458 |
89
+ | 0.2814 | 37.02 | 2280 | 0.9954 | 0.7119 |
90
+ | 0.2187 | 38.02 | 2340 | 0.7515 | 0.7797 |
91
+ | 0.4876 | 39.02 | 2400 | 0.8392 | 0.7627 |
92
+ | 0.1148 | 40.02 | 2460 | 0.6182 | 0.8729 |
93
+ | 0.3139 | 41.02 | 2520 | 1.1651 | 0.6949 |
94
+ | 0.2638 | 42.02 | 2580 | 0.8299 | 0.7797 |
95
+ | 0.1989 | 43.02 | 2640 | 0.5943 | 0.8220 |
96
+ | 0.5473 | 44.02 | 2700 | 0.6514 | 0.8644 |
97
+ | 0.3921 | 45.02 | 2760 | 0.6708 | 0.8220 |
98
+ | 0.1756 | 46.02 | 2820 | 0.5431 | 0.8305 |
99
+ | 0.1089 | 47.02 | 2880 | 0.6040 | 0.8136 |
100
+ | 0.3616 | 48.02 | 2940 | 0.5281 | 0.8475 |
101
+ | 0.2752 | 49.02 | 3000 | 0.6430 | 0.8305 |
102
+ | 0.3847 | 50.02 | 3060 | 0.5640 | 0.8644 |
103
+ | 0.0909 | 51.02 | 3120 | 0.5178 | 0.8559 |
104
+ | 0.3426 | 52.02 | 3180 | 0.3770 | 0.8983 |
105
+ | 0.0516 | 53.02 | 3240 | 0.5365 | 0.8390 |
106
+ | 0.2133 | 54.02 | 3300 | 0.5919 | 0.8475 |
107
+ | 0.1382 | 55.02 | 3360 | 0.5112 | 0.8390 |
108
+ | 0.1803 | 56.02 | 3420 | 0.5173 | 0.8475 |
109
+ | 0.1352 | 57.02 | 3480 | 0.5207 | 0.8390 |
110
+ | 0.4445 | 58.02 | 3540 | 0.4763 | 0.8559 |
111
+ | 0.3249 | 59.02 | 3600 | 0.4713 | 0.8559 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.29.1
117
+ - Pytorch 2.0.1+cu117
118
+ - Datasets 2.12.0
119
+ - Tokenizers 0.13.3