Hugging Face's logo

steveice
/
videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen

Video Classification
Transformers
PyTorch
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
steveice commited on
Commit
9ab503d
•
1 Parent(s): cd34e0f

Model save

Browse files
Files changed (2) hide show
  1. README.md +110 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: MCG-NJU/videomae-large-finetuned-kinetics
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # videomae-large-finetuned-kinetics-finetuned-videomae-large-kitchen
17
+
18
+ This model is a fine-tuned version of [MCG-NJU/videomae-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6309
21
+ - Accuracy: 0.8900
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 11100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 3.5158 | 0.02 | 222 | 3.6067 | 0.0588 |
54
+ | 2.8571 | 1.02 | 444 | 3.1445 | 0.3014 |
55
+ | 1.8854 | 2.02 | 666 | 2.3644 | 0.4607 |
56
+ | 1.5533 | 3.02 | 888 | 1.7967 | 0.5621 |
57
+ | 1.3935 | 4.02 | 1110 | 1.3755 | 0.6502 |
58
+ | 1.1722 | 5.02 | 1332 | 1.2232 | 0.7109 |
59
+ | 0.2896 | 6.02 | 1554 | 1.2859 | 0.6256 |
60
+ | 0.3166 | 7.02 | 1776 | 1.2910 | 0.6720 |
61
+ | 0.6902 | 8.02 | 1998 | 1.2702 | 0.6995 |
62
+ | 0.4193 | 9.02 | 2220 | 1.2087 | 0.7137 |
63
+ | 0.1889 | 10.02 | 2442 | 1.0500 | 0.7611 |
64
+ | 0.4502 | 11.02 | 2664 | 1.1647 | 0.7118 |
65
+ | 0.7703 | 12.02 | 2886 | 1.1037 | 0.7242 |
66
+ | 0.0957 | 13.02 | 3108 | 1.0967 | 0.7706 |
67
+ | 0.3202 | 14.02 | 3330 | 1.0479 | 0.7545 |
68
+ | 0.3634 | 15.02 | 3552 | 1.0714 | 0.8057 |
69
+ | 0.3883 | 16.02 | 3774 | 1.2323 | 0.7498 |
70
+ | 0.0322 | 17.02 | 3996 | 1.0504 | 0.7848 |
71
+ | 0.5108 | 18.02 | 4218 | 1.1356 | 0.7915 |
72
+ | 0.309 | 19.02 | 4440 | 1.1409 | 0.7592 |
73
+ | 0.56 | 20.02 | 4662 | 1.0828 | 0.7915 |
74
+ | 0.3675 | 21.02 | 4884 | 0.9154 | 0.8123 |
75
+ | 0.0076 | 22.02 | 5106 | 1.0974 | 0.8133 |
76
+ | 0.0451 | 23.02 | 5328 | 1.0361 | 0.8152 |
77
+ | 0.2558 | 24.02 | 5550 | 0.7830 | 0.8237 |
78
+ | 0.0125 | 25.02 | 5772 | 0.8728 | 0.8171 |
79
+ | 0.4184 | 26.02 | 5994 | 0.8413 | 0.8265 |
80
+ | 0.2566 | 27.02 | 6216 | 1.0644 | 0.8009 |
81
+ | 0.1257 | 28.02 | 6438 | 0.8641 | 0.8265 |
82
+ | 0.1326 | 29.02 | 6660 | 0.8444 | 0.8417 |
83
+ | 0.0436 | 30.02 | 6882 | 0.8615 | 0.8322 |
84
+ | 0.0408 | 31.02 | 7104 | 0.8075 | 0.8332 |
85
+ | 0.0316 | 32.02 | 7326 | 0.8699 | 0.8341 |
86
+ | 0.2235 | 33.02 | 7548 | 0.8151 | 0.8455 |
87
+ | 0.0079 | 34.02 | 7770 | 0.8099 | 0.8550 |
88
+ | 0.001 | 35.02 | 7992 | 0.8640 | 0.8370 |
89
+ | 0.0007 | 36.02 | 8214 | 0.7146 | 0.8483 |
90
+ | 0.464 | 37.02 | 8436 | 0.7917 | 0.8464 |
91
+ | 0.0005 | 38.02 | 8658 | 0.7239 | 0.8531 |
92
+ | 0.0004 | 39.02 | 8880 | 0.7702 | 0.8701 |
93
+ | 0.1705 | 40.02 | 9102 | 0.7543 | 0.8521 |
94
+ | 0.0039 | 41.02 | 9324 | 0.7456 | 0.8673 |
95
+ | 0.0168 | 42.02 | 9546 | 0.7255 | 0.8730 |
96
+ | 0.2615 | 43.02 | 9768 | 0.7453 | 0.8758 |
97
+ | 0.0004 | 44.02 | 9990 | 0.6824 | 0.8806 |
98
+ | 0.236 | 45.02 | 10212 | 0.6624 | 0.8825 |
99
+ | 0.0007 | 46.02 | 10434 | 0.6727 | 0.8815 |
100
+ | 0.0004 | 47.02 | 10656 | 0.6478 | 0.8863 |
101
+ | 0.268 | 48.02 | 10878 | 0.6309 | 0.8900 |
102
+ | 0.0025 | 49.02 | 11100 | 0.6284 | 0.8900 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.33.2
108
+ - Pytorch 1.12.1+cu113
109
+ - Datasets 2.14.5
110
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03896d25f575ce6d99ecdfda04d321a245361f06d5e8749f8cd1e4472d11f16b
3
  size 1215734821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0211367ce588f4122495f5180d67c014ea80be13aebd8cbd34e85eeb61fa1dd3
3
  size 1215734821