yangboyuan
commited on
Commit
•
02ffff0
1
Parent(s):
09191a7
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: google/vivit-b-16x2-kinetics400
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: vivit-b-16x2-kinetics400-finetuned-vivit-diagnose
|
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 |
+
# vivit-b-16x2-kinetics400-finetuned-vivit-diagnose
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.8988
|
21 |
+
- Accuracy: 0.6953
|
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: 1
|
42 |
+
- eval_batch_size: 1
|
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: 3430
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 1.8386 | 0.1 | 343 | 1.5448 | 0.5448 |
|
54 |
+
| 1.1419 | 1.1 | 686 | 1.2918 | 0.5412 |
|
55 |
+
| 0.778 | 2.1 | 1029 | 1.4229 | 0.7240 |
|
56 |
+
| 0.7591 | 3.1 | 1372 | 1.5418 | 0.6918 |
|
57 |
+
| 0.8103 | 4.1 | 1715 | 1.3608 | 0.6810 |
|
58 |
+
| 0.3701 | 5.1 | 2058 | 1.6575 | 0.6810 |
|
59 |
+
| 0.2027 | 6.1 | 2401 | 1.8233 | 0.6774 |
|
60 |
+
| 0.0002 | 7.1 | 2744 | 1.9324 | 0.6738 |
|
61 |
+
| 0.1793 | 8.1 | 3087 | 1.8483 | 0.6953 |
|
62 |
+
| 0.0007 | 9.1 | 3430 | 1.8988 | 0.6953 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.42.4
|
68 |
+
- Pytorch 2.0.1+cu117
|
69 |
+
- Datasets 2.20.0
|
70 |
+
- Tokenizers 0.19.1
|