Steve Chiou
commited on
Commit
•
b10190c
1
Parent(s):
b6b54f9
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-finetuned-engine-subset-20230310
|
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-finetuned-engine-subset-20230310
|
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: 0.4958
|
20 |
+
- Accuracy: 0.85
|
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: 6
|
41 |
+
- eval_batch_size: 6
|
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: 600
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 2.5947 | 0.05 | 31 | 2.5383 | 0.15 |
|
53 |
+
| 2.4195 | 1.05 | 62 | 2.5108 | 0.15 |
|
54 |
+
| 2.2476 | 2.05 | 93 | 2.0533 | 0.225 |
|
55 |
+
| 1.9449 | 3.05 | 124 | 2.0719 | 0.2375 |
|
56 |
+
| 1.5724 | 4.05 | 155 | 1.4756 | 0.475 |
|
57 |
+
| 1.395 | 5.05 | 186 | 1.2884 | 0.5 |
|
58 |
+
| 1.0822 | 6.05 | 217 | 1.0679 | 0.575 |
|
59 |
+
| 1.0635 | 7.05 | 248 | 0.8040 | 0.7 |
|
60 |
+
| 0.8707 | 8.05 | 279 | 0.9334 | 0.525 |
|
61 |
+
| 0.7042 | 9.05 | 310 | 0.6477 | 0.75 |
|
62 |
+
| 0.6543 | 10.05 | 341 | 0.6963 | 0.7375 |
|
63 |
+
| 0.6807 | 11.05 | 372 | 0.4958 | 0.85 |
|
64 |
+
| 0.4924 | 12.05 | 403 | 0.6374 | 0.775 |
|
65 |
+
| 0.4822 | 13.05 | 434 | 0.6145 | 0.75 |
|
66 |
+
| 0.4878 | 14.05 | 465 | 0.6274 | 0.7625 |
|
67 |
+
| 0.4442 | 15.05 | 496 | 0.4231 | 0.85 |
|
68 |
+
| 0.2739 | 16.05 | 527 | 0.4999 | 0.85 |
|
69 |
+
| 0.3514 | 17.05 | 558 | 0.4639 | 0.8375 |
|
70 |
+
| 0.4158 | 18.05 | 589 | 0.4291 | 0.85 |
|
71 |
+
| 0.2689 | 19.02 | 600 | 0.4294 | 0.85 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.26.1
|
77 |
+
- Pytorch 1.12.1+cu113
|
78 |
+
- Datasets 2.10.1
|
79 |
+
- Tokenizers 0.13.2
|