Hugging Face's logo

koya1
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
PyTorch
TensorBoard
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
koya1 commited on
Commit
bb4cc26
•
1 Parent(s): 1cb0bcb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -13
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.6198
20
- - Accuracy: 0.7886
21
 
22
  ## Model description
23
 
@@ -43,22 +43,23 @@ The following hyperparameters were used during training:
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: 3650
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 1.1996 | 0.1 | 365 | 2.4460 | 0.5567 |
53
- | 1.4174 | 1.1 | 730 | 0.6252 | 0.8041 |
54
- | 0.0092 | 2.1 | 1095 | 1.2255 | 0.7629 |
55
- | 0.765 | 3.1 | 1460 | 0.9238 | 0.7732 |
56
- | 0.1714 | 4.1 | 1825 | 1.0449 | 0.7938 |
57
- | 0.09 | 5.1 | 2190 | 1.4747 | 0.7629 |
58
- | 0.0006 | 6.1 | 2555 | 1.3157 | 0.7835 |
59
- | 0.0004 | 7.1 | 2920 | 1.6183 | 0.7216 |
60
- | 0.0012 | 8.1 | 3285 | 1.5373 | 0.7732 |
61
- | 0.0005 | 9.1 | 3650 | 1.6775 | 0.7629 |
 
62
 
63
 
64
  ### Framework versions
 
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: 0.8124
20
+ - Accuracy: 0.8324
21
 
22
  ## Model description
23
 
 
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: 3990
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 2.1012 | 0.1 | 398 | 1.9809 | 0.38 |
53
+ | 1.0416 | 1.1 | 796 | 1.6140 | 0.56 |
54
+ | 0.2096 | 2.1 | 1194 | 1.5776 | 0.66 |
55
+ | 0.7101 | 3.1 | 1592 | 1.2004 | 0.74 |
56
+ | 1.2344 | 4.1 | 1990 | 1.9621 | 0.58 |
57
+ | 0.1809 | 5.1 | 2388 | 1.6322 | 0.71 |
58
+ | 0.0011 | 6.1 | 2786 | 1.8266 | 0.71 |
59
+ | 0.0951 | 7.1 | 3184 | 1.5910 | 0.78 |
60
+ | 0.4047 | 8.1 | 3582 | 1.9999 | 0.7 |
61
+ | 0.0011 | 9.1 | 3980 | 1.5903 | 0.78 |
62
+ | 0.001 | 10.0 | 3990 | 1.5903 | 0.78 |
63
 
64
 
65
  ### Framework versions