Hugging Face's logo

kojex
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kojex commited on
Commit
d597e26
·
verified ·
1 Parent(s): 855422e

End of training

Browse files
Files changed (2) hide show
  1. README.md +9 -14
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2673
21
- - Accuracy: 0.9
22
 
23
  ## Model description
24
 
@@ -38,27 +38,22 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
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: 90
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 1.3462 | 0.1111 | 10 | 1.3265 | 0.5286 |
54
- | 0.8487 | 1.1111 | 20 | 0.9102 | 0.6714 |
55
- | 0.5164 | 2.1111 | 30 | 0.6970 | 0.7571 |
56
- | 0.3456 | 3.1111 | 40 | 0.4381 | 0.8714 |
57
- | 0.2549 | 4.1111 | 50 | 0.6148 | 0.7571 |
58
- | 0.1676 | 5.1111 | 60 | 0.4580 | 0.7571 |
59
- | 0.1241 | 6.1111 | 70 | 0.3453 | 0.8286 |
60
- | 0.082 | 7.1111 | 80 | 0.2994 | 0.8714 |
61
- | 0.0666 | 8.1111 | 90 | 0.2673 | 0.9 |
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7252
21
+ - Accuracy: 0.5714
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
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: 52
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.7861 | 0.2692 | 14 | 0.7792 | 0.5714 |
54
+ | 0.7229 | 1.2692 | 28 | 0.7375 | 0.5429 |
55
+ | 0.7061 | 2.2692 | 42 | 0.7304 | 0.4571 |
56
+ | 0.6506 | 3.1923 | 52 | 0.7252 | 0.5714 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6c82097441b9058a2b7b0d1a44b025c6722e7af977be7b906165c81b68b9fc0
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb24cfd17a81747fe7fbfccb51a3676edba61c913ac7c60be05c6e3f9165fc9e
3
  size 344937368