Hugging Face's logo

asmaa1
/
videomae-base-finetuned-SLT-subset

Video Classification
Transformers
PyTorch
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
asmaa1 commited on
Commit
872140f
•
1 Parent(s): a0b52ac

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -11
  2. pytorch_model.bin +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: 2.8449
21
- - Accuracy: 0.2
22
 
23
  ## Model description
24
 
@@ -38,26 +38,39 @@ More information needed
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: 60
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 3.4023 | 0.33 | 20 | 2.9551 | 0.1 |
54
- | 3.209 | 1.33 | 40 | 2.9234 | 0.1 |
55
- | 2.9811 | 2.33 | 60 | 2.8449 | 0.2 |
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
59
 
60
- - Transformers 4.33.0
61
- - Pytorch 2.0.0
62
- - Datasets 2.1.0
63
  - Tokenizers 0.13.3
 
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: 0.3551
21
+ - Accuracy: 1.0
22
 
23
  ## Model description
24
 
 
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: 992
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 3.9682 | 0.06 | 63 | 3.6880 | 0.0233 |
54
+ | 3.9178 | 1.06 | 126 | 3.7027 | 0.0465 |
55
+ | 3.849 | 2.06 | 189 | 3.6568 | 0.0465 |
56
+ | 3.8048 | 3.06 | 252 | 3.6098 | 0.0698 |
57
+ | 3.7667 | 4.06 | 315 | 3.5407 | 0.0930 |
58
+ | 3.5213 | 5.06 | 378 | 3.4482 | 0.0930 |
59
+ | 3.4635 | 6.06 | 441 | 3.4000 | 0.1163 |
60
+ | 3.4635 | 7.06 | 504 | 3.3042 | 0.1628 |
61
+ | 3.227 | 8.06 | 567 | 2.9691 | 0.2791 |
62
+ | 3.1302 | 9.06 | 630 | 2.2268 | 0.6512 |
63
+ | 2.4687 | 10.06 | 693 | 1.4347 | 0.9070 |
64
+ | 1.4134 | 11.06 | 756 | 0.9489 | 0.9302 |
65
+ | 0.8296 | 12.06 | 819 | 0.6633 | 0.9302 |
66
+ | 0.775 | 13.06 | 882 | 0.4595 | 0.9767 |
67
+ | 0.2714 | 14.06 | 945 | 0.3763 | 1.0 |
68
+ | 0.5427 | 15.05 | 992 | 0.3551 | 1.0 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.33.3
74
+ - Pytorch 2.0.1+cu118
75
+ - Datasets 2.14.5
76
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ade49e2c121a924681981aeae51792b53edad7b1d357560fbf550b38cde74b
3
  size 345095797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddc3e3eac663d0ca7d478944f60d13d8e06c1ef8de19520d1711d6f7c1909f1
3
  size 345095797