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
7135f86
•
1 Parent(s): 9c29ce0

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  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: 0.4622
21
- - Accuracy: 0.975
22
 
23
  ## Model description
24
 
@@ -44,33 +44,33 @@ The following hyperparameters were used during training:
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: 960
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 3.8796 | 0.06 | 60 | 3.6666 | 0.05 |
54
- | 3.8535 | 1.06 | 120 | 3.4913 | 0.05 |
55
- | 3.7537 | 2.06 | 180 | 3.3941 | 0.075 |
56
- | 3.5163 | 3.06 | 240 | 3.3433 | 0.075 |
57
- | 3.4903 | 4.06 | 300 | 3.2711 | 0.075 |
58
- | 3.4318 | 5.06 | 360 | 3.2221 | 0.1 |
59
- | 3.0782 | 6.06 | 420 | 3.1301 | 0.225 |
60
- | 3.3261 | 7.06 | 480 | 2.9363 | 0.475 |
61
- | 2.8341 | 8.06 | 540 | 2.5592 | 0.5 |
62
- | 2.4863 | 9.06 | 600 | 1.8678 | 0.8 |
63
- | 1.7275 | 10.06 | 660 | 1.2153 | 0.925 |
64
- | 1.2468 | 11.06 | 720 | 0.9454 | 0.95 |
65
- | 0.871 | 12.06 | 780 | 0.7030 | 0.975 |
66
- | 0.6857 | 13.06 | 840 | 0.5486 | 0.95 |
67
- | 0.6182 | 14.06 | 900 | 0.4743 | 1.0 |
68
- | 0.3517 | 15.06 | 960 | 0.4622 | 0.975 |
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
 
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: 0.4349
21
+ - Accuracy: 1.0
22
 
23
  ## Model description
24
 
 
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: 944
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 3.8217 | 0.06 | 59 | 3.7146 | 0.025 |
54
+ | 3.8922 | 1.06 | 118 | 3.6380 | 0.05 |
55
+ | 3.8685 | 2.06 | 177 | 3.5008 | 0.075 |
56
+ | 3.5993 | 3.06 | 236 | 3.3747 | 0.075 |
57
+ | 3.5955 | 4.06 | 295 | 3.3114 | 0.1 |
58
+ | 3.3868 | 5.06 | 354 | 3.2517 | 0.15 |
59
+ | 3.0407 | 6.06 | 413 | 3.1527 | 0.375 |
60
+ | 3.2339 | 7.06 | 472 | 2.9500 | 0.625 |
61
+ | 2.964 | 8.06 | 531 | 2.4629 | 0.6 |
62
+ | 2.6435 | 9.06 | 590 | 1.9360 | 0.875 |
63
+ | 1.8166 | 10.06 | 649 | 1.3224 | 0.925 |
64
+ | 1.5438 | 11.06 | 708 | 0.9461 | 0.925 |
65
+ | 1.0153 | 12.06 | 767 | 0.6873 | 1.0 |
66
+ | 0.8273 | 13.06 | 826 | 0.5575 | 1.0 |
67
+ | 0.5994 | 14.06 | 885 | 0.4687 | 0.975 |
68
+ | 0.5846 | 15.06 | 944 | 0.4349 | 1.0 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.34.0
74
  - Pytorch 2.0.1+cu118
75
  - Datasets 2.14.5
76
+ - Tokenizers 0.14.0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f98f0ad8e9a17d3850c0f8a7ed19e7cc5b0dccd932c3be70c36387251a5be9c1
3
  size 345095797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ebb94630389b94813232a99ae80560068bf7f5722eb9f927ac13b224530194
3
  size 345095797