Hugging Face's logo

asmaa1
/
videomae-base-groub13-14-finetuned-SLT-subset

Video Classification
Transformers
PyTorch
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
asmaa1 commited on
Commit
f2dd940
·
1 Parent(s): e063882

Model save

Browse files
Files changed (1) hide show
  1. README.md +21 -14
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: 3.2580
21
- - Accuracy: 0.5
22
 
23
  ## Model description
24
 
@@ -44,25 +44,32 @@ 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: 80
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 3.8748 | 0.12 | 10 | 3.6846 | 0.05 |
54
- | 3.7799 | 1.12 | 20 | 3.6477 | 0.025 |
55
- | 3.7271 | 2.12 | 30 | 3.6026 | 0.075 |
56
- | 3.6374 | 3.12 | 40 | 3.5275 | 0.125 |
57
- | 3.5356 | 4.12 | 50 | 3.4335 | 0.2 |
58
- | 3.4315 | 5.12 | 60 | 3.3521 | 0.35 |
59
- | 3.3418 | 6.12 | 70 | 3.2853 | 0.375 |
60
- | 3.254 | 7.12 | 80 | 3.2580 | 0.5 |
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
64
 
65
- - Transformers 4.33.0
66
- - Pytorch 2.0.0+cpu
67
- - Datasets 2.1.0
68
  - 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: 0.9463
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: 224
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 3.0689 | 0.07 | 15 | 2.9460 | 0.1 |
54
+ | 3.1203 | 1.07 | 30 | 2.7839 | 0.15 |
55
+ | 2.8375 | 2.07 | 45 | 2.6131 | 0.2 |
56
+ | 2.619 | 3.07 | 60 | 2.5076 | 0.2 |
57
+ | 2.455 | 4.07 | 75 | 2.4382 | 0.15 |
58
+ | 2.4831 | 5.07 | 90 | 2.3911 | 0.25 |
59
+ | 2.5183 | 6.07 | 105 | 2.3353 | 0.3 |
60
+ | 2.4267 | 7.07 | 120 | 2.2589 | 0.35 |
61
+ | 2.257 | 8.07 | 135 | 2.1845 | 0.4 |
62
+ | 2.1795 | 9.07 | 150 | 2.0329 | 0.6 |
63
+ | 1.9706 | 10.07 | 165 | 1.7614 | 0.9 |
64
+ | 1.7866 | 11.07 | 180 | 1.4249 | 0.95 |
65
+ | 1.4293 | 12.07 | 195 | 1.1991 | 0.9 |
66
+ | 0.9984 | 13.07 | 210 | 1.0114 | 0.95 |
67
+ | 0.9409 | 14.06 | 224 | 0.9463 | 1.0 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.33.3
73
+ - Pytorch 2.0.1+cu118
74
+ - Datasets 2.14.5
75
  - Tokenizers 0.13.3