ronias commited on
Commit
c8a606c
1 Parent(s): abcc8e6

End of training

Browse files
Files changed (1) hide show
  1. README.md +8 -10
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: 0.2787
21
- - Accuracy: 0.9286
22
 
23
  ## Model description
24
 
@@ -45,21 +45,19 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - training_steps: 1200
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.9197 | 0.25 | 300 | 1.8284 | 0.3286 |
55
- | 0.5231 | 1.25 | 600 | 0.5825 | 0.7286 |
56
- | 0.1344 | 2.25 | 900 | 0.5880 | 0.8143 |
57
- | 0.5295 | 3.25 | 1200 | 0.2787 | 0.9286 |
58
 
59
 
60
  ### Framework versions
61
 
62
- - Transformers 4.40.1
63
- - Pytorch 2.0.1+cu117
64
- - Datasets 2.19.1
65
  - Tokenizers 0.19.1
 
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: 0.5973
21
+ - Accuracy: 0.8286
22
 
23
  ## Model description
24
 
 
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - training_steps: 1200
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.8559 | 0.25 | 300 | 0.9768 | 0.6286 |
54
+ | 1.3879 | 1.25 | 600 | 1.3276 | 0.5857 |
55
+ | 0.3694 | 2.25 | 900 | 1.2342 | 0.7 |
56
+ | 1.0305 | 3.25 | 1200 | 0.5973 | 0.8286 |
57
 
58
 
59
  ### Framework versions
60
 
61
+ - Transformers 4.40.2
62
+ - Pytorch 2.2.1+cu121
 
63
  - Tokenizers 0.19.1