Hugging Face's logo

skywalker290
/
videomae-videomae-d1

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
skywalker290 commited on
Commit
ae1f650
·
verified ·
1 Parent(s): a2195df

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -9
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.8458
22
- - Accuracy: 0.7364
23
 
24
  ## Model description
25
 
@@ -39,23 +39,27 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
- - train_batch_size: 10
43
- - eval_batch_size: 10
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - training_steps: 480
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 0.5803 | 0.2521 | 121 | 0.8145 | 0.6059 |
56
- | 0.4256 | 1.2521 | 242 | 0.8485 | 0.6580 |
57
- | 0.3913 | 2.2521 | 363 | 0.9005 | 0.7110 |
58
- | 0.3751 | 3.2437 | 480 | 0.8458 | 0.7364 |
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.1903
22
+ - Accuracy: 0.7335
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
+ - train_batch_size: 5
43
+ - eval_batch_size: 5
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 1920
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 0.5817 | 0.1255 | 241 | 0.6961 | 0.6601 |
56
+ | 0.4524 | 1.1255 | 482 | 1.1878 | 0.6009 |
57
+ | 0.5473 | 2.1255 | 723 | 1.0509 | 0.6420 |
58
+ | 0.5044 | 3.1255 | 964 | 1.0045 | 0.6745 |
59
+ | 0.7258 | 4.1255 | 1205 | 0.9840 | 0.6567 |
60
+ | 0.3606 | 5.1255 | 1446 | 1.0898 | 0.7377 |
61
+ | 0.2423 | 6.1255 | 1687 | 1.0520 | 0.7460 |
62
+ | 0.3488 | 7.1214 | 1920 | 1.1903 | 0.7335 |
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:067bf018ea599074f5d4933586edce3f2b30af93820d628e57c9a8bdedbda51d
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07257f09f897adf954aaad25ead86a552ea1bcbe17c6bbf6180e390c8d963dd8
3
  size 344937368