Hugging Face's logo

Joy28
/
videomae-base-finetuned-subset-check10

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
Joy28 commited on
Commit
ecf2ef4
·
verified ·
1 Parent(s): 26bb03d

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ license: cc-by-nc-4.0
3
  base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - accuracy
8
  model-index:
9
  - name: videomae-base-finetuned-subset-check10
10
  results: []
@@ -17,8 +15,13 @@ 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: 0.9676
21
- - Accuracy: 0.6296
 
 
 
 
 
22
 
23
  ## Model description
24
 
@@ -38,33 +41,17 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 4
42
- - eval_batch_size: 4
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: 1110
48
-
49
- ### Training results
50
-
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.6046 | 0.1 | 112 | 1.5695 | 0.2581 |
54
- | 1.5968 | 1.1 | 224 | 1.5343 | 0.3502 |
55
- | 1.4175 | 2.1 | 336 | 1.4348 | 0.3088 |
56
- | 1.2801 | 3.1 | 448 | 0.9527 | 0.6774 |
57
- | 1.1862 | 4.1 | 560 | 1.1452 | 0.5253 |
58
- | 1.1711 | 5.1 | 672 | 0.9195 | 0.6959 |
59
- | 1.0642 | 6.1 | 784 | 0.9303 | 0.6636 |
60
- | 1.2081 | 7.1 | 896 | 1.0957 | 0.5714 |
61
- | 0.9326 | 8.1 | 1008 | 0.9903 | 0.6774 |
62
- | 0.9876 | 9.09 | 1110 | 0.9823 | 0.6820 |
63
-
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.36.2
68
- - Pytorch 1.13.1
69
  - Datasets 2.16.1
70
  - Tokenizers 0.15.0
 
3
  base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: videomae-base-finetuned-subset-check10
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 1.3321
19
+ - eval_accuracy: 0.6111
20
+ - eval_runtime: 168.011
21
+ - eval_samples_per_second: 1.286
22
+ - eval_steps_per_second: 0.161
23
+ - epoch: 96.01
24
+ - step: 5426
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - training_steps: 5550
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
  ### Framework versions
53
 
54
  - Transformers 4.36.2
55
+ - Pytorch 2.1.1
56
  - Datasets 2.16.1
57
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f0abc375b0cc3437b1d2cce772146675801cc3cab1d20c34aaf842b7d5023ec
3
  size 344946604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39892d56222618498a6c48d8f155c0479a85575bee2abcfc43910a1e03427705
3
  size 344946604