Hugging Face's logo

Shwifty
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
PyTorch
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
Shwifty commited on
Commit
4484bbd
•
1 Parent(s): 0cbc125

End of training

Browse files
Files changed (4) hide show
  1. README.md +0 -21
  2. config.json +0 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +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-ucf101-subset
10
  results: []
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
16
  # videomae-base-finetuned-ucf101-subset
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: 0.2770
21
- - Accuracy: 0.9571
22
 
23
  ## Model description
24
 
@@ -46,22 +41,6 @@ The following hyperparameters were used during training:
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - training_steps: 750
48
 
49
- ### Training results
50
-
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.3039 | 0.1 | 75 | 0.8843 | 0.7143 |
54
- | 0.1888 | 1.1 | 150 | 0.5760 | 0.8143 |
55
- | 0.5873 | 2.1 | 225 | 0.3869 | 0.9143 |
56
- | 0.0879 | 3.1 | 300 | 0.2451 | 0.9429 |
57
- | 0.1298 | 4.1 | 375 | 0.3045 | 0.9429 |
58
- | 0.0032 | 5.1 | 450 | 0.3903 | 0.9429 |
59
- | 0.0033 | 6.1 | 525 | 0.1547 | 0.9571 |
60
- | 0.0851 | 7.1 | 600 | 0.3233 | 0.9429 |
61
- | 0.0216 | 8.1 | 675 | 0.2714 | 0.9571 |
62
- | 0.0551 | 9.1 | 750 | 0.2770 | 0.9571 |
63
-
64
-
65
  ### Framework versions
66
 
67
  - Transformers 4.33.3
 
3
  base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: videomae-base-finetuned-ucf101-subset
8
  results: []
 
14
  # videomae-base-finetuned-ucf101-subset
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
 
18
  ## Model description
19
 
 
41
  - lr_scheduler_warmup_ratio: 0.1
42
  - training_steps: 750
43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  ### Framework versions
45
 
46
  - Transformers 4.33.3
config.json CHANGED
@@ -46,7 +46,6 @@
46
  "num_frames": 16,
47
  "num_hidden_layers": 12,
48
  "patch_size": 16,
49
- "problem_type": "single_label_classification",
50
  "qkv_bias": true,
51
  "torch_dtype": "float32",
52
  "transformers_version": "4.33.3",
 
46
  "num_frames": 16,
47
  "num_hidden_layers": 12,
48
  "patch_size": 16,
 
49
  "qkv_bias": true,
50
  "torch_dtype": "float32",
51
  "transformers_version": "4.33.3",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8a4df94a38237cc282a596d6b26bccde96e854ce58ecdbb08e8b9a6d95e4c0d
3
  size 345003509
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba349613420457ba70688cfbe7c0d2156c20f08148168904d48ac0b7c7efdd1
3
  size 345003509
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ead3da684b8f684f03aa0561823b400ba59e7b6b9d013823a194c75ca8c4508c
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d9b171b05b5bca4d88fcfe972751ad7415e1bfa2624a0b44aa018d07206289
3
  size 4091