Hugging Face's logo

archit11
/
videomae-base-finetuned-ucfcrime-full

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
vandalism
ucf-crime
vandalism-dectection
Inference Endpoints
Model card Files Metrics Community
1
archit11 commited on
Commit
4ddcb94
•
1 Parent(s): f306d3a

Model save

Browse files
Files changed (4) hide show
  1. README.md +12 -8
  2. model.safetensors +1 -1
  3. runs/Mar17_19-35-48_500f3adbbe43/events.out.tfevents.1710704166.500f3adbbe43.26.0 +2 -2
  4. runs/Mar17_19-35-48_500f3adbbe43/events.out.tfevents.1710729400.500f3adbbe43.26.1 +3 -0
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: 2.6882
21
- - Accuracy: 0.1173
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-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
@@ -50,10 +50,14 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 2.6564 | 0.25 | 175 | 2.5464 | 0.1719 |
54
- | 2.3285 | 1.25 | 350 | 2.8665 | 0.1255 |
55
- | 2.3545 | 2.25 | 525 | 2.7751 | 0.1353 |
56
- | 1.9726 | 3.25 | 700 | 2.5616 | 0.1840 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
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: 2.5014
21
+ - Accuracy: 0.225
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 2.5836 | 0.13 | 88 | 2.4944 | 0.2080 |
54
+ | 2.3212 | 1.13 | 176 | 2.5855 | 0.1773 |
55
+ | 2.2333 | 2.13 | 264 | 2.6270 | 0.1046 |
56
+ | 1.985 | 3.13 | 352 | 2.4058 | 0.2109 |
57
+ | 2.194 | 4.13 | 440 | 2.3654 | 0.2235 |
58
+ | 1.9796 | 5.13 | 528 | 2.2609 | 0.2235 |
59
+ | 1.8786 | 6.13 | 616 | 2.2725 | 0.2341 |
60
+ | 1.71 | 7.12 | 700 | 2.2228 | 0.2226 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16393022887c4d68acece3a89e8c8f46139ef6c77500bf15d4b4a46d68a1d1c8
3
  size 344974288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba99a3d4164208683bae69f90dcb21a6f194eb50428952f3f6b6defcc9dcf5ae
3
  size 344974288
runs/Mar17_19-35-48_500f3adbbe43/events.out.tfevents.1710704166.500f3adbbe43.26.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d953fd7e4bed42875e0599f96d810175e8d9b7ca86fa0053835d434dbefed4
3
- size 22729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aba03293798fe33df829e845341c9d300fc66a2e6a4e8f13ce8f35f241097df
3
+ size 23083
runs/Mar17_19-35-48_500f3adbbe43/events.out.tfevents.1710729400.500f3adbbe43.26.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1b342a8b2c6d00ac8c36a307ac47d42b946637655330563b51a955a801c871
3
+ size 411