Hugging Face's logo

Beybars
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Beybars commited on
Commit
2d16dde
·
1 Parent(s): 0dbe9d0

Model save

Browse files
Files changed (3) hide show
  1. README.md +13 -9
  2. model.safetensors +1 -1
  3. runs/Jan06_19-59-38_44017.example.com/events.out.tfevents.1704568368.44017.example.com +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: 0.2867
21
- - Accuracy: 0.8903
22
 
23
  ## Model description
24
 
@@ -44,21 +44,25 @@ The following hyperparameters were used during training:
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: 300
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.9487 | 0.25 | 75 | 1.7081 | 0.3286 |
54
- | 0.9701 | 1.25 | 150 | 0.5870 | 0.8286 |
55
- | 0.3204 | 2.25 | 225 | 0.3160 | 0.8571 |
56
- | 0.2186 | 3.25 | 300 | 0.1952 | 0.9429 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 4.35.2
62
- - Pytorch 2.1.0+cu121
63
  - Datasets 2.16.1
64
  - Tokenizers 0.15.0
 
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: 0.2061
21
+ - Accuracy: 0.9484
22
 
23
  ## Model description
24
 
 
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: 600
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.9543 | 0.12 | 75 | 1.5145 | 0.6 |
54
+ | 0.7175 | 1.12 | 150 | 0.9735 | 0.6571 |
55
+ | 0.2914 | 2.12 | 225 | 0.4764 | 0.8 |
56
+ | 0.54 | 3.12 | 300 | 0.6036 | 0.8 |
57
+ | 0.1074 | 4.12 | 375 | 0.1995 | 0.9286 |
58
+ | 0.0087 | 5.12 | 450 | 0.1256 | 0.9714 |
59
+ | 0.0061 | 6.12 | 525 | 0.0466 | 0.9857 |
60
+ | 0.0082 | 7.12 | 600 | 0.0363 | 0.9857 |
61
 
62
 
63
  ### Framework versions
64
 
65
+ - Transformers 4.36.2
66
+ - Pytorch 2.1.2+cu121
67
  - Datasets 2.16.1
68
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:548d3722cb00730ecdc48c3eeff4850cfa745e0a2e4d464c26b789ec403087e8
3
  size 344961984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ebbf7d2c5081c4f32a9db6782b096f13f47f21bd47f28c39a16aee4513e944
3
  size 344961984
runs/Jan06_19-59-38_44017.example.com/events.out.tfevents.1704568368.44017.example.com ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2641582fc62085c8ee894b429fd9f4732affaa8f40a8594e3131b4f4338fa14e
3
+ size 40