Hugging Face's logo

yauk
/
videomae-base-finetuned-ucfsuc-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yauk commited on
Commit
81a7bb0
·
verified ·
1 Parent(s): cd3d8b6

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. runs/Dec06_11-52-02_28168986a9e3/events.out.tfevents.1733485940.28168986a9e3.304.0 +2 -2
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: 0.0098
22
- - Accuracy: 1.0
23
 
24
  ## Model description
25
 
@@ -45,27 +45,27 @@ The following hyperparameters were used during training:
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: 170
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
- | 0.6733 | 0.1059 | 18 | 0.5553 | 0.8213 |
55
- | 0.6044 | 1.1059 | 36 | 0.4723 | 0.8488 |
56
- | 0.4479 | 2.1059 | 54 | 0.5580 | 0.8574 |
57
- | 0.5565 | 3.1059 | 72 | 0.1609 | 0.9175 |
58
- | 0.4652 | 4.1059 | 90 | 0.1305 | 0.9399 |
59
- | 0.4022 | 5.1059 | 108 | 0.1216 | 0.9433 |
60
- | 0.2586 | 6.1059 | 126 | 0.0411 | 0.9845 |
61
- | 0.4183 | 7.1059 | 144 | 0.0139 | 1.0 |
62
- | 0.2282 | 8.1059 | 162 | 0.0201 | 0.9948 |
63
- | 0.0072 | 9.0471 | 170 | 0.0098 | 1.0 |
64
 
65
 
66
  ### Framework versions
67
 
68
- - Transformers 4.46.2
69
  - Pytorch 2.5.1+cu121
70
  - Datasets 3.1.0
71
  - Tokenizers 0.20.3
 
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: 0.6334
22
+ - Accuracy: 0.7079
23
 
24
  ## Model description
25
 
 
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: 310
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 0.7131 | 0.1032 | 32 | 0.7573 | 0.3596 |
55
+ | 0.7351 | 1.1032 | 64 | 0.6929 | 0.5393 |
56
+ | 0.6892 | 2.1032 | 96 | 0.7539 | 0.5393 |
57
+ | 0.693 | 3.1032 | 128 | 0.7079 | 0.5169 |
58
+ | 0.5903 | 4.1032 | 160 | 0.7080 | 0.6180 |
59
+ | 0.626 | 5.1032 | 192 | 0.6610 | 0.6854 |
60
+ | 0.6316 | 6.1032 | 224 | 0.5789 | 0.7303 |
61
+ | 0.5287 | 7.1032 | 256 | 0.6366 | 0.7079 |
62
+ | 0.6648 | 8.1032 | 288 | 0.6215 | 0.7191 |
63
+ | 0.4605 | 9.0710 | 310 | 0.6334 | 0.7079 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.46.3
69
  - Pytorch 2.5.1+cu121
70
  - Datasets 3.1.0
71
  - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab3804da7f066e7b2e11bbcd74e7fa7702db105941a8f541f6aa097a0a0fb341
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda57a8537a0015a300c43e0c65b1fb4a3e631f4df155c7b3862662175ca1cf6
3
  size 344937368
runs/Dec06_11-52-02_28168986a9e3/events.out.tfevents.1733485940.28168986a9e3.304.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:907ed0c01a581bddcd576926a5eb0cf044bc7d55ebd68c14e6f33a11cffb4858
3
- size 15070
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af608f52473f170a922ba3417954285545a57d1fa7d80814f0941e6ef4f90b03
3
+ size 15424