Hugging Face's logo

josesantorcuato
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
josesantorcuato commited on
Commit
f029b5d
·
verified ·
1 Parent(s): 6901ffd

Model save

Browse files
Files changed (4) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
  3. runs/Oct29_20-22-21_7c56bb07786b/events.out.tfevents.1730233360.7c56bb07786b.46717.0 +2 -2
  4. runs/Oct29_20-22-21_7c56bb07786b/events.out.tfevents.1730234240.7c56bb07786b.46717.1 +3 -0
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: 0.3301
22
- - Accuracy: 0.8689
23
 
24
  ## Model description
25
 
@@ -45,22 +45,22 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - training_steps: 530
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
- | 2.4559 | 0.1019 | 54 | 2.3856 | 0.2024 |
55
- | 1.7637 | 1.1019 | 108 | 1.5237 | 0.5 |
56
- | 0.8196 | 2.1019 | 162 | 0.9368 | 0.5952 |
57
- | 0.6174 | 3.1019 | 216 | 0.5995 | 0.7738 |
58
- | 0.3827 | 4.1019 | 270 | 0.5287 | 0.8214 |
59
- | 0.3031 | 5.1019 | 324 | 0.2036 | 0.9286 |
60
- | 0.0844 | 6.1019 | 378 | 0.3585 | 0.8333 |
61
- | 0.0299 | 7.1019 | 432 | 0.1888 | 0.9167 |
62
- | 0.0835 | 8.1019 | 486 | 0.0911 | 0.9881 |
63
- | 0.0798 | 9.0830 | 530 | 0.0995 | 0.9762 |
64
 
65
 
66
  ### Framework versions
 
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: 0.1620
22
+ - Accuracy: 0.9618
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 460
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 2.2403 | 0.1022 | 47 | 2.2387 | 0.1364 |
55
+ | 1.2918 | 1.1022 | 94 | 1.3612 | 0.5152 |
56
+ | 0.8662 | 2.1022 | 141 | 0.8152 | 0.7424 |
57
+ | 0.6072 | 3.1022 | 188 | 0.3968 | 0.8939 |
58
+ | 0.2958 | 4.1022 | 235 | 0.3365 | 0.8788 |
59
+ | 0.1534 | 5.1022 | 282 | 0.2506 | 0.9242 |
60
+ | 0.0907 | 6.1022 | 329 | 0.1101 | 0.9848 |
61
+ | 0.1085 | 7.1022 | 376 | 0.1033 | 0.9545 |
62
+ | 0.0666 | 8.1022 | 423 | 0.1031 | 0.9697 |
63
+ | 0.0251 | 9.0804 | 460 | 0.1119 | 0.9697 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd7a95304d28674a3bccf264411a9148e6389bacbf38823127893791bfabac6e
3
  size 344968136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbb5f6c19d9356273e856abd7f42e2d9da3768decbccd8afc784fbe9b4b3dfd
3
  size 344968136
runs/Oct29_20-22-21_7c56bb07786b/events.out.tfevents.1730233360.7c56bb07786b.46717.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05b8ef2f45d859ec6158a43b2a99808e60e03c2271439852273ba9e6d1186637
3
- size 18247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206f2eb01651d1ffd1f14461961827fa70b62230edd9f62febb089b3a36c1a20
3
+ size 18924
runs/Oct29_20-22-21_7c56bb07786b/events.out.tfevents.1730234240.7c56bb07786b.46717.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb4f6437df2b77386f3957338c87e1e8b3ba01150cccd948a8369e14e4689d2
3
+ size 411