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
0706443
•
1 Parent(s): f108a0a

Model save

Browse files
Files changed (4) hide show
  1. README.md +15 -15
  2. model.safetensors +1 -1
  3. runs/Nov05_16-00-57_612d7c91d57a/events.out.tfevents.1730822606.612d7c91d57a.6074.0 +2 -2
  4. runs/Nov05_16-00-57_612d7c91d57a/events.out.tfevents.1730823607.612d7c91d57a.6074.1 +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: 1.1455
22
- - Accuracy: 0.5714
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: 160
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
- |:-------------:|:------:|:----:|:---------------:|:--------:|
54
- | 1.4262 | 0.1062 | 17 | 1.4081 | 0.3571 |
55
- | 1.3918 | 1.1062 | 34 | 1.5798 | 0.2143 |
56
- | 1.2887 | 2.1063 | 51 | 1.3649 | 0.5 |
57
- | 1.3115 | 3.1063 | 68 | 1.4629 | 0.4286 |
58
- | 1.0533 | 4.1063 | 85 | 1.5869 | 0.2857 |
59
- | 0.9616 | 5.1063 | 102 | 1.7206 | 0.3571 |
60
- | 0.9531 | 6.1063 | 119 | 1.4406 | 0.3571 |
61
- | 0.6531 | 7.1063 | 136 | 1.3292 | 0.5 |
62
- | 0.5778 | 8.1062 | 153 | 1.1212 | 0.6429 |
63
- | 0.4835 | 9.0437 | 160 | 1.1138 | 0.5714 |
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: 0.7852
22
+ - Accuracy: 0.7857
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: 380
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.3762 | 0.1 | 38 | 1.4490 | 0.2857 |
55
+ | 1.2421 | 1.1 | 76 | 1.3190 | 0.4286 |
56
+ | 0.8753 | 2.1 | 114 | 0.9506 | 0.5714 |
57
+ | 0.4285 | 3.1 | 152 | 0.5580 | 0.7857 |
58
+ | 0.3808 | 4.1 | 190 | 0.4951 | 0.8571 |
59
+ | 0.1368 | 5.1 | 228 | 0.1578 | 0.9286 |
60
+ | 0.043 | 6.1 | 266 | 0.0475 | 1.0 |
61
+ | 0.0842 | 7.1 | 304 | 0.0624 | 1.0 |
62
+ | 0.003 | 8.1 | 342 | 0.0557 | 1.0 |
63
+ | 0.0828 | 9.1 | 380 | 0.0446 | 1.0 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4915afc32579c62ca3e784ec5b5d0ae05b780370c1cb313df004d4856dab2d96
3
  size 344943528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727735e124443f0b4784d51ed95ecd6cb8159edf1a337c376a66c14bbec27391
3
  size 344943528
runs/Nov05_16-00-57_612d7c91d57a/events.out.tfevents.1730822606.612d7c91d57a.6074.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6e29b5c6fd08ecbd394e996bbf7742b1fd424e420ff7a3b735f53ad51025022
3
- size 15313
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc4ac57e5478dd0934c5d921b8491cf2c99a352e9a44a32164d5e1afb893d86
3
+ size 16834
runs/Nov05_16-00-57_612d7c91d57a/events.out.tfevents.1730823607.612d7c91d57a.6074.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d359571268aea4298fa123d2911dfe48b114ebeacb8c3d0a542358a79411841c
3
+ size 411