Hugging Face's logo

bluebird089
/
videomae-base-finetuned-kinetics-finetuned-round2

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bluebird089 commited on
Commit
3626d94
•
1 Parent(s): ac6ec9a

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. runs/Mar15_13-30-49_9c6513a9bc4c/events.out.tfevents.1710509468.9c6513a9bc4c.2057.0 +2 -2
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-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5973
21
- - Accuracy: 0.8505
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
  - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 42
@@ -50,17 +50,17 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.0176 | 0.09 | 165 | 1.0811 | 0.6766 |
54
- | 0.3557 | 1.09 | 330 | 0.8774 | 0.7402 |
55
- | 0.5484 | 2.09 | 495 | 0.5486 | 0.8019 |
56
- | 0.0925 | 3.09 | 660 | 0.7637 | 0.8112 |
57
- | 0.0086 | 4.09 | 825 | 0.6512 | 0.8355 |
58
- | 0.0011 | 5.09 | 990 | 0.5377 | 0.8673 |
59
- | 0.0012 | 6.09 | 1155 | 0.5820 | 0.8579 |
60
- | 0.0007 | 7.09 | 1320 | 0.4911 | 0.8579 |
61
- | 0.0008 | 8.09 | 1485 | 0.5254 | 0.8542 |
62
- | 0.0006 | 9.09 | 1650 | 0.5867 | 0.8542 |
63
- | 0.0006 | 10.09 | 1804 | 0.5973 | 0.8505 |
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4130
21
+ - Accuracy: 0.8846
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 9e-05
41
  - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.7036 | 0.09 | 165 | 1.0471 | 0.7005 |
54
+ | 0.4684 | 1.09 | 330 | 0.5678 | 0.8214 |
55
+ | 0.4301 | 2.09 | 495 | 0.7029 | 0.7857 |
56
+ | 0.1361 | 3.09 | 660 | 0.4828 | 0.8599 |
57
+ | 0.0118 | 4.09 | 825 | 0.5531 | 0.8324 |
58
+ | 0.0721 | 5.09 | 990 | 0.3536 | 0.8956 |
59
+ | 0.001 | 6.09 | 1155 | 0.4194 | 0.8929 |
60
+ | 0.0017 | 7.09 | 1320 | 0.3476 | 0.9038 |
61
+ | 0.0007 | 8.09 | 1485 | 0.4356 | 0.8819 |
62
+ | 0.0008 | 9.09 | 1650 | 0.4232 | 0.8874 |
63
+ | 0.0007 | 10.09 | 1804 | 0.4130 | 0.8846 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:485c4eaad05d922ff6a133782c61b24fd09ea84afeebbc8ca0fae723716ba5f6
3
  size 344998856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75aa0311eb979c51ab317fb2003347eef896e35977e66fbd259ede43e06dc593
3
  size 344998856
runs/Mar15_13-30-49_9c6513a9bc4c/events.out.tfevents.1710509468.9c6513a9bc4c.2057.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab2eda8620abb04ded32c15a8618cbb8d5f0080f00a325836b9b18438b9f53b
3
- size 47391
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963730ddadca0e19171bc9d803b1460dab5d06aa77024c4a8c40d190d406d433
3
+ size 47745