Model save
Browse files- README.md +24 -11
- pytorch_model.bin +1 -1
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:
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,26 +38,39 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
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:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
-
| 3.
|
54 |
-
| 3.
|
55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
-
- Transformers 4.33.
|
61 |
-
- Pytorch 2.0.
|
62 |
-
- Datasets 2.
|
63 |
- Tokenizers 0.13.3
|
|
|
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: 0.3056
|
21 |
+
- Accuracy: 0.9767
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 2
|
42 |
+
- eval_batch_size: 2
|
43 |
- seed: 42
|
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: 1008
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 3.8889 | 0.06 | 64 | 3.6733 | 0.0465 |
|
54 |
+
| 3.8474 | 1.06 | 128 | 3.7358 | 0.0698 |
|
55 |
+
| 3.7886 | 2.06 | 192 | 3.6336 | 0.0465 |
|
56 |
+
| 3.7398 | 3.06 | 256 | 3.5894 | 0.0698 |
|
57 |
+
| 3.7363 | 4.06 | 320 | 3.4637 | 0.0698 |
|
58 |
+
| 3.6345 | 5.06 | 384 | 3.3875 | 0.0698 |
|
59 |
+
| 3.2723 | 6.06 | 448 | 3.2156 | 0.1163 |
|
60 |
+
| 3.2814 | 7.06 | 512 | 2.7291 | 0.7209 |
|
61 |
+
| 2.7245 | 8.06 | 576 | 1.9657 | 0.8140 |
|
62 |
+
| 1.8616 | 9.06 | 640 | 1.2883 | 0.8837 |
|
63 |
+
| 1.3802 | 10.06 | 704 | 0.8116 | 0.9302 |
|
64 |
+
| 1.0416 | 11.06 | 768 | 0.5877 | 0.9535 |
|
65 |
+
| 0.6415 | 12.06 | 832 | 0.4426 | 0.9767 |
|
66 |
+
| 0.5546 | 13.06 | 896 | 0.3599 | 0.9767 |
|
67 |
+
| 0.4495 | 14.06 | 960 | 0.3212 | 0.9767 |
|
68 |
+
| 0.2214 | 15.05 | 1008 | 0.3056 | 0.9767 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
72 |
|
73 |
+
- Transformers 4.33.3
|
74 |
+
- Pytorch 2.0.1+cu118
|
75 |
+
- Datasets 2.14.5
|
76 |
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 345095797
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b929f104a664145e55f979102135b77a2ca6d2dd7d7bc342fcf06846184af860
|
3 |
size 345095797
|