Commit
·
0be83a5
1
Parent(s):
57261d5
update model card README.md
Browse files
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: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -44,14 +44,37 @@ The following hyperparameters were used during training:
|
|
| 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 |
-
|
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 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: 0.3585
|
| 21 |
+
- Accuracy: 0.9226
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 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: 3750
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 2.0046 | 0.04 | 150 | 2.0806 | 0.3143 |
|
| 54 |
+
| 1.9549 | 1.04 | 300 | 1.4746 | 0.5429 |
|
| 55 |
+
| 0.6873 | 2.04 | 450 | 0.9489 | 0.6714 |
|
| 56 |
+
| 1.6042 | 3.04 | 600 | 0.6865 | 0.7571 |
|
| 57 |
+
| 0.2082 | 4.04 | 750 | 0.4017 | 0.8857 |
|
| 58 |
+
| 0.2805 | 5.04 | 900 | 0.9705 | 0.7714 |
|
| 59 |
+
| 0.0062 | 6.04 | 1050 | 0.4833 | 0.8571 |
|
| 60 |
+
| 0.2727 | 7.04 | 1200 | 0.8048 | 0.8714 |
|
| 61 |
+
| 0.1055 | 8.04 | 1350 | 0.0264 | 0.9857 |
|
| 62 |
+
| 0.234 | 9.04 | 1500 | 0.1460 | 0.9714 |
|
| 63 |
+
| 0.0015 | 10.04 | 1650 | 0.3039 | 0.9429 |
|
| 64 |
+
| 0.0012 | 11.04 | 1800 | 0.2351 | 0.9571 |
|
| 65 |
+
| 0.0009 | 12.04 | 1950 | 0.3080 | 0.9286 |
|
| 66 |
+
| 0.0009 | 13.04 | 2100 | 0.3477 | 0.9429 |
|
| 67 |
+
| 0.036 | 14.04 | 2250 | 0.2366 | 0.9571 |
|
| 68 |
+
| 0.0008 | 15.04 | 2400 | 0.4506 | 0.9 |
|
| 69 |
+
| 0.0037 | 16.04 | 2550 | 0.2327 | 0.9571 |
|
| 70 |
+
| 0.0007 | 17.04 | 2700 | 0.3480 | 0.9286 |
|
| 71 |
+
| 0.0007 | 18.04 | 2850 | 0.1762 | 0.9714 |
|
| 72 |
+
| 0.0006 | 19.04 | 3000 | 0.0991 | 0.9714 |
|
| 73 |
+
| 0.0006 | 20.04 | 3150 | 0.1551 | 0.9714 |
|
| 74 |
+
| 0.0006 | 21.04 | 3300 | 0.3023 | 0.9429 |
|
| 75 |
+
| 0.0006 | 22.04 | 3450 | 0.1543 | 0.9571 |
|
| 76 |
+
| 0.0006 | 23.04 | 3600 | 0.1025 | 0.9571 |
|
| 77 |
+
| 0.0006 | 24.04 | 3750 | 0.0876 | 0.9571 |
|
| 78 |
|
| 79 |
|
| 80 |
### Framework versions
|