Model save
Browse files- README.md +14 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
-
base_model: MCG-NJU/videomae-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# violence_detection
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [MCG-NJU/videomae-large
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -42,15 +42,23 @@ The following hyperparameters were used during training:
|
|
| 42 |
- total_train_batch_size: 8
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
-
- num_epochs:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
-
| No log | 1.0 | 35 | 0.
|
| 53 |
-
| No log | 2.0 | 70 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
base_model: MCG-NJU/videomae-large
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# violence_detection
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7861
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 42 |
- total_train_batch_size: 8
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 10
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| No log | 1.0 | 35 | 0.8953 |
|
| 53 |
+
| No log | 2.0 | 70 | 0.8102 |
|
| 54 |
+
| No log | 3.0 | 105 | 0.5775 |
|
| 55 |
+
| No log | 4.0 | 140 | 0.6276 |
|
| 56 |
+
| No log | 5.0 | 175 | 0.6347 |
|
| 57 |
+
| No log | 6.0 | 210 | 0.5628 |
|
| 58 |
+
| No log | 7.0 | 245 | 0.7472 |
|
| 59 |
+
| No log | 8.0 | 280 | 0.5381 |
|
| 60 |
+
| No log | 9.0 | 315 | 0.6392 |
|
| 61 |
+
| No log | 10.0 | 350 | 0.7861 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1215496248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb1b746355d14b0c7441bd918a71b4add7925e8a6f7ef8b3bba61e2439fb81e1
|
| 3 |
size 1215496248
|