finetuned-Accident-Video-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0765
- Accuracy: 0.5161
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 90
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5898 | 0.13 | 12 | 1.3173 | 0.48 |
| 1.2104 | 1.13 | 24 | 1.2157 | 0.4 |
| 1.418 | 2.13 | 36 | 1.1617 | 0.52 |
| 1.1202 | 3.13 | 48 | 1.1279 | 0.52 |
| 1.2226 | 4.13 | 60 | 1.1111 | 0.48 |
| 1.1886 | 5.13 | 72 | 1.0728 | 0.48 |
| 1.0177 | 6.13 | 84 | 1.0453 | 0.56 |
| 1.0443 | 7.07 | 90 | 1.0378 | 0.56 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for pavitemple/finetuned-Accident-Video-subset
Base model
MCG-NJU/videomae-base