metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned-Accident-MultipleLabels-Video-subset
results: []
finetuned-Accident-MultipleLabels-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: 2.0208
- Accuracy: 0.2593
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: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9193 | 0.08 | 16 | 1.9108 | 0.2344 |
| 1.4025 | 1.08 | 32 | 2.0975 | 0.1094 |
| 1.5413 | 2.08 | 48 | 2.0303 | 0.2969 |
| 1.4147 | 3.08 | 64 | 2.3447 | 0.2969 |
| 1.3804 | 4.08 | 80 | 2.4733 | 0.0469 |
| 1.3687 | 5.08 | 96 | 2.4051 | 0.3438 |
| 1.2929 | 6.08 | 112 | 2.3691 | 0.3125 |
| 1.1661 | 7.08 | 128 | 2.6412 | 0.1875 |
| 1.2024 | 8.08 | 144 | 2.6427 | 0.3125 |
| 1.0824 | 9.08 | 160 | 2.7478 | 0.3594 |
| 1.1011 | 10.08 | 176 | 2.7789 | 0.3594 |
| 0.9492 | 11.08 | 192 | 2.7706 | 0.3281 |
| 1.1232 | 12.04 | 200 | 2.7944 | 0.2969 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1