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-v2
results: []
finetuned-Accident-MultipleLabels-Video-subset-v2
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: 1.7815
- 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.08 | 4 | 2.0559 | 0.0156 |
| No log | 1.08 | 8 | 1.9961 | 0.1719 |
| 1.7392 | 2.08 | 12 | 2.1035 | 0.3594 |
| 1.7392 | 3.08 | 16 | 2.0893 | 0.3438 |
| 1.4679 | 4.08 | 20 | 2.0625 | 0.2031 |
| 1.4679 | 5.08 | 24 | 1.9845 | 0.3125 |
| 1.4679 | 6.08 | 28 | 1.9829 | 0.3125 |
| 1.3757 | 7.08 | 32 | 1.9941 | 0.3438 |
| 1.3757 | 8.08 | 36 | 2.0449 | 0.3125 |
| 1.2956 | 9.08 | 40 | 2.0877 | 0.3281 |
| 1.2956 | 10.08 | 44 | 2.1224 | 0.3281 |
| 1.2956 | 11.08 | 48 | 2.1418 | 0.3281 |
| 1.2352 | 12.04 | 50 | 2.1479 | 0.3281 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231202+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0