metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-Risky-situations
results: []
videomae-base-finetuned-Risky-situations
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: 0.1588
- Accuracy: 0.9565
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: 2
- eval_batch_size: 2
- 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: 1040
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.42 | 0.1010 | 105 | 1.1518 | 0.6957 |
| 0.4222 | 1.1010 | 210 | 2.0082 | 0.6196 |
| 0.8311 | 2.1010 | 315 | 0.1588 | 0.9565 |
| 0.2905 | 3.1010 | 420 | 0.3990 | 0.9239 |
| 0.0003 | 4.1010 | 525 | 0.5733 | 0.9130 |
| 0.0015 | 5.1010 | 630 | 0.3354 | 0.9565 |
| 0.1905 | 6.1010 | 735 | 0.3576 | 0.9565 |
| 0.0001 | 7.1010 | 840 | 0.3462 | 0.9457 |
| 0.0001 | 8.1010 | 945 | 0.3043 | 0.9565 |
| 0.0001 | 9.0913 | 1040 | 0.3424 | 0.9565 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1