videomae-base-fatigue-detection-full
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7131
- Accuracy: 0.5080
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: 2457.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0402 | 0.08 | 200 | 1.2844 | 0.4647 |
0.0003 | 0.16 | 400 | 1.6560 | 0.4692 |
0.0001 | 0.24 | 600 | 2.0519 | 0.4510 |
0.0001 | 0.33 | 800 | 1.6676 | 0.4396 |
0.0001 | 1.07 | 1000 | 2.1058 | 0.4305 |
0.0001 | 1.15 | 1200 | 2.1659 | 0.4419 |
0.0 | 1.24 | 1400 | 2.2195 | 0.4374 |
0.0 | 1.32 | 1600 | 2.3093 | 0.4351 |
0.0013 | 2.07 | 1800 | 2.1501 | 0.5604 |
0.0 | 2.15 | 2000 | 2.2250 | 0.5148 |
0.0 | 2.23 | 2200 | 2.6678 | 0.5330 |
0.0 | 2.31 | 2400 | 2.7131 | 0.5080 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 119
Model state unknown