metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-videomae-asl
results: []
videomae-base-videomae-asl
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: 0.2106
- Accuracy: 0.9375
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: 8
- eval_batch_size: 8
- 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: 720
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7142 | 0.12 | 90 | 1.7574 | 0.2 |
| 1.2973 | 1.12 | 180 | 1.0885 | 0.625 |
| 0.7412 | 2.12 | 270 | 0.3997 | 0.9 |
| 0.3196 | 3.12 | 360 | 0.3584 | 0.8875 |
| 0.3123 | 4.12 | 450 | 0.3616 | 0.8875 |
| 0.1454 | 5.12 | 540 | 0.3104 | 0.925 |
| 0.237 | 6.12 | 630 | 0.1316 | 0.95 |
| 0.1447 | 7.12 | 720 | 0.2106 | 0.9375 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2