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-SLT-subset
results: []
videomae-base-finetuned-SLT-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: 1.0411
- Accuracy: 1.0
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: 944
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9695 | 0.06 | 59 | 3.6889 | 0.05 |
| 3.898 | 1.06 | 118 | 3.6205 | 0.05 |
| 3.6781 | 2.06 | 177 | 3.4775 | 0.075 |
| 3.4169 | 3.06 | 236 | 3.3709 | 0.075 |
| 3.6405 | 4.06 | 295 | 3.3190 | 0.075 |
| 3.5568 | 5.06 | 354 | 3.3243 | 0.075 |
| 3.3347 | 6.06 | 413 | 3.2671 | 0.175 |
| 3.3946 | 7.06 | 472 | 3.2436 | 0.15 |
| 3.2943 | 8.06 | 531 | 3.2095 | 0.25 |
| 3.4037 | 9.06 | 590 | 3.1415 | 0.35 |
| 3.3753 | 10.06 | 649 | 2.9745 | 0.7 |
| 3.2246 | 11.06 | 708 | 2.5009 | 0.65 |
| 2.4989 | 12.06 | 767 | 1.8618 | 0.8 |
| 1.905 | 13.06 | 826 | 1.4972 | 0.9 |
| 1.7084 | 14.06 | 885 | 1.1309 | 1.0 |
| 1.2838 | 15.06 | 944 | 1.0411 | 1.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0