metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-IEMOCAP_2
results: []
videomae-base-finetuned-IEMOCAP_2
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: 1.3381
- Accuracy: 0.3434
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: 4500
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3215 | 0.1 | 451 | 1.4351 | 0.2622 |
| 1.3236 | 1.1 | 902 | 1.3517 | 0.3579 |
| 1.2642 | 2.1 | 1353 | 1.4280 | 0.2982 |
| 1.2741 | 3.1 | 1804 | 1.3943 | 0.3012 |
| 1.2655 | 4.1 | 2255 | 1.3665 | 0.3311 |
| 1.1476 | 5.1 | 2706 | 1.3808 | 0.3293 |
| 1.2231 | 6.1 | 3157 | 1.3216 | 0.3573 |
| 1.2715 | 7.1 | 3608 | 1.3162 | 0.3720 |
| 1.3088 | 8.1 | 4059 | 1.2985 | 0.3982 |
| 1.2636 | 9.1 | 4500 | 1.2666 | 0.4098 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3