|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: MCG-NJU/videomae-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-IEMOCAP_1xx |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# videomae-base-finetuned-IEMOCAP_1xx |
|
|
|
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co./MCG-NJU/videomae-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.2253 |
|
- Accuracy: 0.3303 |
|
|
|
## 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: 4440 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.2487 | 0.1 | 445 | 1.5638 | 0.3912 | |
|
| 0.6787 | 1.1 | 890 | 1.1789 | 0.4877 | |
|
| 0.7851 | 2.1 | 1335 | 0.9786 | 0.5811 | |
|
| 0.3104 | 3.1 | 1780 | 1.1209 | 0.6273 | |
|
| 0.5358 | 4.1 | 2225 | 0.8696 | 0.7084 | |
|
| 0.3483 | 5.1 | 2670 | 1.0214 | 0.7084 | |
|
| 0.3458 | 6.1 | 3115 | 1.0766 | 0.7125 | |
|
| 0.2962 | 7.1 | 3560 | 1.2876 | 0.7351 | |
|
| 0.0641 | 8.1 | 4005 | 1.3037 | 0.7382 | |
|
| 0.0131 | 9.1 | 4440 | 1.3754 | 0.7474 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 1.12.0+cu116 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
