---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-IEMOCAP_1
  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_1

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: 1.3409
- Accuracy: 0.3480

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.35          | 0.1   | 445  | 1.4144          | 0.2478   |
| 1.3944        | 1.1   | 890  | 1.3677          | 0.3340   |
| 1.2676        | 2.1   | 1335 | 1.3613          | 0.3434   |
| 1.2343        | 3.1   | 1780 | 1.3674          | 0.3289   |
| 1.222         | 4.1   | 2225 | 1.3379          | 0.3522   |
| 1.3494        | 5.1   | 2670 | 1.3466          | 0.3421   |
| 1.2836        | 6.1   | 3115 | 1.3277          | 0.3591   |
| 1.226         | 7.1   | 3560 | 1.3132          | 0.3704   |
| 1.3174        | 8.1   | 4005 | 1.3001          | 0.3604   |
| 1.2933        | 9.1   | 4440 | 1.2912          | 0.3629   |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3