|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: videomae-base-finetuned-IEMOCAP_videos |
|
|
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_videos |
|
|
|
|
|
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: 1.3194 |
|
|
- Accuracy: 0.3761 |
|
|
|
|
|
## 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: 4070 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 1.4161 | 0.1 | 408 | 1.4228 | 0.2115 | |
|
|
| 1.3522 | 1.1 | 816 | 1.3968 | 0.2363 | |
|
|
| 1.2575 | 2.1 | 1224 | 1.4228 | 0.3115 | |
|
|
| 1.2897 | 3.1 | 1632 | 1.4101 | 0.2984 | |
|
|
| 1.3398 | 4.1 | 2040 | 1.4176 | 0.2599 | |
|
|
| 1.3621 | 5.1 | 2448 | 1.3590 | 0.2830 | |
|
|
| 1.2824 | 6.1 | 2856 | 1.3133 | 0.3610 | |
|
|
| 1.3064 | 7.1 | 3264 | 1.3195 | 0.3077 | |
|
|
| 1.378 | 8.1 | 3672 | 1.3562 | 0.2643 | |
|
|
| 1.1909 | 9.1 | 4070 | 1.3917 | 0.2621 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.29.1 |
|
|
- Pytorch 2.0.0+cu118 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
