|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: sridhar1ga/speech_emotion_is25 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: speech_emotion_is25 |
|
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. --> |
|
|
|
# speech_emotion_is25 |
|
|
|
This model is a fine-tuned version of [sridhar1ga/speech_emotion_is25](https://huggingface.co/sridhar1ga/speech_emotion_is25) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- F1: 0.1507 |
|
- Loss: 1.9786 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | F1 | Validation Loss | |
|
|:-------------:|:------:|:----:|:------:|:---------------:| |
|
| 8.3207 | 1.0 | 73 | 0.0288 | 2.0793 | |
|
| 8.3072 | 2.0 | 146 | 0.0379 | 2.0790 | |
|
| 8.2824 | 3.0 | 219 | 0.1134 | 2.0707 | |
|
| 8.178 | 4.0 | 292 | 0.1204 | 2.0244 | |
|
| 8.0941 | 5.0 | 365 | 0.1380 | 2.0037 | |
|
| 8.0498 | 6.0 | 438 | 0.1395 | 1.9927 | |
|
| 7.9997 | 7.0 | 511 | 0.1379 | 1.9860 | |
|
| 7.9315 | 8.0 | 584 | 0.1485 | 1.9829 | |
|
| 7.9988 | 9.0 | 657 | 0.1464 | 1.9797 | |
|
| 7.9838 | 9.8690 | 720 | 0.1507 | 1.9786 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
