metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: wavlm-large-finetuned-iemocap
results: []
wavlm-large-finetuned-iemocap
This model is a fine-tuned version of microsoft/wavlm-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1588
- Accuracy: 0.4811
- F1: 0.4602
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.3733 | 0.98 | 25 | 1.3723 | 0.2502 | 0.1002 |
| 1.2784 | 1.98 | 50 | 1.3130 | 0.3307 | 0.2503 |
| 1.2228 | 2.98 | 75 | 1.2485 | 0.3899 | 0.3398 |
| 1.1588 | 3.98 | 100 | 1.2129 | 0.4646 | 0.4650 |
| 1.1116 | 4.98 | 125 | 1.1941 | 0.4753 | 0.4655 |
| 1.1212 | 5.98 | 150 | 1.1688 | 0.4762 | 0.4639 |
| 1.0919 | 6.98 | 175 | 1.1574 | 0.4850 | 0.4710 |
| 1.0749 | 7.98 | 200 | 1.1612 | 0.4840 | 0.4639 |
| 1.0943 | 8.98 | 225 | 1.1586 | 0.4888 | 0.4677 |
| 1.0746 | 9.98 | 250 | 1.1588 | 0.4811 | 0.4602 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2