metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: finetuning-xlsr-53-PSST_V7
results: []
finetuning-xlsr-53-PSST_V7
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4691
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.5902 | 4.1 | 400 | 3.5931 |
| 2.8519 | 8.21 | 800 | 1.6398 |
| 1.3002 | 12.31 | 1200 | 1.3060 |
| 0.7496 | 16.41 | 1600 | 1.2790 |
| 0.5284 | 20.51 | 2000 | 1.3452 |
| 0.3743 | 24.62 | 2400 | 1.3639 |
| 0.2814 | 28.72 | 2800 | 1.4691 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3