metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audio_cls
results: []
audio_cls
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6549
- Accuracy: 0.0336
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.639 | 1.0 | 30 | 2.6473 | 0.0504 |
| 2.6399 | 2.0 | 60 | 2.6481 | 0.0672 |
| 2.6514 | 3.0 | 90 | 2.6458 | 0.0588 |
| 2.6384 | 4.0 | 120 | 2.6581 | 0.0336 |
| 2.6289 | 5.0 | 150 | 2.6557 | 0.0336 |
| 2.6308 | 6.0 | 180 | 2.6607 | 0.0252 |
| 2.643 | 7.0 | 210 | 2.6600 | 0.0336 |
| 2.648 | 8.0 | 240 | 2.6641 | 0.0336 |
| 2.6333 | 9.0 | 270 | 2.6596 | 0.0336 |
| 2.6289 | 10.0 | 300 | 2.6549 | 0.0336 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0