metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_model
results: []
my_model
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: 2.6403
- Accuracy: 0.0672
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 |
|---|---|---|---|---|
| 2.6453 | 1.0 | 30 | 2.6434 | 0.0336 |
| 2.6503 | 2.0 | 60 | 2.6434 | 0.0840 |
| 2.649 | 3.0 | 90 | 2.6506 | 0.0588 |
| 2.6433 | 4.0 | 120 | 2.6488 | 0.0924 |
| 2.6252 | 5.0 | 150 | 2.6514 | 0.1008 |
| 2.6123 | 6.0 | 180 | 2.6542 | 0.0840 |
| 2.6167 | 7.0 | 210 | 2.6520 | 0.0840 |
| 2.6051 | 8.0 | 240 | 2.6461 | 0.0588 |
| 2.5975 | 9.0 | 270 | 2.6402 | 0.1345 |
| 2.5809 | 10.0 | 300 | 2.6403 | 0.0672 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0