metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: run_20250121_121944
results: []
run_20250121_121944
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: 1.9678
- Accuracy: 0.5676
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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 22
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5043 | 2.7200 | 34 | 0.9872 | 0.6757 |
| 0.4196 | 5.44 | 68 | 0.9670 | 0.6486 |
| 0.3056 | 8.16 | 102 | 1.2386 | 0.5946 |
| 0.2666 | 10.88 | 136 | 1.3272 | 0.5676 |
| 0.1761 | 13.6 | 170 | 1.5065 | 0.5946 |
| 0.1485 | 16.32 | 204 | 1.9727 | 0.5405 |
| 0.1022 | 19.04 | 238 | 1.9678 | 0.5676 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3