hubert-base-libri-pruning-FINAL-TEST2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1261
- Wer: 0.1114
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0609 | 1.12 | 500 | 0.1243 | 0.1111 |
0.0579 | 2.24 | 1000 | 0.1242 | 0.1112 |
0.0557 | 3.36 | 1500 | 0.1237 | 0.1112 |
0.0582 | 4.48 | 2000 | 0.1242 | 0.1112 |
0.0507 | 5.61 | 2500 | 0.1247 | 0.1112 |
0.0451 | 6.73 | 3000 | 0.1251 | 0.1113 |
0.0472 | 7.85 | 3500 | 0.1256 | 0.1114 |
0.048 | 8.97 | 4000 | 0.1261 | 0.1114 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1
- Datasets 2.12.1.dev0
- Tokenizers 0.13.3
- Downloads last month
- 1