metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: w_small_lv_70_norm
results: []
w_small_lv_70_norm
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6392
- Wer: 55.8512
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: 1e-05
- train_batch_size: 16
- 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: 500
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6903 | 0.7184 | 1000 | 0.6575 | 62.6997 |
| 0.449 | 1.4368 | 2000 | 0.6212 | 64.2444 |
| 0.3108 | 2.1552 | 3000 | 0.6157 | 71.5088 |
| 0.293 | 2.8736 | 4000 | 0.6116 | 61.7210 |
| 0.2093 | 3.5920 | 5000 | 0.6392 | 55.8512 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu118
- Datasets 3.0.0
- Tokenizers 0.19.1