output
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9947
- Cer: 0.4133
- Wer: 0.6195
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: 0.0006
- train_batch_size: 16
- eval_batch_size: 16
- seed: 300
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
---|---|---|---|---|---|
1.5851 | 1.6 | 1000 | 1.9947 | 0.4133 | 0.6195 |
1.8352 | 3.2 | 2000 | 2.1491 | 0.4724 | 0.7895 |
2.3755 | 4.8 | 3000 | 2.3793 | 0.4433 | 0.7270 |
3.3134 | 6.4 | 4000 | 3.3025 | 0.5204 | 0.8033 |
3.4098 | 8.0 | 5000 | 3.2885 | 0.5196 | 0.8050 |
3.1155 | 9.6 | 6000 | 3.2885 | 0.5196 | 0.8050 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4