<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
finetune_teacher_clean_mozilla_200_epochs
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 51.1994
- Wer: 0.2767
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 200
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
192.4936 | 29.41 | 1000 | 31.6902 | 0.3122 |
123.9408 | 58.82 | 2000 | 36.2166 | 0.3028 |
87.1469 | 88.23 | 3000 | 43.5998 | 0.3144 |
62.0674 | 117.64 | 4000 | 44.5869 | 0.2944 |
44.2649 | 147.06 | 5000 | 47.9859 | 0.2825 |
33.7306 | 176.47 | 6000 | 51.1994 | 0.2767 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2