<!-- 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. -->
Nystrom-W2V2-100hrs-take-2
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 26.8554
- Wer: 0.1392
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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
1090.0902 | 4.5 | 1000 | 54.4575 | 0.4841 |
307.7589 | 9.01 | 2000 | 29.7460 | 0.2633 |
170.6373 | 13.51 | 3000 | 25.5445 | 0.1984 |
113.7445 | 18.02 | 4000 | 24.8862 | 0.1696 |
78.7363 | 22.52 | 5000 | 25.9566 | 0.1494 |
59.5531 | 27.03 | 6000 | 26.8554 | 0.1392 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.11.0