<!-- 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-3-unfreeze-extractor
This model is a fine-tuned version of rohitp1/Nystrom-W2V2-100hrs-take-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 29.1951
- Wer: 0.1183
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: 32
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
123.0399 | 37.04 | 1000 | 27.2466 | 0.1448 |
89.1443 | 74.07 | 2000 | 29.1951 | 0.1183 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2