<!-- 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. -->
dgx1_distil_w2v2_base_mozilla_12_to_6_batch_16_epoch_20
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 26.8431
- Wer: 0.3778
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
465.0357 | 2.2 | 150 | 27.3961 | 0.4137 |
425.0158 | 4.41 | 300 | 27.1168 | 0.4018 |
388.6065 | 6.61 | 450 | 26.7368 | 0.3952 |
366.0589 | 8.82 | 600 | 26.3986 | 0.3879 |
353.06 | 11.03 | 750 | 26.5929 | 0.3836 |
339.4883 | 13.23 | 900 | 26.8030 | 0.3800 |
337.4981 | 15.44 | 1050 | 26.7429 | 0.3786 |
331.5542 | 17.64 | 1200 | 26.7569 | 0.3783 |
327.284 | 19.85 | 1350 | 26.8431 | 0.3778 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2