<!-- 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. -->
dgx2_distil_w2v2_base_mozilla_12_to_6_batch_16_epoch_30
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 66.6618
- Wer: 0.9801
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 1024
- 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 |
|---|---|---|---|---|
| 1685.0568 | 1.1 | 150 | 31.2699 | 0.9782 |
| 224.147 | 2.2 | 300 | 17.6511 | 0.7425 |
| 147.425 | 3.31 | 450 | 14.1351 | 0.5397 |
| 128.1261 | 4.41 | 600 | 13.4210 | 0.5068 |
| 119.1109 | 5.51 | 750 | 12.9610 | 0.4787 |
| 127.7067 | 6.61 | 900 | 15.1543 | 0.5724 |
| 289.179 | 7.72 | 1050 | 64.2107 | 0.9746 |
| 343.3656 | 8.82 | 1200 | 41.4259 | 0.9738 |
| 371.938 | 9.92 | 1350 | 59.4227 | 0.9766 |
| 482.1259 | 11.03 | 1500 | 66.6618 | 0.9801 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
