<!-- 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. -->
m11_msl_1
This model is a fine-tuned version of Sjdan/m11_main on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0947
- Wer: 1.7712
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.6701 | 0.96 | 500 | 0.1058 | 1.7988 |
0.1484 | 1.92 | 1000 | 0.1113 | 1.8185 |
0.1373 | 2.88 | 1500 | 0.1140 | 1.8639 |
0.1006 | 3.84 | 2000 | 0.1136 | 1.6607 |
0.0625 | 4.8 | 2500 | 0.1023 | 1.8087 |
0.0442 | 5.76 | 3000 | 0.0932 | 1.7830 |
0.0305 | 6.72 | 3500 | 0.0947 | 1.7712 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2