<!-- 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. -->
canine_vowelizer_2105_v6
This model is a fine-tuned version of google/canine-s on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1704
- Precision: 0.9998
- Recall: 0.9998
- F1: 0.9998
- Accuracy: 0.9391
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4826 | 1.0 | 3885 | 0.4310 | 0.9997 | 0.9998 | 0.9997 | 0.8467 |
| 0.4118 | 2.0 | 7770 | 0.3556 | 0.9997 | 0.9998 | 0.9997 | 0.8748 |
| 0.369 | 3.0 | 11655 | 0.3126 | 0.9997 | 0.9998 | 0.9997 | 0.8893 |
| 0.339 | 4.0 | 15540 | 0.2811 | 0.9997 | 0.9998 | 0.9998 | 0.9014 |
| 0.3192 | 5.0 | 19425 | 0.2589 | 0.9997 | 0.9998 | 0.9998 | 0.9095 |
| 0.3052 | 6.0 | 23310 | 0.2399 | 0.9997 | 0.9998 | 0.9998 | 0.9157 |
| 0.281 | 7.0 | 27195 | 0.2252 | 0.9997 | 0.9998 | 0.9998 | 0.9207 |
| 0.2749 | 8.0 | 31080 | 0.2117 | 0.9998 | 0.9998 | 0.9998 | 0.9248 |
| 0.2589 | 9.0 | 34965 | 0.2011 | 0.9998 | 0.9998 | 0.9998 | 0.9285 |
| 0.253 | 10.0 | 38850 | 0.1940 | 0.9998 | 0.9998 | 0.9998 | 0.9314 |
| 0.2428 | 11.0 | 42735 | 0.1842 | 0.9998 | 0.9998 | 0.9998 | 0.9348 |
| 0.2433 | 12.0 | 46620 | 0.1783 | 0.9998 | 0.9998 | 0.9998 | 0.9365 |
| 0.2265 | 13.0 | 50505 | 0.1751 | 0.9998 | 0.9998 | 0.9998 | 0.9375 |
| 0.2244 | 14.0 | 54390 | 0.1721 | 0.9998 | 0.9998 | 0.9998 | 0.9387 |
| 0.2203 | 15.0 | 58275 | 0.1704 | 0.9998 | 0.9998 | 0.9998 | 0.9391 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
