Commit
•
1ac8a1b
1
Parent(s):
2a7f245
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,43 @@ datasets:
|
|
| 7 |
|
| 8 |
A model trained for language classification. Thanks to @sanchit-gandhi for [this code](https://huggingface.co/sanchit-gandhi/whisper-base-ft-common-language-id) which was used to train the model.
|
| 9 |
|
| 10 |
-
This model was trained for 15 epochs.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
A model trained for language classification. Thanks to @sanchit-gandhi for [this code](https://huggingface.co/sanchit-gandhi/whisper-base-ft-common-language-id) which was used to train the model.
|
| 9 |
|
| 10 |
+
This model was trained for 15 epochs.
|
| 11 |
+
|
| 12 |
+
## Evaluation
|
| 13 |
+
|
| 14 |
+
It achieves the following results on the evaluation set:
|
| 15 |
+
- Loss: 1.1229
|
| 16 |
+
- Accuracy: 0.7401
|
| 17 |
+
|
| 18 |
+
## Hyperparameters
|
| 19 |
+
|
| 20 |
+
The following hyperparameters were used during training:
|
| 21 |
+
- learning_rate: 1e-05
|
| 22 |
+
- train_batch_size: 64
|
| 23 |
+
- eval_batch_size: 16
|
| 24 |
+
- seed: 0
|
| 25 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 26 |
+
- lr_scheduler_type: linear
|
| 27 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 28 |
+
- num_epochs: 15.0
|
| 29 |
+
- mixed_precision_training: Native AMP
|
| 30 |
+
|
| 31 |
+
## Training Results
|
| 32 |
+
|
| 33 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 34 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 35 |
+
| 3.1638 | 1.0 | 347 | 3.0152 | 0.4200 |
|
| 36 |
+
| 2.0788 | 2.0 | 694 | 1.9700 | 0.5504 |
|
| 37 |
+
| 1.4236 | 3.0 | 1041 | 1.5048 | 0.6374 |
|
| 38 |
+
| 1.0305 | 4.0 | 1388 | 1.2979 | 0.6685 |
|
| 39 |
+
| 0.7651 | 5.0 | 1735 | 1.1692 | 0.7023 |
|
| 40 |
+
| 0.5782 | 6.0 | 2082 | 1.0896 | 0.7227 |
|
| 41 |
+
| 0.4483 | 7.0 | 2429 | 1.0605 | 0.7198 |
|
| 42 |
+
| 0.3253 | 8.0 | 2776 | 1.0255 | 0.7376 |
|
| 43 |
+
| 0.2589 | 9.0 | 3123 | 1.0478 | 0.7354 |
|
| 44 |
+
| 0.1825 | 10.0 | 3470 | 1.0677 | 0.7318 |
|
| 45 |
+
| 0.1489 | 11.0 | 3817 | 1.0946 | 0.7373 |
|
| 46 |
+
| 0.1274 | 12.0 | 4164 | 1.1180 | 0.7376 |
|
| 47 |
+
| 0.1074 | 13.0 | 4511 | 1.1229 | 0.7401 |
|
| 48 |
+
| 0.0979 | 14.0 | 4858 | 1.1523 | 0.7383 |
|
| 49 |
+
| 0.0914 | 15.0 | 5205 | 1.1498 | 0.7401 |
|