<!-- 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. -->
model-baru-collab-4
This model is a fine-tuned version of zarko1231/model-baru-collab-3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0326
- Wer: 0.3423
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: 50
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 100
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.9939 | 1.0 | 26 | 3.3198 | 1.0039 |
| 3.019 | 2.0 | 52 | 2.7545 | 1.0039 |
| 2.4572 | 3.0 | 78 | 1.7117 | 1.0587 |
| 1.3597 | 4.0 | 104 | 0.5751 | 1.0185 |
| 0.6395 | 5.0 | 130 | 0.2423 | 0.7125 |
| 0.3831 | 6.0 | 156 | 0.1320 | 0.5572 |
| 0.3083 | 7.0 | 182 | 0.0855 | 0.4575 |
| 0.2039 | 8.0 | 208 | 0.0603 | 0.3941 |
| 0.1589 | 9.0 | 234 | 0.0487 | 0.3787 |
| 0.2031 | 10.0 | 260 | 0.0442 | 0.3794 |
| 0.1396 | 11.0 | 286 | 0.0406 | 0.3655 |
| 0.1612 | 12.0 | 312 | 0.0390 | 0.3532 |
| 0.1285 | 13.0 | 338 | 0.0373 | 0.3509 |
| 0.1355 | 14.0 | 364 | 0.0356 | 0.3532 |
| 0.1527 | 15.0 | 390 | 0.0352 | 0.3478 |
| 0.1207 | 16.0 | 416 | 0.0339 | 0.3470 |
| 0.1106 | 17.0 | 442 | 0.0332 | 0.3462 |
| 0.1243 | 18.0 | 468 | 0.0332 | 0.3447 |
| 0.1107 | 19.0 | 494 | 0.0328 | 0.3447 |
| 0.0986 | 20.0 | 520 | 0.0326 | 0.3423 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
