<!-- 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. -->
gmra_model_distilbert-base-uncased-distilled-squad_17082023T161354
This model is a fine-tuned version of distilbert-base-uncased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4850
- Accuracy: 93.06%
- F1: 0.9487
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 284 | 0.2984 | 91.92% | 0.9357 |
| 0.1624 | 2.0 | 568 | 0.3141 | 92.79% | 0.9401 |
| 0.1624 | 3.0 | 852 | 0.3593 | 93.15% | 0.9480 |
| 0.0634 | 4.0 | 1137 | 0.4000 | 92.97% | 0.9484 |
| 0.0634 | 5.0 | 1421 | 0.4545 | 92.71% | 0.9469 |
| 0.0222 | 6.0 | 1705 | 0.4625 | 93.59% | 0.9527 |
| 0.0222 | 7.0 | 1989 | 0.4649 | 93.41% | 0.9510 |
| 0.0085 | 8.0 | 2274 | 0.4772 | 93.06% | 0.9485 |
| 0.0055 | 9.0 | 2558 | 0.4848 | 93.15% | 0.9493 |
| 0.0055 | 9.99 | 2840 | 0.4850 | 93.06% | 0.9487 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.2
