<!-- 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. -->
mobilebert-uncased-squad-v2-qa
This model is a fine-tuned version of badokorach/mobilebert-uncased-squad-v2-qa on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0681
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 265 | 2.3277 |
| 2.6476 | 2.0 | 530 | 2.1362 |
| 2.6476 | 3.0 | 795 | 1.9784 |
| 2.3668 | 4.0 | 1060 | 1.7966 |
| 2.3668 | 5.0 | 1325 | 1.7200 |
| 2.0871 | 6.0 | 1590 | 1.5585 |
| 2.0871 | 7.0 | 1855 | 1.3859 |
| 1.9018 | 8.0 | 2120 | 1.2941 |
| 1.9018 | 9.0 | 2385 | 1.2245 |
| 1.6963 | 10.0 | 2650 | 1.1069 |
| 1.6963 | 11.0 | 2915 | 0.9504 |
| 1.5186 | 12.0 | 3180 | 0.8660 |
| 1.5186 | 13.0 | 3445 | 0.8664 |
| 1.3707 | 14.0 | 3710 | 0.6955 |
| 1.3707 | 15.0 | 3975 | 0.6217 |
| 1.2402 | 16.0 | 4240 | 0.5880 |
| 1.0937 | 17.0 | 4505 | 0.5604 |
| 1.0937 | 18.0 | 4770 | 0.4484 |
| 0.9468 | 19.0 | 5035 | 0.3988 |
| 0.9468 | 20.0 | 5300 | 0.3981 |
| 0.8648 | 21.0 | 5565 | 0.3145 |
| 0.8648 | 22.0 | 5830 | 0.3053 |
| 0.7644 | 23.0 | 6095 | 0.2580 |
| 0.7644 | 24.0 | 6360 | 0.2741 |
| 0.6697 | 25.0 | 6625 | 0.2122 |
| 0.6697 | 26.0 | 6890 | 0.1946 |
| 0.6188 | 27.0 | 7155 | 0.1915 |
| 0.6188 | 28.0 | 7420 | 0.1550 |
| 0.5341 | 29.0 | 7685 | 0.1430 |
| 0.5341 | 30.0 | 7950 | 0.1287 |
| 0.4874 | 31.0 | 8215 | 0.1250 |
| 0.4874 | 32.0 | 8480 | 0.0994 |
| 0.4516 | 33.0 | 8745 | 0.0955 |
| 0.4164 | 34.0 | 9010 | 0.0890 |
| 0.4164 | 35.0 | 9275 | 0.0838 |
| 0.3864 | 36.0 | 9540 | 0.0796 |
| 0.3864 | 37.0 | 9805 | 0.0766 |
| 0.353 | 38.0 | 10070 | 0.0788 |
| 0.353 | 39.0 | 10335 | 0.0711 |
| 0.3331 | 40.0 | 10600 | 0.0681 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
