bert-squad2
This model is a fine-tuned version of SpanBERT/spanbert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9506
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5815 | 0.0394 | 100 | 1.1717 |
| 1.1525 | 0.0788 | 200 | 1.1207 |
| 1.1214 | 0.1182 | 300 | 1.1106 |
| 1.1132 | 0.1576 | 400 | 1.1067 |
| 1.1205 | 0.1970 | 500 | 1.1044 |
| 3.7006 | 0.2364 | 600 | 5.9506 |
| 5.9537 | 0.2758 | 700 | 5.9506 |
| 5.9517 | 0.3152 | 800 | 5.9506 |
| 5.954 | 0.3546 | 900 | 5.9506 |
| 5.9531 | 0.3940 | 1000 | 5.9506 |
| 5.9527 | 0.4334 | 1100 | 5.9506 |
| 5.9505 | 0.4728 | 1200 | 5.9506 |
| 5.9528 | 0.5122 | 1300 | 5.9506 |
| 5.9491 | 0.5516 | 1400 | 5.9506 |
| 5.9523 | 0.5910 | 1500 | 5.9506 |
| 5.951 | 0.6304 | 1600 | 5.9506 |
| 5.9526 | 0.6698 | 1700 | 5.9506 |
| 5.9499 | 0.7092 | 1800 | 5.9506 |
| 5.9513 | 0.7486 | 1900 | 5.9506 |
| 5.9496 | 0.7880 | 2000 | 5.9506 |
| 5.9528 | 0.8274 | 2100 | 5.9506 |
| 5.9538 | 0.8668 | 2200 | 5.9506 |
| 5.9535 | 0.9062 | 2300 | 5.9506 |
| 5.9535 | 0.9456 | 2400 | 5.9506 |
| 5.9521 | 0.9850 | 2500 | 5.9506 |
| 5.95 | 1.0244 | 2600 | 5.9506 |
| 5.9501 | 1.0638 | 2700 | 5.9506 |
| 5.9507 | 1.1032 | 2800 | 5.9506 |
| 5.9512 | 1.1426 | 2900 | 5.9506 |
| 5.9522 | 1.1820 | 3000 | 5.9506 |
| 5.9524 | 1.2214 | 3100 | 5.9506 |
| 5.9494 | 1.2608 | 3200 | 5.9506 |
| 5.9526 | 1.3002 | 3300 | 5.9506 |
| 5.953 | 1.3396 | 3400 | 5.9506 |
| 5.9512 | 1.3790 | 3500 | 5.9506 |
| 5.9533 | 1.4184 | 3600 | 5.9506 |
| 5.9544 | 1.4578 | 3700 | 5.9506 |
| 5.9514 | 1.4972 | 3800 | 5.9506 |
| 5.9504 | 1.5366 | 3900 | 5.9506 |
| 5.9527 | 1.5760 | 4000 | 5.9506 |
| 5.9516 | 1.6154 | 4100 | 5.9506 |
| 5.9492 | 1.6548 | 4200 | 5.9506 |
| 5.9531 | 1.6942 | 4300 | 5.9506 |
| 5.951 | 1.7336 | 4400 | 5.9506 |
| 5.9526 | 1.7730 | 4500 | 5.9506 |
| 5.9517 | 1.8125 | 4600 | 5.9506 |
| 5.9518 | 1.8519 | 4700 | 5.9506 |
| 5.951 | 1.8913 | 4800 | 5.9506 |
| 5.9521 | 1.9307 | 4900 | 5.9506 |
| 5.9529 | 1.9701 | 5000 | 5.9506 |
| 5.9502 | 2.0095 | 5100 | 5.9506 |
| 5.9496 | 2.0489 | 5200 | 5.9506 |
| 5.9505 | 2.0883 | 5300 | 5.9506 |
| 5.9527 | 2.1277 | 5400 | 5.9506 |
| 5.9523 | 2.1671 | 5500 | 5.9506 |
| 5.951 | 2.2065 | 5600 | 5.9506 |
| 5.9515 | 2.2459 | 5700 | 5.9506 |
| 5.9503 | 2.2853 | 5800 | 5.9506 |
| 5.9502 | 2.3247 | 5900 | 5.9506 |
| 5.9498 | 2.3641 | 6000 | 5.9506 |
| 5.9494 | 2.4035 | 6100 | 5.9506 |
| 5.9526 | 2.4429 | 6200 | 5.9506 |
| 5.9496 | 2.4823 | 6300 | 5.9506 |
| 5.9532 | 2.5217 | 6400 | 5.9506 |
| 5.9523 | 2.5611 | 6500 | 5.9506 |
| 5.9482 | 2.6005 | 6600 | 5.9506 |
| 5.9522 | 2.6399 | 6700 | 5.9506 |
| 5.9505 | 2.6793 | 6800 | 5.9506 |
| 5.9512 | 2.7187 | 6900 | 5.9506 |
| 5.9529 | 2.7581 | 7000 | 5.9506 |
| 5.9505 | 2.7975 | 7100 | 5.9506 |
| 5.9496 | 2.8369 | 7200 | 5.9506 |
| 5.9525 | 2.8763 | 7300 | 5.9506 |
| 5.9518 | 2.9157 | 7400 | 5.9506 |
| 5.9519 | 2.9551 | 7500 | 5.9506 |
| 5.9516 | 2.9945 | 7600 | 5.9506 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for parth0908/bert-squad2
Base model
SpanBERT/spanbert-large-cased