TFG
Collection
Datasets and models leveraged and developed during my final degree work (TFG). Info and code can be found at https://github.com/enriquesaou/tfg-lm-qa
•
18 items
•
Updated
•
2
t5-small-mrqa
This model is a fine-tuned version of google-t5/t5-small on an MRQA sample. It achieves the following results on the evaluation set:
- Loss: 0.8647
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: 3e-05
- train_batch_size: 14
- eval_batch_size: 14
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9991 | 357 | 0.9669 |
| 1.0947 | 1.9981 | 714 | 0.9170 |
| 0.9558 | 3.0 | 1072 | 0.8990 |
| 0.9558 | 3.9991 | 1429 | 0.8855 |
| 0.9023 | 4.9981 | 1786 | 0.8680 |
| 0.8684 | 6.0 | 2144 | 0.8680 |
| 0.8542 | 6.9991 | 2501 | 0.8668 |
| 0.8542 | 7.9925 | 2856 | 0.8647 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.