metadata
license: cc-by-4.0
base_model: deepset/roberta-base-squad2
tags:
- generated_from_trainer
model-index:
- name: RobertaLr1e-10Wd0.01
results: []
RobertaLr1e-10Wd0.01
This model is a fine-tuned version of deepset/roberta-base-squad2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.2070
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: 1e-10
- 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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.701 | 1.0 | 72 | 4.2072 |
| 4.9109 | 2.0 | 144 | 4.2072 |
| 4.8957 | 3.0 | 216 | 4.2071 |
| 4.798 | 4.0 | 288 | 4.2071 |
| 3.1796 | 5.0 | 360 | 4.2070 |
| 4.2849 | 6.0 | 432 | 4.2070 |
| 3.2476 | 7.0 | 504 | 4.2070 |
| 3.379 | 8.0 | 576 | 4.2070 |
| 4.5789 | 9.0 | 648 | 4.2070 |
| 3.1122 | 10.0 | 720 | 4.2070 |
| 3.688 | 11.0 | 792 | 4.2070 |
| 5.0388 | 12.0 | 864 | 4.2070 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.4.0
- Datasets 2.20.0
- Tokenizers 0.19.1