<!-- 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. -->
ClimateBertQA
This model is a fine-tuned version of climatebert/distilroberta-base-climate-f on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.3251
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1604 | 1.0 | 4081 | 1.1894 |
| 0.8577 | 2.0 | 8162 | 1.1763 |
| 0.6395 | 3.0 | 12243 | 1.1118 |
| 0.5015 | 4.0 | 16324 | 1.3251 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
