distilbert-base-uncased-MLM-scirepeval_fos_chemistry
This model is a fine-tuned version of distilbert-base-uncased on the scirepeval dataset. It achieves the following results on the evaluation set:
- Loss: 2.2937
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5835 | 1.0 | 125 | 2.4845 |
| 2.4632 | 2.0 | 250 | 2.3178 |
| 2.3484 | 3.0 | 375 | 2.4016 |
| 2.2896 | 4.0 | 500 | 2.3199 |
| 2.2798 | 5.0 | 625 | 2.4068 |
| 2.2428 | 6.0 | 750 | 2.2321 |
| 2.1922 | 7.0 | 875 | 2.2316 |
| 2.2027 | 8.0 | 1000 | 2.2645 |
| 2.1843 | 9.0 | 1125 | 2.1635 |
| 2.1805 | 10.0 | 1250 | 2.1585 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2