<!-- 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. -->
distilr2-lr1e05-wd0.1-bs64
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2723
- Rmse: 0.5219
- Mse: 0.2723
- Mae: 0.4098
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-05
- train_batch_size: 512
- eval_batch_size: 512
- 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 | Rmse | Mse | Mae |
---|---|---|---|---|---|---|
0.2779 | 1.0 | 312 | 0.2756 | 0.5250 | 0.2756 | 0.4246 |
0.2747 | 2.0 | 624 | 0.2734 | 0.5229 | 0.2734 | 0.4091 |
0.2732 | 3.0 | 936 | 0.2726 | 0.5221 | 0.2726 | 0.4155 |
0.2714 | 4.0 | 1248 | 0.2723 | 0.5219 | 0.2723 | 0.4098 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1