<!-- 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-lr2e05-wd0.1-bs32
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2809
- Rmse: 0.5300
- Mse: 0.2809
- Mae: 0.4214
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: 256
- eval_batch_size: 256
- 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 |
---|---|---|---|---|---|---|
0.2771 | 1.0 | 623 | 0.2730 | 0.5224 | 0.2730 | 0.4164 |
0.2732 | 2.0 | 1246 | 0.2731 | 0.5226 | 0.2731 | 0.4156 |
0.271 | 3.0 | 1869 | 0.2791 | 0.5283 | 0.2791 | 0.4308 |
0.2681 | 4.0 | 2492 | 0.2751 | 0.5245 | 0.2751 | 0.4004 |
0.2648 | 5.0 | 3115 | 0.2795 | 0.5286 | 0.2795 | 0.4238 |
0.2606 | 6.0 | 3738 | 0.2809 | 0.5300 | 0.2809 | 0.4214 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1