<!-- 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-lr5e05-wd0.08-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: 0.2814
- Rmse: 0.5305
- Mse: 0.2814
- Mae: 0.4398
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: 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 |
---|---|---|---|---|---|---|
0.2772 | 1.0 | 623 | 0.2735 | 0.5230 | 0.2735 | 0.4158 |
0.2731 | 2.0 | 1246 | 0.2753 | 0.5247 | 0.2753 | 0.4214 |
0.2707 | 3.0 | 1869 | 0.2814 | 0.5305 | 0.2814 | 0.4398 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1