<!-- 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. -->
distil-Is-upper
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6095
- Rmse: 0.7807
- Mse: 0.6095
- Mae: 0.5993
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rmse | Mse | Mae |
---|---|---|---|---|---|---|
0.7129 | 1.0 | 492 | 0.7088 | 0.8419 | 0.7088 | 0.5968 |
0.5953 | 2.0 | 984 | 0.6426 | 0.8016 | 0.6426 | 0.5838 |
0.5865 | 3.0 | 1476 | 0.6083 | 0.7800 | 0.6083 | 0.6023 |
0.5888 | 4.0 | 1968 | 0.6209 | 0.7880 | 0.6209 | 0.5880 |
0.5859 | 5.0 | 2460 | 0.6095 | 0.7807 | 0.6095 | 0.5993 |
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 2.4.0
- Tokenizers 0.12.1