metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilroberta-base-wiki-mark
results: []
distilroberta-base-wiki-mark
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2066
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2545 | 1.0 | 2028 | 2.3260 |
| 2.2803 | 2.0 | 4056 | 2.2899 |
| 2.24 | 3.0 | 6084 | 2.1889 |
| 2.2414 | 4.0 | 8112 | 2.2387 |
| 2.1412 | 5.0 | 10140 | 2.1748 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.6.0
- Datasets 2.3.2
- Tokenizers 0.12.1