metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: BERTModified-finetuned-wikitext-test
results: []
BERTModified-finetuned-wikitext-test
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.8018
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| 6.8778 | 1.0 | 1096 | 6.3188 |
| 5.9673 | 2.0 | 2192 | 6.0563 |
| 5.6729 | 3.0 | 3288 | 5.9121 |
| 5.5048 | 4.0 | 4384 | 5.8427 |
| 5.4082 | 5.0 | 5480 | 5.8018 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.2