metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-finetuned-wikitext2-test
results: []
distilgpt2-finetuned-wikitext2-test
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8267
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 277 | 3.8379 |
| 3.8669 | 2.0 | 554 | 3.8250 |
| 3.8669 | 3.0 | 831 | 3.8267 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3