GPT
Collection
Series of GPT fine-tuned models
•
6 items
•
Updated
distilgpt2-wikitext2
This model is a fine-tuned version of distilgpt2 on the wikitext wikitext-2-raw-v1 dataset. It achieves the following results on the evaluation set:
- Loss: 3.3259
- Accuracy: 0.3932
- perplexity: 27.8235
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: 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
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 7
Dataset used to train Intel/distilgpt2-wikitext2
Collection including Intel/distilgpt2-wikitext2
Evaluation results
- Accuracy on wikitext wikitext-2-raw-v1self-reported0.393