metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: pretrained_gpt2
results: []
pretrained_gpt2
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4775
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: 0.0005
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.4897 | 1.17 | 500 | 6.1071 |
5.5542 | 2.35 | 1000 | 5.7496 |
5.0727 | 3.52 | 1500 | 5.5820 |
4.6986 | 4.69 | 2000 | 5.4866 |
4.3625 | 5.87 | 2500 | 5.4438 |
4.0439 | 7.04 | 3000 | 5.4475 |
3.7449 | 8.22 | 3500 | 5.4655 |
3.5157 | 9.39 | 4000 | 5.4775 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0