metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-finetuned-yannic-test
results: []
gpt2-finetuned-yannic-test
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3803
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: 8
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.5406 | 1.0 | 503 | 3.4633 |
3.4091 | 2.0 | 1006 | 3.4278 |
3.3505 | 3.0 | 1509 | 3.4075 |
3.3088 | 4.0 | 2012 | 3.3954 |
3.281 | 5.0 | 2515 | 3.3892 |
3.2616 | 6.0 | 3018 | 3.3846 |
3.2434 | 7.0 | 3521 | 3.3815 |
3.2357 | 8.0 | 4024 | 3.3803 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2