metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets: cmotions/Beatles_lyrics
widget:
- text: Last night in Kiev the
example_title: Kiev
- text: It hasn't rained in weeks
example_title: Rain
base_model: distilgpt2
model-index:
- name: DistilGPT2-Beatles-Lyrics-finetuned-newlyrics
results: []
DistilGPT2-Beatles-Lyrics-finetuned-newlyrics
This model is a fine-tuned version of distilgpt2 on the Cmotions - Beatles lyrics dataset. It will complete an input prompt with Beatles-like text.
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.786 | 1.0 | 18 | 2.0410 |
| 2.5587 | 2.0 | 36 | 1.9280 |
| 2.3651 | 3.0 | 54 | 1.8829 |
| 2.2759 | 4.0 | 72 | 1.8473 |
| 2.1241 | 5.0 | 90 | 1.8237 |
| 2.1018 | 6.0 | 108 | 1.8535 |
| 1.8537 | 7.0 | 126 | 1.8497 |
| 1.7859 | 8.0 | 144 | 1.8618 |
| 1.69 | 9.0 | 162 | 1.8657 |
| 1.6481 | 10.0 | 180 | 1.8711 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1