perc_poem_baseline
This model is a fine-tuned version of ismaelfaro/gpt2-poems.en on the PERC dataset. It achieves the following results on the evaluation set:
- Loss: 5.9662
- Accuracy: 0.2925
Model description
A finetuned GPT2 on the PERC data (https://data.mendeley.com/datasets/n9vbc8g9cx/1)
Intended uses & limitations
For UCL COMP0087 SNLP poem generation baseline model
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: 4
- eval_batch_size: 4
- seed: 19019509
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50.0
Training results
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2