license: mit library_name: peft tags:
- trl
- sft
- generated_from_trainer base_model: openai-community/gpt2-medium model-index:
- name: openai_community_med_e3 results: [] pipeline_tag: text2text-generation metrics:
- rouge
- 'rouge1': 0.23894966434046966,
- 'rouge2': 0.106373660644453,
- 'rougeL': 0.2292802155791441,
- 'rougeLsum': 0.22745052553203093
openai_community_med_e3
This model is a fine-tuned version of openai-community/gpt2-medium on the None dataset.
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: 0.0009
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.39.1
- Pytorch 2.0.0
- Datasets 2.18.0
- Tokenizers 0.15.2