fine-tuned-BioBART-10-epochs

This model is a fine-tuned version of GanjinZero/biobart-v2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7099
• Rouge1: 0.2929
• Rouge2: 0.1172
• Rougel: 0.2685
• Rougelsum: 0.2674
• Gen Len: 14.66

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	151	0.7536	0.204	0.0789	0.1879	0.1874	13.31
No log	2.0	302	0.7161	0.2576	0.0833	0.2281	0.227	13.88
No log	3.0	453	0.7013	0.2314	0.082	0.2052	0.2053	14.57
0.7283	4.0	604	0.6976	0.2835	0.1092	0.2574	0.2572	14.34
0.7283	5.0	755	0.7012	0.2761	0.0916	0.252	0.2525	14.35
0.7283	6.0	906	0.6963	0.2959	0.108	0.2692	0.2692	14.97
0.5246	7.0	1057	0.7043	0.2848	0.1074	0.2558	0.2563	14.68
0.5246	8.0	1208	0.7043	0.2945	0.1168	0.271	0.2701	14.16
0.5246	9.0	1359	0.7080	0.2875	0.1097	0.2604	0.2598	14.69
0.4414	10.0	1510	0.7099	0.2929	0.1172	0.2685	0.2674	14.66

Framework versions

• Transformers 4.36.2
• Pytorch 1.12.1+cu113
• Datasets 2.15.0
• Tokenizers 0.15.0