finetuned_ClinicalLongformer_random_1090

This model is a fine-tuned version of yikuan8/Clinical-Longformer on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1601
• F1: 0.8777

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: 8e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.0807	1.0	189	0.2094	0.7681
0.2059	2.0	378	0.1441	0.8296
0.0632	3.0	567	0.1467	0.8633
0.0194	4.0	756	0.1497	0.8592
0.0751	5.0	945	0.1559	0.8671
0.0723	6.0	1134	0.1708	0.8732
0.0007	7.0	1323	0.1601	0.8777
0.0231	8.0	1512	0.1852	0.8652
0.1065	9.0	1701	0.1886	0.8633
0.0519	10.0	1890	0.1812	0.8714
0.0259	11.0	2079	0.1956	0.8696
0.0697	12.0	2268	0.1921	0.8714
0.0271	13.0	2457	0.2098	0.8551
0.0073	14.0	2646	0.2109	0.8551
0.0002	15.0	2835	0.2142	0.8551

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0