finetuned_ClinicalLongformer_original

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: 0.3942
• F1: 0.9286

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: 1e-05
• 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
0.5955	1.0	25	0.4497	0.88
0.4968	2.0	50	0.4056	0.9078
0.4323	3.0	75	0.3942	0.9286
0.3859	4.0	100	0.4318	0.9037
0.3287	5.0	125	0.4231	0.9130
0.3811	6.0	150	0.4103	0.9209
0.267	7.0	175	0.4821	0.9104
0.1595	8.0	200	0.6278	0.8939
0.2034	9.0	225	0.5937	0.9051
0.0837	10.0	250	0.7161	0.9065
0.1404	11.0	275	0.8732	0.8872
0.1493	12.0	300	0.8892	0.8872
0.1148	13.0	325	0.8537	0.8971
0.0328	14.0	350	0.8915	0.8788
0.1523	15.0	375	0.9008	0.8788

Framework versions

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