finetuned_ClinicalLongformer_negsampling_llama_5050

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: 0.3217
• F1: 0.8889

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
0.6739	1.0	38	0.3638	0.8346
0.3866	2.0	76	0.3469	0.8710
0.2627	3.0	114	0.3217	0.8889
0.2636	4.0	152	0.3962	0.88
0.1862	5.0	190	0.5527	0.8403
0.2031	6.0	228	0.5769	0.8548
0.1784	7.0	266	0.5310	0.8819
0.1762	8.0	304	0.5902	0.8889
0.1089	9.0	342	0.7058	0.8594
0.0828	10.0	380	0.6648	0.8661
0.0573	11.0	418	0.7363	0.8730
0.0417	12.0	456	0.7568	0.8730
0.0727	13.0	494	0.8009	0.8618
0.0198	14.0	532	0.7883	0.8730
0.098	15.0	570	0.7891	0.8730

Framework versions

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