stop_reasons

This model is a fine-tuned version of domenicrosati/ClinicalTrialBioBert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4674
• Accuracy Thresh: 0.4706
• F1 Micro: 0.0526
• F1 Macro: 0.0062
• Confusion Matrix: [[286 0] [ 20 0]]

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Thresh	F1 Micro	F1 Macro	Confusion Matrix
No log	1.0	6	0.6000	0.0654	0.0	0.0	[[286 0]
[ 20 0]]
No log	2.0	12	0.5413	0.1699	0.0	0.0	[[286 0]
[ 20 0]]
No log	3.0	18	0.5106	0.2876	0.0541	0.0065	[[286 0]
[ 20 0]]
No log	4.0	24	0.4902	0.3595	0.0526	0.0062	[[286 0]
[ 20 0]]
No log	5.0	30	0.4775	0.4641	0.0526	0.0062	[[286 0]
[ 20 0]]
No log	6.0	36	0.4701	0.4706	0.0526	0.0062	[[286 0]
[ 20 0]]
No log	7.0	42	0.4674	0.4706	0.0526	0.0062	[[286 0]
[ 20 0]]

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2