This model is a fine-tuned version of andrewoh/RoBERTa-lifescience-domain on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1048
Precision: 0.8366
Recall: 0.8765
F1: 0.8561
Accuracy: 0.9707

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: Use OptimizerNames.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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2159	1.0	1366	0.1589	0.7668	0.7377	0.7520	0.9505
0.1264	2.0	2732	0.1155	0.8073	0.8333	0.8201	0.9638
0.0853	3.0	4098	0.1089	0.8179	0.8533	0.8352	0.9668
0.0631	4.0	5464	0.1050	0.8363	0.8707	0.8532	0.9700
0.047	5.0	6830	0.1048	0.8366	0.8765	0.8561	0.9707

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 2.21.0
Tokenizers 0.21.1

andrewoh/RoBERTa-finetuned-lifescience-ner

RoBERTa-finetuned-lifescience-ner

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

andrewoh/
RoBERTa-finetuned-lifescience-ner