bsc-bio-ehr-es

aimarsg/bsc-bio-ehr-es

bsc-bio-ehr-es is a token classification model from aimarsg. Use it when you need labels on individual words, such as names. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

369

Public

Repo size

40.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin496 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: roberta
Access: Public
Created: Mar 6, 2023
Updated: Mar 16, 2023
SHA: 1f3fbd3f

Try a prompt

Model card

From the Hugging Face model README

bsc-bio-ehr-es

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4593
Precision: 0.4074
Recall: 0.2696
F1: 0.3245
Accuracy: 0.9050

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	116	0.4621	0.4928	0.1667	0.2491	0.9033
No log	2.0	232	0.4577	0.4472	0.2696	0.3364	0.9048
No log	3.0	348	0.4593	0.4074	0.2696	0.3245	0.9050

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2

Task: Token Classification
Library: transformers
Type: roberta
Created: Mar 6, 2023
Updated: Mar 16, 2023