Variome_5e-05_250

Brizape/Variome_5e-05_250

Variome_5e-05_250 is a token classification model from Brizape. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

32% of all-time downloads

All-time downloads

Public

Repo size

2.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin436 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Mar 31, 2023
Updated: Mar 31, 2023
SHA: 794cc05e

Try a prompt

Model card

From the Hugging Face model README

Variome_5e-05_250

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0679
Precision: 0.6097
Recall: 0.5389
F1: 0.5721
Accuracy: 0.9860

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5834	0.35	25	0.1849	0.0	0.0	0.0	0.9760
0.1856	0.69	50	0.1791	0.0	0.0	0.0	0.9760
0.1611	1.04	75	0.1698	0.0	0.0	0.0	0.9760
0.1471	1.39	100	0.1219	0.1478	0.0290	0.0485	0.9764
0.1117	1.74	125	0.1133	0.1784	0.1426	0.1585	0.9767
0.1071	2.08	150	0.1030	0.2899	0.2220	0.2515	0.9789
0.0844	2.43	175	0.0977	0.3838	0.2750	0.3204	0.9805
0.087	2.78	200	0.0884	0.4084	0.3903	0.3991	0.9815
0.0785	3.12	225	0.0803	0.4895	0.4176	0.4507	0.9833
0.0647	3.47	250	0.0784	0.5545	0.4518	0.4979	0.9842
0.0592	3.82	275	0.0740	0.5655	0.5013	0.5315	0.9847
0.0525	4.17	300	0.0725	0.5916	0.5158	0.5511	0.9854
0.0515	4.51	325	0.0698	0.5861	0.5115	0.5463	0.9853
0.0483	4.86	350	0.0691	0.5994	0.5201	0.5569	0.9855
0.047	5.21	375	0.0702	0.5905	0.5209	0.5535	0.9855
0.0429	5.56	400	0.0693	0.5986	0.5286	0.5615	0.9858
0.0435	5.9	425	0.0673	0.5951	0.5397	0.5661	0.9858
0.0418	6.25	450	0.0676	0.5949	0.5329	0.5622	0.9858
0.038	6.6	475	0.0679	0.6013	0.5397	0.5689	0.9860
0.0355	6.94	500	0.0679	0.6097	0.5389	0.5721	0.9860

Framework versions

Transformers 4.27.4
Pytorch 1.13.1+cu116
Datasets 2.11.0
Tokenizers 0.13.2

Task: Token Classification
Library: transformers
Type: bert
License: mit
Created: Mar 31, 2023
Updated: Mar 31, 2023