scideberta-cs-tdm-pretrained

sohamtiwari3120/scideberta-cs-tdm-pretrained

scideberta-cs-tdm-pretrained is a token classification model from sohamtiwari3120. 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

344

Public

Repo size

13.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin555 MB · 99%

At a glance

Task: Token Classification
Library: transformers
Model type: deberta
Access: Public
Created: Oct 26, 2022
Updated: Oct 26, 2022
SHA: bc959466

Try a prompt

Model card

From the Hugging Face model README

scideberta-cs-tdm-pretrained

This model is a fine-tuned version of KISTI-AI/scideberta-cs on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8211
Overall Precision: 0.6247
Overall Recall: 0.7665
Overall F1: 0.6884
Overall Accuracy: 0.9288
Datasetname F1: 0.6345
Metricname F1: 0.8177
Taskname F1: 0.6622

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Datasetname F1	Metricname F1	Taskname F1
No log	1.0	191	0.3160	0.4684	0.6953	0.5597	0.9187	0.5439	0.7008	0.5135
No log	2.0	382	0.3152	0.4370	0.6544	0.5240	0.9084	0.3623	0.7527	0.5303
0.4334	3.0	573	0.3713	0.4900	0.6768	0.5684	0.9116	0.5525	0.7692	0.5025
0.4334	4.0	764	0.4347	0.5554	0.6807	0.6117	0.9253	0.5943	0.7074	0.5795
0.4334	5.0	955	0.5098	0.5777	0.7309	0.6453	0.9258	0.6478	0.7902	0.5868
0.1097	6.0	1146	0.5453	0.5784	0.7401	0.6493	0.9265	0.5782	0.7642	0.6390
0.1097	7.0	1337	0.6200	0.6264	0.7586	0.6862	0.9349	0.6513	0.7826	0.6629
0.0499	8.0	1528	0.6072	0.6448	0.7401	0.6892	0.9380	0.6783	0.7935	0.6496
0.0499	9.0	1719	0.6568	0.6329	0.7414	0.6829	0.9347	0.6413	0.8086	0.6487
0.0499	10.0	1910	0.6726	0.6264	0.7520	0.6835	0.9312	0.6618	0.7967	0.6472
0.0247	11.0	2101	0.8104	0.6635	0.7282	0.6943	0.9395	0.6514	0.8159	0.6635
0.0247	12.0	2292	0.7022	0.6320	0.7704	0.6944	0.9376	0.6452	0.8122	0.6704
0.0247	13.0	2483	0.8143	0.6655	0.7216	0.6924	0.9366	0.6321	0.8122	0.6700
0.0176	14.0	2674	0.7723	0.6434	0.7309	0.6844	0.9329	0.6190	0.7934	0.6699
0.0176	15.0	2865	0.7726	0.6071	0.7480	0.6702	0.9320	0.6174	0.8122	0.6391
0.0132	16.0	3056	0.8124	0.6404	0.7493	0.6906	0.9329	0.6326	0.8098	0.6682
0.0132	17.0	3247	0.8269	0.6374	0.7467	0.6877	0.9336	0.6071	0.8268	0.6714
0.0132	18.0	3438	0.8826	0.6315	0.7573	0.6887	0.9343	0.6456	0.8142	0.6573
0.0125	19.0	3629	0.8602	0.6446	0.7467	0.6919	0.9320	0.6190	0.8156	0.6760
0.0125	20.0	3820	1.0048	0.6679	0.7216	0.6937	0.9350	0.6683	0.7932	0.6634
0.0093	21.0	4011	0.8211	0.6247	0.7665	0.6884	0.9288	0.6345	0.8177	0.6622

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu102
Datasets 2.6.1
Tokenizers 0.13.1

Task: Token Classification
Library: transformers
Type: deberta
Created: Oct 26, 2022
Updated: Oct 26, 2022