NeRUBioS_xlm_RoBERTa_base_Training_Development

ajtamayoh/NeRUBioS_xlm_RoBERTa_base_Training_Development

NeRUBioS_xlm_RoBERTa_base_Training_Development is a token classification model from ajtamayoh. 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

16% of all-time downloads

All-time downloads

Public

Parameters

277M

10 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 98%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Apr 13, 2024
Updated: Apr 13, 2024
SHA: 76750c97

Try a prompt

Base models

FacebookAI/xlm-roberta-base

Model card

From the Hugging Face model README

NeRUBioS_xlm_RoBERTa_base_Training_Development

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3324
Negref Precision: 0.5672
Negref Recall: 0.5696
Negref F1: 0.5684
Neg Precision: 0.9480
Neg Recall: 0.9760
Neg F1: 0.9618
Nsco Precision: 0.8685
Nsco Recall: 0.9097
Nsco F1: 0.8886
Unc Precision: 0.8419
Unc Recall: 0.8842
Unc F1: 0.8625
Usco Precision: 0.6429
Usco Recall: 0.7383
Usco F1: 0.6873
Precision: 0.8190
Recall: 0.8548
F1: 0.8365
Accuracy: 0.9520

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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Negref Precision	Negref Recall	Negref F1	Neg Precision	Neg Recall	Neg F1	Nsco Precision	Nsco Recall	Nsco F1	Unc Precision	Unc Recall	Unc F1	Usco Precision	Usco Recall	Usco F1	Precision	Recall	F1	Accuracy
0.2316	1.0	1729	0.2023	0.4328	0.4958	0.4621	0.8759	0.9629	0.9173	0.7259	0.8397	0.7786	0.7059	0.8340	0.7646	0.4408	0.6836	0.5360	0.6864	0.8063	0.7415	0.9364
0.1596	2.0	3458	0.1756	0.4771	0.5274	0.5010	0.9252	0.9727	0.9484	0.8113	0.8836	0.8459	0.8036	0.8687	0.8349	0.5615	0.6953	0.6213	0.7624	0.8329	0.7961	0.9480
0.1197	3.0	5187	0.1735	0.5214	0.5401	0.5306	0.9436	0.9672	0.9553	0.8449	0.8800	0.8621	0.8094	0.8687	0.8380	0.5705	0.6953	0.6268	0.7891	0.8322	0.8101	0.9510
0.1006	4.0	6916	0.2003	0.5324	0.5717	0.5514	0.9365	0.9814	0.9584	0.8510	0.8955	0.8727	0.7965	0.8764	0.8346	0.5755	0.7148	0.6376	0.7890	0.8497	0.8182	0.9508
0.0706	5.0	8645	0.2077	0.5434	0.5675	0.5552	0.9497	0.9683	0.9589	0.8821	0.9062	0.8940	0.8285	0.8764	0.8518	0.6013	0.7188	0.6548	0.8107	0.8482	0.8290	0.9531
0.0514	6.0	10374	0.2554	0.5282	0.5527	0.5402	0.9281	0.9716	0.9493	0.8476	0.9050	0.8754	0.8433	0.8726	0.8577	0.6131	0.7305	0.6667	0.7950	0.8471	0.8202	0.9496
0.039	7.0	12103	0.2547	0.5306	0.5675	0.5484	0.9508	0.9705	0.9606	0.8672	0.9074	0.8868	0.8582	0.9112	0.8839	0.6609	0.7461	0.7009	0.8136	0.8551	0.8339	0.9525
0.0273	8.0	13832	0.2796	0.5447	0.5401	0.5424	0.9459	0.9738	0.9597	0.8615	0.9086	0.8844	0.8088	0.8494	0.8286	0.6575	0.75	0.7007	0.8115	0.8464	0.8286	0.9497
0.0214	9.0	15561	0.3079	0.5429	0.5738	0.5579	0.9391	0.9771	0.9577	0.8707	0.9121	0.8910	0.8448	0.9035	0.8731	0.6084	0.7344	0.6655	0.8066	0.8580	0.8315	0.9514
0.0136	10.0	17290	0.3172	0.5524	0.5781	0.5649	0.9459	0.9738	0.9597	0.8848	0.9121	0.8982	0.8476	0.8803	0.8636	0.6519	0.7461	0.6958	0.8201	0.8566	0.8380	0.9520
0.0098	11.0	19019	0.3312	0.5729	0.5717	0.5723	0.9501	0.9771	0.9634	0.8753	0.9086	0.8916	0.8476	0.8803	0.8636	0.6574	0.7422	0.6972	0.8251	0.8551	0.8398	0.9516
0.008	12.0	20748	0.3324	0.5672	0.5696	0.5684	0.9480	0.9760	0.9618	0.8685	0.9097	0.8886	0.8419	0.8842	0.8625	0.6429	0.7383	0.6873	0.8190	0.8548	0.8365	0.9520

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Token Classification
Library: transformers
Type: xlm-roberta
License: mit
Created: Apr 13, 2024
Updated: Apr 13, 2024