xlm-roberta-base-david

davidliu1110/xlm-roberta-base-david

xlm-roberta-base-david is a token classification model from davidliu1110. 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

13% of all-time downloads

All-time downloads

Public

Repo size

5.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 98%

At a glance

Task: Token Classification
Library: transformers
Model type: xlm-roberta
Access: Public
Created: May 10, 2023
Updated: May 10, 2023
SHA: 7503f50d

Try a prompt

Model card

From the Hugging Face model README

xlm-roberta-base-david

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

Loss: 0.0697
Precision: 0.9497
Recall: 0.9544
F1: 0.9520
Accuracy: 0.9864

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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.2104	0.1	100	0.6752	0.1279	0.0587	0.0804	0.7761
0.5384	0.2	200	0.3366	0.2616	0.2119	0.2341	0.8771
0.3168	0.3	300	0.2264	0.5493	0.4996	0.5233	0.9211
0.2345	0.39	400	0.1796	0.6662	0.8297	0.7390	0.9395
0.1883	0.49	500	0.1687	0.7203	0.8207	0.7672	0.9413
0.1587	0.59	600	0.1414	0.7661	0.8354	0.7992	0.9525
0.1605	0.69	700	0.1209	0.7946	0.8672	0.8293	0.9609
0.1365	0.79	800	0.1120	0.8304	0.8696	0.8495	0.9657
0.1205	0.89	900	0.1098	0.8659	0.8786	0.8722	0.9683
0.1353	0.99	1000	0.1239	0.8436	0.8794	0.8611	0.9643
0.1083	1.09	1100	0.1243	0.8537	0.8892	0.8711	0.9657
0.0961	1.18	1200	0.1078	0.8689	0.8965	0.8825	0.9696
0.0798	1.28	1300	0.0995	0.8774	0.9038	0.8904	0.9724
0.0843	1.38	1400	0.0965	0.8793	0.9144	0.8965	0.9733
0.0923	1.48	1500	0.0957	0.8815	0.9030	0.8921	0.9730
0.0847	1.58	1600	0.0959	0.8617	0.8941	0.8776	0.9709
0.089	1.68	1700	0.0844	0.8982	0.9201	0.9090	0.9760
0.0721	1.78	1800	0.0767	0.9	0.9095	0.9047	0.9782
0.0803	1.88	1900	0.0776	0.8981	0.9340	0.9157	0.9774
0.0766	1.97	2000	0.0611	0.9166	0.9315	0.9240	0.9816
0.0651	2.07	2100	0.0771	0.9127	0.9454	0.9287	0.9817
0.0562	2.17	2200	0.0908	0.9031	0.9112	0.9071	0.9771
0.0629	2.27	2300	0.0656	0.9184	0.9356	0.9269	0.9817
0.0504	2.37	2400	0.0836	0.8998	0.9299	0.9146	0.9775
0.0464	2.47	2500	0.0791	0.9310	0.9340	0.9325	0.9816
0.0396	2.57	2600	0.0763	0.9167	0.9234	0.9200	0.9816
0.0582	2.67	2700	0.0705	0.9198	0.9446	0.9320	0.9833
0.0561	2.76	2800	0.0635	0.9274	0.9470	0.9371	0.9835
0.0446	2.86	2900	0.0679	0.9301	0.9438	0.9369	0.9828
0.0429	2.96	3000	0.0663	0.9209	0.9397	0.9302	0.9820
0.0323	3.06	3100	0.0771	0.9303	0.9462	0.9382	0.9825
0.0228	3.16	3200	0.0839	0.9279	0.9446	0.9362	0.9830
0.0332	3.26	3300	0.0717	0.9365	0.9495	0.9429	0.9839
0.0351	3.36	3400	0.0668	0.9358	0.9381	0.9369	0.9840
0.0425	3.46	3500	0.0688	0.9363	0.9462	0.9412	0.9838
0.0431	3.55	3600	0.0710	0.9321	0.9503	0.9411	0.9840
0.0228	3.65	3700	0.0748	0.9343	0.9511	0.9426	0.9838
0.0334	3.75	3800	0.0770	0.9401	0.9462	0.9431	0.9834
0.0373	3.85	3900	0.0713	0.9294	0.9446	0.9369	0.9832
0.0368	3.95	4000	0.0668	0.9380	0.9495	0.9437	0.9845
0.0295	4.05	4100	0.0706	0.9364	0.9487	0.9425	0.9843
0.0169	4.15	4200	0.0675	0.9426	0.9503	0.9464	0.9863
0.0234	4.24	4300	0.0697	0.9497	0.9544	0.9520	0.9864
0.0235	4.34	4400	0.0713	0.9392	0.9576	0.9483	0.9857
0.0233	4.44	4500	0.0689	0.9428	0.9544	0.9486	0.9857
0.015	4.54	4600	0.0744	0.9404	0.9511	0.9457	0.9846
0.0154	4.64	4700	0.0753	0.9406	0.9552	0.9478	0.9860
0.0235	4.74	4800	0.0733	0.9431	0.9584	0.9507	0.9859
0.0239	4.84	4900	0.0728	0.9438	0.9576	0.9506	0.9864
0.0237	4.94	5000	0.0727	0.9437	0.9560	0.9498	0.9862

Framework versions

Transformers 4.29.0.dev0
Pytorch 1.10.1+cu113
Datasets 2.11.0
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: xlm-roberta
Created: May 10, 2023
Updated: May 10, 2023