V3_20230929-5-xlm-roberta-base-new

soBeauty/V3_20230929-5-xlm-roberta-base-new

V3_20230929-5-xlm-roberta-base-new is a fill-mask model from soBeauty. Use it when you need the model to fill a missing word. 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

Repo size

15.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 100%

At a glance

Task: Fill-Mask
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Sep 30, 2023
Updated: Sep 30, 2023
SHA: d124e672

Try a prompt

Base models

Model card

From the Hugging Face model README

V3_20230929-5-xlm-roberta-base-new

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

Accuracy: 0.5172
Loss: 2.6032

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: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
4.4963	0.46	200	0.2938	nan
4.0957	0.91	400	0.3098	3.5806
3.7431	1.37	600	0.3455	nan
3.6542	1.82	800	0.3075	nan
3.5585	2.28	1000	0.3546	3.4012
3.4027	2.73	1200	0.4049	3.2653
3.3416	3.19	1400	0.4053	nan
3.314	3.64	1600	0.4505	nan
3.2035	4.1	1800	0.4140	2.8518
3.1372	4.56	2000	0.4553	2.7572
3.0738	5.01	2200	0.4188	3.1020
3.0354	5.47	2400	0.4483	2.9353
3.0447	5.92	2600	0.4729	2.8608
2.6643	6.38	2800	0.4833	2.6200
2.8909	6.83	3000	0.4858	2.4677
2.9888	7.29	3200	0.4676	2.8088
2.8658	7.74	3400	0.5162	2.6409
2.7865	8.2	3600	0.5294	nan
2.8237	8.66	3800	0.4986	nan
2.7182	9.11	4000	0.5087	nan
2.7962	9.57	4200	0.5459	nan
2.5706	10.02	4400	0.4801	nan
2.528	10.48	4600	0.4893	2.2799
2.7482	10.93	4800	0.5227	nan
2.799	11.39	5000	0.4501	nan
2.471	11.85	5200	0.5323	2.4217
2.6071	12.3	5400	0.5420	nan
2.5139	12.76	5600	0.5511	2.1409
2.4214	13.21	5800	0.5215	2.4055
2.608	13.67	6000	0.5197	2.3034
2.5468	14.12	6200	0.5259	nan
2.4802	14.58	6400	0.5172	2.6032

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

Task: Fill-Mask
Library: transformers
Type: xlm-roberta
License: mit
Created: Sep 30, 2023
Updated: Sep 30, 2023