V3_20230929-3-xlm-roberta-base-new

soBeauty/V3_20230929-3-xlm-roberta-base-new

V3_20230929-3-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

11% of all-time downloads

All-time downloads

Public

Repo size

14.5 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: fe24c54a

Try a prompt

Base models

Model card

From the Hugging Face model README

V3_20230929-3-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: 0.5509
Loss: 2.1676

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
4.4138	0.46	200	0.2723	nan
4.0972	0.91	400	0.3135	nan
3.7299	1.37	600	0.3289	nan
3.7476	1.82	800	0.3242	3.6812
3.8098	2.28	1000	0.4011	3.5966
3.6111	2.73	1200	0.4	2.8744
3.3202	3.19	1400	0.4334	2.9269
3.3557	3.64	1600	0.3649	nan
3.198	4.1	1800	0.4349	nan
3.1623	4.56	2000	0.4237	2.9731
3.1379	5.01	2200	0.4521	nan
3.0795	5.47	2400	0.4538	2.8971
3.0176	5.92	2600	0.4138	3.0068
2.9956	6.38	2800	0.4729	nan
2.9666	6.83	3000	0.4674	2.3240
2.9124	7.29	3200	0.5039	nan
2.9806	7.74	3400	0.4457	nan
2.7471	8.2	3600	0.5138	2.4373
2.7762	8.66	3800	0.4963	2.4425
2.7485	9.11	4000	0.5302	nan
2.6488	9.57	4200	0.5499	2.3581
2.69	10.02	4400	0.5066	2.3862
2.6669	10.48	4600	0.4802	2.4588
2.5595	10.93	4800	0.4938	2.4186
2.5512	11.39	5000	0.5076	2.5922
2.5686	11.85	5200	0.5648	nan
2.5772	12.3	5400	0.5480	2.4634
2.5701	12.76	5600	0.5497	2.5381
2.3937	13.21	5800	0.5310	nan
2.5274	13.67	6000	0.5681	nan
2.3513	14.12	6200	0.5671	nan
2.529	14.58	6400	0.5509	2.1676

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