BERiT_2000_ls_.2

gngpostalsrvc/BERiT_2000_ls_.2

BERiT_2000_ls_.2 is a fill-mask model from gngpostalsrvc. 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

2% of all-time downloads

All-time downloads

296

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin351 MB · 100%

At a glance

Task: Fill-Mask
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Nov 14, 2022
Updated: Nov 14, 2022
SHA: dbc3064a

Try a prompt

Model card

From the Hugging Face model README

BERiT_2000_ls

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

Loss: 6.9311

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: 5e-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: 3
label_smoothing_factor: 0.2

Training results

Training Loss	Epoch	Step	Validation Loss
7.0431	0.19	500	6.9715
6.9481	0.39	1000	6.9600
6.9487	0.58	1500	6.9444
6.9495	0.77	2000	6.9505
6.9373	0.97	2500	6.9556
6.9332	1.16	3000	6.9371
6.9295	1.36	3500	6.9256
6.9367	1.55	4000	6.9137
6.9387	1.74	4500	6.9337
6.9237	1.94	5000	6.9251
6.9363	2.13	5500	6.9490
6.9591	2.32	6000	6.9261
6.9066	2.52	6500	6.9322
6.9385	2.71	7000	6.9222
6.9293	2.9	7500	6.9311

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.2

Task: Fill-Mask
Library: transformers
Type: roberta
License: mit
Created: Nov 14, 2022
Updated: Nov 14, 2022