mt5_fill_puntuation

jamie613/mt5_fill_puntuation

mt5_fill_puntuation is a machine learning model from jamie613. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

6% of all-time downloads

All-time downloads

592

Public

Repo size

51.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin2.3 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: mt5
Access: Public
Created: May 31, 2022
Updated: Jul 11, 2022
SHA: a3041da4

Model card

From the Hugging Face model README

mt5_fill_puntuation

This model is a fine-tuned version of jamie613/mt5_fill_puntuation on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0717

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: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.0918	0.04	500	0.0803
0.0894	0.07	1000	0.0773
0.0905	0.11	1500	0.0822
0.0908	0.15	2000	0.0833
0.0868	0.18	2500	0.0840
0.09	0.22	3000	0.0811
0.0868	0.26	3500	0.0735
0.0869	0.29	4000	0.0805
0.0874	0.33	4500	0.0742
0.088	0.37	5000	0.0749
0.0884	0.4	5500	0.0730
0.0861	0.44	6000	0.0749
0.0804	0.48	6500	0.0739
0.0845	0.51	7000	0.0717
0.0861	0.55	7500	0.0743
0.0812	0.59	8000	0.0726
0.0824	0.62	8500	0.0729
0.0836	0.66	9000	0.0751
0.079	0.7	9500	0.0731
0.0806	0.73	10000	0.0725
0.0798	0.77	10500	0.0749
0.0794	0.81	11000	0.0725
0.0795	0.84	11500	0.0726
0.0755	0.88	12000	0.0732
0.0815	0.92	12500	0.0722
0.0776	0.95	13000	0.0719
0.0838	0.99	13500	0.0717

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1

Library: transformers
Type: mt5
License: apache-2.0
Created: May 31, 2022
Updated: Jul 11, 2022