mt5-small-finetune-sumsum

Paligonshik/mt5-small-finetune-sumsum

mt5-small-finetune-sumsum is a machine learning model from Paligonshik. 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

3% of all-time downloads

All-time downloads

436

Public

Parameters

300M

3.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.2 GB · 50%

At a glance

Library: transformers
License: apache-2.0
Model type: mt5
Access: Public
Created: Dec 4, 2022
Updated: Mar 3, 2025
SHA: 11135b9e

Datasets

samsum

Model card

From the Hugging Face model README

mt5-small-finetune-sumsum

This model is a fine-tuned version of google/mt5-small on the samsum dataset. It achieves the following results on the evaluation set:

Loss: 3.3263
Rouge1: 20.9651
Rouge2: 7.1527
Rougel: 18.4396
Rougelsum: 19.5209

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: 5.6e-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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
12.2648	1.0	125	4.3790	9.8078	1.7255	9.0852	9.4233
6.0853	2.0	250	3.4753	20.7185	6.502	18.079	19.2584
4.9838	3.0	375	3.3263	20.9651	7.1527	18.4396	19.5209

Framework versions

Transformers 4.18.0
Pytorch 1.13.0
Datasets 2.6.1
Tokenizers 0.11.0

Library: transformers
Type: mt5
License: apache-2.0
Created: Dec 4, 2022
Updated: Mar 3, 2025