t5-base-finetuned-es-to-sja

mekjr1/t5-base-finetuned-es-to-sja

t5-base-finetuned-es-to-sja is a machine learning model from mekjr1. 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

9% of all-time downloads

All-time downloads

Public

Repo size

6.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin892 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Apr 13, 2023
Updated: Apr 14, 2023
SHA: 897bd201

Model card

From the Hugging Face model README

t5-base-finetuned-es-to-sja

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5730
Bleu: 0.089
Gen Len: 19.0

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	199	2.1692	0.0253	19.0
No log	2.0	398	1.8872	0.0533	19.0
2.4927	3.0	597	1.7759	0.0723	19.0
2.4927	4.0	796	1.7032	0.0652	18.9924
2.4927	5.0	995	1.6562	0.0899	19.0
1.9132	6.0	1194	1.6232	0.0856	19.0
1.9132	7.0	1393	1.6005	0.0823	19.0
1.793	8.0	1592	1.5853	0.0876	19.0
1.793	9.0	1791	1.5758	0.087	19.0
1.793	10.0	1990	1.5730	0.089	19.0

Framework versions

Transformers 4.28.0
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3

Library: transformers
Type: t5
License: apache-2.0
Created: Apr 13, 2023
Updated: Apr 14, 2023