output_loss_only

letri345/output_loss_only

output_loss_only is a machine learning model from letri345. 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 mit.

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

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

226M

905 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors904 MB · 99%

At a glance

Library: transformers
License: mit
Model type: t5
Access: Public
Created: Nov 26, 2025
Updated: Nov 26, 2025
SHA: a2a0f342

Base models

VietAI/vit5-base

Model card

From the Hugging Face model README

output_loss_only

This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3426

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7587	0.4	100	1.5070
1.6074	0.8	200	1.4301
1.4991	1.2	300	1.3961
1.4815	1.6	400	1.3718
1.4502	2.0	500	1.3557
1.3857	2.4	600	1.3490
1.399	2.8	700	1.3426

Framework versions

Transformers 4.57.3
Pytorch 2.6.0+cu124
Datasets 4.4.1
Tokenizers 0.22.1

Library: transformers
Type: t5
License: mit
Created: Nov 26, 2025
Updated: Nov 26, 2025