mt5-stage3-codemixed-si

RASHINI01/mt5-stage3-codemixed-si

mt5-stage3-codemixed-si is a machine learning model from RASHINI01. 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.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

107

Public

Parameters

582M

65.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt4.7 GB · 50%

At a glance

Library: transformers
Model type: mt5
Access: Public
Created: Jan 2, 2026
Updated: Jan 2, 2026
SHA: 2f27bb32

Base models

RASHINI01/mt5-stage2-singlish-si

Model card

From the Hugging Face model README

mt5-stage3-codemixed-si

This model is a fine-tuned version of RASHINI01/mt5-stage2-singlish-si on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3999
Cer: 0.0696

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.99	1.0	1199	0.6023	0.1132
0.8297	2.0	2398	0.5142	0.0945
0.676	3.0	3597	0.4585	0.0850
0.5951	4.0	4796	0.4411	0.0809
0.5332	5.0	5995	0.4227	0.0749
0.4828	6.0	7194	0.4177	0.0721
0.4343	7.0	8393	0.4077	0.0713
0.4247	8.0	9592	0.4047	0.0710
0.4337	9.0	10791	0.3993	0.0695
0.4094	10.0	11990	0.3999	0.0696

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1

Library: transformers
Type: mt5
Created: Jan 2, 2026
Updated: Jan 2, 2026