t5-small-xasqp-rest16

arus05/t5-small-xasqp-rest16

t5-small-xasqp-rest16 is a machine learning model from arus05. 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

Public

Parameters

300M

24 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 98%

At a glance

Library: transformers
License: apache-2.0
Model type: mt5
Access: Public
Created: Jul 2, 2025
Updated: Jul 2, 2025
SHA: 06dec627

Base models

google/mt5-small

Model card

From the Hugging Face model README

t5-small-xasqp-rest16

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3982
Precision: 0.3771
Recall: 0.4208
F1: 0.3977

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: 0.00015
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	92	0.9713	0.0339	0.0528	0.0413
No log	2.0	184	0.6932	0.0606	0.1567	0.0875
No log	3.0	276	0.5689	0.1143	0.184	0.141
No log	4.0	368	0.5124	0.1451	0.2658	0.1877
No log	5.0	460	0.4812	0.1991	0.3015	0.2398
1.289	6.0	552	0.4646	0.2299	0.322	0.2683
1.289	7.0	644	0.4442	0.2649	0.3629	0.3063
1.289	8.0	736	0.4356	0.2649	0.3629	0.3063
1.289	9.0	828	0.4324	0.2855	0.3697	0.3222
1.289	10.0	920	0.4328	0.2932	0.3731	0.3283
0.5244	11.0	1012	0.4202	0.3546	0.3697	0.362
0.5244	12.0	1104	0.4187	0.2877	0.3935	0.3324
0.5244	13.0	1196	0.4072	0.3338	0.3901	0.3598
0.5244	14.0	1288	0.4126	0.3333	0.4072	0.3666
0.5244	15.0	1380	0.4076	0.3614	0.402	0.3806
0.5244	16.0	1472	0.4035	0.374	0.4123	0.3922
0.3906	17.0	1564	0.4032	0.3559	0.4208	0.3856
0.3906	18.0	1656	0.4006	0.3594	0.4157	0.3855
0.3906	19.0	1748	0.3987	0.3832	0.4191	0.4003
0.3906	20.0	1840	0.3982	0.3771	0.4208	0.3977

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

Library: transformers
Type: mt5
License: apache-2.0
Created: Jul 2, 2025
Updated: Jul 2, 2025