slac-new-palate-upsample_replacement

trungpq/slac-new-palate-upsample_replacement

slac-new-palate-upsample_replacement is a machine learning model from trungpq. 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

31% of all-time downloads

All-time downloads

Public

Parameters

109M

1.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors438 MB · 100%

At a glance

Library: transformers
Model type: bert_model
Access: Public
Created: Sep 10, 2025
Updated: Sep 17, 2025
SHA: 0e319f8f

Model card

From the Hugging Face model README

slac-new-palate-upsample_replacement

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

Loss: 0.4783
Accuracy: 0.9457
F1 Macro: 0.8626
Precision Macro: 0.8890
Recall Macro: 0.8407
F1 Micro: 0.9457
Precision Micro: 0.9457
Recall Micro: 0.9457
Total Tf: [1463, 84, 1463, 84]

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: 64
eval_batch_size: 64
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
lr_scheduler_warmup_steps: 336
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	F1 Micro	Precision Micro	Recall Micro	Total Tf
0.2061	1.0	337	0.1905	0.9386	0.8585	0.8484	0.8694	0.9386	0.9386	0.9386	[1452, 95, 1452, 95]
0.0784	2.0	674	0.2541	0.9270	0.8428	0.8154	0.8791	0.9270	0.9270	0.9270	[1434, 113, 1434, 113]
0.0338	3.0	1011	0.2829	0.9425	0.8611	0.8673	0.8552	0.9425	0.9425	0.9425	[1458, 89, 1458, 89]
0.0276	4.0	1348	0.2982	0.9470	0.8686	0.8861	0.8531	0.9470	0.9470	0.9470	[1465, 82, 1465, 82]
0.0224	5.0	1685	0.3440	0.9438	0.8574	0.8845	0.8349	0.9438	0.9438	0.9438	[1460, 87, 1460, 87]
0.0096	6.0	2022	0.4022	0.9367	0.8460	0.8546	0.8379	0.9367	0.9367	0.9367	[1449, 98, 1449, 98]
0.008	7.0	2359	0.4061	0.9386	0.8503	0.8600	0.8413	0.9386	0.9386	0.9386	[1452, 95, 1452, 95]
0.006	8.0	2696	0.4193	0.9438	0.8588	0.8814	0.8396	0.9438	0.9438	0.9438	[1460, 87, 1460, 87]
0.0012	9.0	3033	0.4604	0.9457	0.8605	0.8942	0.8337	0.9457	0.9457	0.9457	[1463, 84, 1463, 84]
0.003	10.0	3370	0.4691	0.9412	0.8559	0.8677	0.8451	0.9412	0.9412	0.9412	[1456, 91, 1456, 91]
0.0016	11.0	3707	0.4729	0.9457	0.8612	0.8924	0.8360	0.9457	0.9457	0.9457	[1463, 84, 1463, 84]
0.0037	12.0	4044	0.4790	0.9438	0.8581	0.8829	0.8373	0.9438	0.9438	0.9438	[1460, 87, 1460, 87]
0.007	13.0	4381	0.4749	0.9451	0.8621	0.8848	0.8427	0.9451	0.9451	0.9451	[1462, 85, 1462, 85]
0.003	14.0	4718	0.4791	0.9457	0.8626	0.8890	0.8407	0.9457	0.9457	0.9457	[1463, 84, 1463, 84]
0.001	15.0	5055	0.4783	0.9457	0.8626	0.8890	0.8407	0.9457	0.9457	0.9457	[1463, 84, 1463, 84]

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

Library: transformers
Type: bert_model
Created: Sep 10, 2025
Updated: Sep 17, 2025