rlcc-palate-sentences-concat

trungpq/rlcc-palate-sentences-concat

rlcc-palate-sentences-concat 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

29% of all-time downloads

All-time downloads

Public

Parameters

109M

438 MB 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_classifier
Access: Public
Created: May 18, 2025
Updated: May 18, 2025
SHA: 9ffba41c

Model card

From the Hugging Face model README

rlcc-palate-sentences-concat

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

Loss: 2.4310
Accuracy: 0.4244
F1 Macro: 0.3883
Precision Macro: 0.3863
Recall Macro: 0.3970
Total Tf: [174, 236, 994, 236]

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: 79
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro	Total Tf
1.394	1.0	80	1.3439	0.4122	0.1829	0.1791	0.2565	[169, 241, 989, 241]
1.3273	2.0	160	1.3414	0.4195	0.3570	0.4300	0.4148	[172, 238, 992, 238]
1.0648	3.0	240	1.3414	0.3341	0.3323	0.3576	0.3818	[137, 273, 957, 273]
0.8498	4.0	320	1.4105	0.3805	0.3710	0.3827	0.4032	[156, 254, 976, 254]
0.6044	5.0	400	1.5343	0.3805	0.3664	0.3653	0.3916	[156, 254, 976, 254]
0.4662	6.0	480	1.6489	0.4073	0.3700	0.3726	0.3905	[167, 243, 987, 243]
0.3261	7.0	560	1.7789	0.3951	0.3739	0.3724	0.3859	[162, 248, 982, 248]
0.2888	8.0	640	1.9595	0.3805	0.3544	0.3520	0.3643	[156, 254, 976, 254]
0.2103	9.0	720	2.0901	0.4171	0.3874	0.3885	0.3961	[171, 239, 991, 239]
0.1766	10.0	800	2.1652	0.4268	0.3885	0.3864	0.3979	[175, 235, 995, 235]
0.1301	11.0	880	2.1983	0.4268	0.3928	0.3900	0.3967	[175, 235, 995, 235]
0.1138	12.0	960	2.2969	0.4195	0.3852	0.3832	0.3928	[172, 238, 992, 238]
0.0752	13.0	1040	2.4233	0.4073	0.3809	0.3827	0.3905	[167, 243, 987, 243]
0.0706	14.0	1120	2.4180	0.4195	0.3888	0.3879	0.3952	[172, 238, 992, 238]
0.0654	15.0	1200	2.4310	0.4244	0.3883	0.3863	0.3970	[174, 236, 994, 236]

Framework versions

Transformers 4.51.1
Pytorch 2.8.0.dev20250409+cu128
Datasets 3.5.0
Tokenizers 0.21.1

Library: transformers
Type: bert_classifier
Created: May 18, 2025
Updated: May 18, 2025