slac-new-aroma-upsample_replacement

trungpq/slac-new-aroma-upsample_replacement

slac-new-aroma-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

21% 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: 76c3cda3

Model card

From the Hugging Face model README

slac-new-aroma-upsample_replacement

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

Loss: 0.3607
Accuracy: 0.9606
F1 Macro: 0.9103
Precision Macro: 0.9168
Recall Macro: 0.9041
F1 Micro: 0.9606
Precision Micro: 0.9606
Recall Micro: 0.9606
Total Tf: [1486, 61, 1486, 61]

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: 326
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
0.1406	1.0	327	0.1637	0.9438	0.8845	0.8567	0.9204	0.9438	0.9438	0.9438	[1460, 87, 1460, 87]
0.0621	2.0	654	0.1721	0.9567	0.9036	0.9010	0.9062	0.9567	0.9567	0.9567	[1480, 67, 1480, 67]
0.0255	3.0	981	0.2418	0.9522	0.8929	0.8929	0.8929	0.9522	0.9522	0.9522	[1473, 74, 1473, 74]
0.0123	4.0	1308	0.2581	0.9567	0.9032	0.9023	0.9041	0.9567	0.9567	0.9567	[1480, 67, 1480, 67]
0.0047	5.0	1635	0.2953	0.9573	0.9040	0.9058	0.9023	0.9573	0.9573	0.9573	[1481, 66, 1481, 66]
0.0037	6.0	1962	0.3191	0.9567	0.9015	0.9078	0.8954	0.9567	0.9567	0.9567	[1480, 67, 1480, 67]
0.0042	7.0	2289	0.3480	0.9573	0.9057	0.9006	0.9109	0.9573	0.9573	0.9573	[1481, 66, 1481, 66]
0.0043	8.0	2616	0.3425	0.9573	0.9044	0.9044	0.9044	0.9573	0.9573	0.9573	[1481, 66, 1481, 66]
0.0025	9.0	2943	0.3557	0.9580	0.9061	0.9052	0.9070	0.9580	0.9580	0.9580	[1482, 65, 1482, 65]
0.0004	10.0	3270	0.3851	0.9535	0.8988	0.8877	0.9108	0.9535	0.9535	0.9535	[1475, 72, 1475, 72]
0.0003	11.0	3597	0.3441	0.9619	0.9133	0.9198	0.9070	0.9619	0.9619	0.9619	[1488, 59, 1488, 59]
0.0025	12.0	3924	0.3482	0.9599	0.9094	0.9131	0.9059	0.9599	0.9599	0.9599	[1485, 62, 1485, 62]
0.0005	13.0	4251	0.3609	0.9606	0.9111	0.9138	0.9084	0.9606	0.9606	0.9606	[1486, 61, 1486, 61]
0.0015	14.0	4578	0.3598	0.9612	0.9120	0.9175	0.9067	0.9612	0.9612	0.9612	[1487, 60, 1487, 60]
0.0017	15.0	4905	0.3607	0.9606	0.9103	0.9168	0.9041	0.9606	0.9606	0.9606	[1486, 61, 1486, 61]

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