You can deploy this model and start earning money today!

diogocarapito/
text-to-icpc2-bert-base-portuguese-cased

Name: text-to-icpc2-bert-base-portuguese-cased
Availability: InStock

safetensors

bert

generated_from_trainer

neuralmind/bert-base-portuguese-cased

finetune

mit

Views

No views yet

text-to-icpc2-bert-base-portuguese-cased

This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6597
Accuracy: 0.9062
Top3 Accuracy: 0.9631
Top5 Accuracy: 0.9727
Macro F1: 0.9053

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: 32
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Top3 Accuracy	Top5 Accuracy	Macro F1
6.384	1.0	452	5.9101	0.1426	0.2523	0.3115	0.0771
5.216	2.0	904	4.5138	0.3786	0.5691	0.6533	0.2705
4.0909	3.0	1356	3.4823	0.5411	0.7325	0.7965	0.4349
2.9031	4.0	1808	2.7509	0.6245	0.7998	0.8419	0.5317
2.2735	5.0	2260	2.2261	0.6837	0.8300	0.8704	0.6195
1.7934	6.0	2712	1.8777	0.7184	0.8446	0.8862	0.6678
1.4213	7.0	3164	1.6175	0.7391	0.8632	0.8923	0.6932
1.0679	8.0	3616	1.4651	0.7508	0.8729	0.8981	0.7133
0.8886	9.0	4068	1.3606	0.7566	0.8737	0.9017	0.7207
0.7452	10.0	4520	1.3072	0.7629	0.8779	0.9039	0.7300
0.6492	11.0	4972	1.2686	0.7682	0.8801	0.9031	0.7355
0.5856	12.0	5424	1.2568	0.7660	0.8806	0.9045	0.7344

Framework versions

Transformers 4.44.0
Pytorch 2.2.2
Datasets 4.8.3
Tokenizers 0.19.1

diogocarapito/text-to-icpc2-bert-base-portuguese-cased

text-to-icpc2-bert-base-portuguese-cased

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

diogocarapito/
text-to-icpc2-bert-base-portuguese-cased