metadata

license: cc-by-4.0
base_model: bertin-project/bertin-roberta-base-spanish
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: my-model-Bertin-Area
    results: []

my-model-Bertin-Area

This model is a fine-tuned version of bertin-project/bertin-roberta-base-spanish on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.0081
Accuracy: 0.5540
F1: 0.5447
Precision: 0.6083
Recall: 0.5540

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: 30
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.8057	1.0	22	1.6694	0.3094	0.1478	0.0971	0.3094
1.6881	2.0	44	1.5645	0.3741	0.2735	0.2381	0.3741
1.4559	3.0	66	1.3527	0.5612	0.4682	0.4308	0.5612
1.0349	4.0	88	1.2698	0.5108	0.4710	0.5251	0.5108
0.5922	5.0	110	1.3228	0.5396	0.5357	0.5761	0.5396
0.3388	6.0	132	1.3421	0.5324	0.5465	0.6025	0.5324
0.1581	7.0	154	1.6898	0.5396	0.5210	0.6214	0.5396
0.0756	8.0	176	1.5726	0.5971	0.5805	0.5852	0.5971
0.0485	9.0	198	1.6224	0.5971	0.6071	0.6341	0.5971
0.0238	10.0	220	1.9468	0.5683	0.5592	0.6588	0.5683
0.0111	11.0	242	1.8085	0.5540	0.5505	0.5994	0.5540
0.0043	12.0	264	1.7379	0.5755	0.5672	0.6076	0.5755
0.0029	13.0	286	1.9594	0.5612	0.5527	0.6202	0.5612
0.0024	14.0	308	2.0399	0.5683	0.5606	0.6429	0.5683
0.0021	15.0	330	1.9871	0.5540	0.5447	0.6083	0.5540
0.002	16.0	352	1.9870	0.5540	0.5447	0.6083	0.5540
0.0018	17.0	374	1.9927	0.5540	0.5447	0.6083	0.5540
0.0018	18.0	396	2.0027	0.5540	0.5447	0.6083	0.5540
0.0017	19.0	418	2.0077	0.5540	0.5447	0.6083	0.5540
0.0017	20.0	440	2.0081	0.5540	0.5447	0.6083	0.5540

Framework versions

Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1