metadata

base_model: MMG/mlm-spanish-roberta-base
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-finetuned-intention-prediction-es
    results: []

roberta-finetuned-intention-prediction-es

This model is a fine-tuned version of MMG/mlm-spanish-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7531
Precision: 0.7331
Recall: 0.7331
F1: 0.7331
Accuracy: 0.7232

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: 16
eval_batch_size: 16
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	Precision	Recall	F1	Accuracy
1.878	1.0	102	1.2561	0.6630	0.6630	0.6630	0.6464
1.0292	2.0	204	1.1108	0.7005	0.7005	0.7005	0.6855
0.7035	3.0	306	1.0948	0.7215	0.7215	0.7215	0.7067
0.4985	4.0	408	1.0831	0.7177	0.7177	0.7177	0.7045
0.3357	5.0	510	1.1830	0.7288	0.7288	0.7288	0.7145
0.2414	6.0	612	1.2706	0.7194	0.7194	0.7194	0.7060
0.1712	7.0	714	1.3205	0.7328	0.7328	0.7328	0.7223
0.1238	8.0	816	1.4237	0.7290	0.7290	0.7290	0.7177
0.0845	9.0	918	1.4820	0.7271	0.7271	0.7271	0.7168
0.0627	10.0	1020	1.5436	0.7204	0.7204	0.7204	0.7099
0.0509	11.0	1122	1.5653	0.7311	0.7311	0.7311	0.7212
0.0366	12.0	1224	1.5724	0.7268	0.7268	0.7268	0.7175
0.023	13.0	1326	1.6088	0.7273	0.7273	0.7273	0.7170
0.02	14.0	1428	1.6797	0.7346	0.7346	0.7346	0.7239
0.0144	15.0	1530	1.7203	0.7369	0.7369	0.7369	0.7266
0.0103	16.0	1632	1.7330	0.7302	0.7302	0.7302	0.7208
0.0087	17.0	1734	1.7284	0.7293	0.7293	0.7293	0.7194
0.008	18.0	1836	1.7434	0.7380	0.7380	0.7380	0.7280
0.0059	19.0	1938	1.7642	0.7355	0.7355	0.7355	0.7261
0.0055	20.0	2040	1.7531	0.7331	0.7331	0.7331	0.7232

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0