metadata

base_model: plncmm/beto-clinical-wl-es
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: beto-clinical-wl-es-ner
    results: []

beto-clinical-wl-es-ner

This model is a fine-tuned version of plncmm/beto-clinical-wl-es on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3299
Precision: 0.8665
Recall: 0.9037
F1: 0.8847
Accuracy: 0.9418

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	280	0.2544	0.8328	0.8489	0.8408	0.9247
0.3847	2.0	560	0.2645	0.8170	0.8667	0.8411	0.9236
0.3847	3.0	840	0.2372	0.8512	0.8726	0.8617	0.9338
0.1056	4.0	1120	0.2749	0.8403	0.8963	0.8674	0.9327
0.1056	5.0	1400	0.2895	0.8557	0.9052	0.8798	0.9354
0.057	6.0	1680	0.2630	0.8707	0.9081	0.8891	0.9408
0.057	7.0	1960	0.2759	0.8614	0.9022	0.8813	0.9418
0.031	8.0	2240	0.3099	0.8689	0.9037	0.8860	0.9408
0.0222	9.0	2520	0.3506	0.8597	0.9081	0.8833	0.9386
0.0222	10.0	2800	0.2962	0.8693	0.8963	0.8826	0.9421
0.0169	11.0	3080	0.3218	0.8709	0.8993	0.8848	0.9432
0.0169	12.0	3360	0.3459	0.8672	0.9096	0.8879	0.9400
0.0134	13.0	3640	0.3299	0.8661	0.9007	0.8831	0.9413
0.0134	14.0	3920	0.3318	0.8707	0.9081	0.8891	0.9429
0.0126	15.0	4200	0.3299	0.8665	0.9037	0.8847	0.9418

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1