metadata

license: apache-2.0
base_model: plncmm/roberta-clinical-wl-es
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-clinical-wl-es-ner
    results: []

roberta-clinical-wl-es-ner

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

Loss: 0.3453
Precision: 0.8647
Recall: 0.8993
F1: 0.8816
Accuracy: 0.9391

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	0.3149	0.7822	0.8356	0.8080	0.9164
0.5325	2.0	560	0.2693	0.8291	0.8696	0.8489	0.9271
0.5325	3.0	840	0.2509	0.8438	0.8726	0.8580	0.9299
0.1484	4.0	1120	0.2511	0.8425	0.9037	0.8721	0.9380
0.1484	5.0	1400	0.2873	0.8371	0.8830	0.8594	0.9307
0.0854	6.0	1680	0.3025	0.8725	0.9022	0.8871	0.9403
0.0854	7.0	1960	0.3040	0.8610	0.8993	0.8797	0.9403
0.0499	8.0	2240	0.3211	0.8683	0.8889	0.8785	0.9363
0.0359	9.0	2520	0.3294	0.8620	0.8978	0.8795	0.9366
0.0359	10.0	2800	0.3374	0.8900	0.8993	0.8946	0.9394
0.0248	11.0	3080	0.3543	0.8712	0.8919	0.8814	0.9372
0.0248	12.0	3360	0.3390	0.8606	0.8963	0.8781	0.9366
0.0209	13.0	3640	0.3337	0.8712	0.9022	0.8865	0.9394
0.0209	14.0	3920	0.3449	0.8698	0.9007	0.8850	0.9391
0.0182	15.0	4200	0.3453	0.8647	0.8993	0.8816	0.9391

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1