Modelpublic

fedeortegariba/roberta-es-clinical-trials-ner-fd-text_cl

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face

0likes5downloads

Model Card

roberta-es-clinical-trials-ner-fd-text_cl

This model is a fine-tuned version of lcampillos/roberta-es-clinical-trials-ner on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.0955
—Accuracy: 0.8961
—Recall: 0.9353
—Precision: 0.8926
—F1: 0.9134

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
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
No log	1.0	231	0.2599	0.9107	0.9273	0.9209	0.9241
No log	2.0	462	0.4050	0.9008	0.9482	0.8897	0.9180
0.1696	3.0	693	0.5082	0.8944	0.9412	0.8857	0.9126
0.1696	4.0	924	0.7025	0.8821	0.9323	0.8748	0.9026
0.0363	5.0	1155	0.6880	0.9026	0.9432	0.8959	0.9190
0.0363	6.0	1386	0.6909	0.9096	0.9263	0.9199	0.9231
0.0051	7.0	1617	0.8435	0.8938	0.9462	0.8813	0.9126
0.0051	8.0	1848	0.9259	0.8891	0.9452	0.8755	0.9090
0.0085	9.0	2079	0.7661	0.9043	0.9253	0.9126	0.9189
0.0085	10.0	2310	0.8466	0.8915	0.9452	0.8787	0.9107
0.0063	11.0	2541	0.8288	0.9043	0.9183	0.9183	0.9183
0.0063	12.0	2772	0.9942	0.8827	0.9472	0.8653	0.9044
0.009	13.0	3003	0.5731	0.9294	0.9223	0.9556	0.9387
0.009	14.0	3234	0.7689	0.9084	0.9402	0.9068	0.9232
0.009	15.0	3465	1.2144	0.8687	0.9532	0.8432	0.8948
0.0017	16.0	3696	0.9313	0.8956	0.9283	0.8970	0.9124
0.0017	17.0	3927	0.8994	0.9049	0.9213	0.9167	0.9190
0.001	18.0	4158	0.9995	0.8956	0.9323	0.8940	0.9127
0.001	19.0	4389	1.0237	0.8932	0.9333	0.8898	0.9110
0.0007	20.0	4620	1.0355	0.8938	0.9373	0.8877	0.9118
0.0007	21.0	4851	1.0372	0.8944	0.9343	0.8908	0.9120
0.0006	22.0	5082	1.0451	0.8944	0.9343	0.8908	0.9120
0.0006	23.0	5313	1.0461	0.8944	0.9343	0.8908	0.9120
0.0004	24.0	5544	1.0582	0.8932	0.9343	0.8891	0.9111
0.0004	25.0	5775	1.0680	0.8944	0.9373	0.8886	0.9123
0.0008	26.0	6006	1.0828	0.8921	0.9343	0.8874	0.9102
0.0008	27.0	6237	1.0875	0.8932	0.9442	0.8819	0.9120
0.0008	28.0	6468	1.0394	0.8961	0.9223	0.9025	0.9123
0.0022	29.0	6699	1.0938	0.8961	0.9353	0.8926	0.9134
0.0022	30.0	6930	1.0955	0.8961	0.9353	0.8926	0.9134

Framework versions

—Transformers 4.51.3
—Pytorch 2.6.0+cu124
—Datasets 3.5.0
—Tokenizers 0.21.1