roberta-basefinetuned-ner-cadec

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

Loss: 0.3874
Precision: 0.4370
Recall: 0.4719
F1: 0.4538
Accuracy: 0.8849
Adr Precision: 0.3917
Adr Recall: 0.4477
Adr F1: 0.4178
Disease Precision: 0.0
Disease Recall: 0.0
Disease F1: 0.0
Drug Precision: 0.7184
Drug Recall: 0.7576
Drug F1: 0.7375
Finding Precision: 0.1389
Finding Recall: 0.1111
Finding F1: 0.1235
Symptom Precision: 0.2353
Symptom Recall: 0.1481
Symptom F1: 0.1818
B-adr Precision: 0.6259
B-adr Recall: 0.6488
B-adr F1: 0.6371
B-disease Precision: 0.0
B-disease Recall: 0.0
B-disease F1: 0.0
B-drug Precision: 0.8589
B-drug Recall: 0.8485
B-drug F1: 0.8537
B-finding Precision: 0.4
B-finding Recall: 0.1778
B-finding F1: 0.2462
B-symptom Precision: 0.2667
B-symptom Recall: 0.16
B-symptom F1: 0.2
I-adr Precision: 0.3877
I-adr Recall: 0.4305
I-adr F1: 0.4079
I-disease Precision: 0.0
I-disease Recall: 0.0
I-disease F1: 0.0
I-drug Precision: 0.7456
I-drug Recall: 0.7636
I-drug F1: 0.7545
I-finding Precision: 0.1429
I-finding Recall: 0.125
I-finding F1: 0.1333
I-symptom Precision: 0.5
I-symptom Recall: 0.1
I-symptom F1: 0.1667
Macro Avg F1: 0.3399
Weighted Avg F1: 0.5527

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Adr Precision	Adr Recall	Adr F1	Drug Precision	Drug Recall	Drug F1	Finding Precision	Finding Recall	Finding F1	Symptom Precision	Symptom Recall	Symptom F1	B-adr Precision	B-adr Recall	B-adr F1	B-drug Precision	B-drug Recall	B-drug F1	B-finding Precision	B-finding Recall	B-finding F1	B-symptom Precision	B-symptom Recall	B-symptom F1	I-adr Precision	I-adr Recall	I-adr F1	I-disease Precision	I-disease Recall	I-disease F1	I-drug Precision	I-drug Recall	I-drug F1	I-finding Precision	I-finding Recall	I-finding F1	I-symptom Precision	I-symptom Recall	I-symptom F1	Macro Avg F1	Weighted Avg F1
No log	1.0	127	0.5344	0.3114	0.2247	0.2611	0.8487	0.1715	0.1505	0.1603	0.98	0.5939	0.7396	0.0	0.0	0.0	0.0	0.0	0.0	0.5933	0.2380	0.3397	1.0	0.5939	0.7452	0.0	0.0	0.0	0.0	0.0	0.0	0.1456	0.1347	0.1399	0.0	0.0	0.0	0.98	0.5939	0.7396	0.0	0.0	0.0	0.0	0.0	0.0	0.1965	0.3329
No log	2.0	254	0.4494	0.3603	0.2946	0.3242	0.8676	0.2676	0.2440	0.2553	0.6519	0.6242	0.6378	0.0	0.0	0.0	0.0	0.0	0.0	0.5703	0.4280	0.4890	1.0	0.6182	0.7640	0.0	0.0	0.0	0.0	0.0	0.0	0.2759	0.2296	0.2506	0.0	0.0	0.0	0.7342	0.7030	0.7183	0.0	0.0	0.0	0.0	0.0	0.0	0.2222	0.4204
No log	3.0	381	0.4357	0.3508	0.3758	0.3629	0.8628	0.2656	0.3431	0.2994	0.7451	0.6909	0.7170	0.0	0.0	0.0	0.0	0.0	0.0	0.5393	0.5662	0.5524	0.9375	0.7273	0.8191	0.0	0.0	0.0	0.0	0.0	0.0	0.2402	0.3113	0.2712	0.0	0.0	0.0	0.7550	0.6909	0.7215	1.0	0.0312	0.0606	0.0	0.0	0.0	0.2425	0.4573
0.5429	4.0	508	0.4086	0.4501	0.4170	0.4329	0.8819	0.3612	0.3890	0.3746	0.7922	0.7394	0.7649	0.0	0.0	0.0	0.0	0.0	0.0	0.5988	0.5816	0.5901	0.9209	0.7758	0.8421	0.0	0.0	0.0	0.0	0.0	0.0	0.3793	0.3642	0.3716	0.0	0.0	0.0	0.82	0.7455	0.7810	1.0	0.0312	0.0606	0.0	0.0	0.0	0.2645	0.5113
0.5429	5.0	635	0.3806	0.4225	0.4457	0.4338	0.8797	0.3398	0.4165	0.3743	0.7805	0.7758	0.7781	0.2	0.0222	0.0400	0.5	0.0370	0.0690	0.5844	0.6180	0.6007	0.8535	0.8121	0.8323	0.5	0.0222	0.0426	0.5	0.04	0.0741	0.3346	0.4018	0.3651	0.1667	0.0769	0.1053	0.8153	0.7758	0.7950	0.2	0.0312	0.0541	0.0	0.0	0.0	0.2869	0.5170
0.5429	6.0	762	0.3902	0.3860	0.4419	0.4121	0.8738	0.3329	0.4239	0.3729	0.6349	0.7273	0.6780	0.0833	0.0222	0.0351	0.4	0.0741	0.125	0.5832	0.6526	0.6159	0.7886	0.8364	0.8118	0.3333	0.0444	0.0784	0.4	0.08	0.1333	0.3198	0.3996	0.3553	0.0588	0.0769	0.0667	0.6910	0.7455	0.7172	0.1	0.0312	0.0476	0.0	0.0	0.0	0.2826	0.5099
0.5429	7.0	889	0.3776	0.4149	0.4594	0.4360	0.8795	0.3595	0.4367	0.3944	0.6949	0.7455	0.7193	0.125	0.0667	0.0870	0.3636	0.1481	0.2105	0.6094	0.6468	0.6276	0.8405	0.8303	0.8354	0.4167	0.1111	0.1754	0.4	0.16	0.2286	0.3443	0.4150	0.3764	0.0	0.0	0.0	0.7326	0.7636	0.7478	0.1905	0.125	0.1509	0.0	0.0	0.0	0.3142	0.5330
0.3019	8.0	1016	0.3892	0.4108	0.4657	0.4365	0.8781	0.3488	0.4404	0.3893	0.75	0.7636	0.7568	0.16	0.0889	0.1143	0.2727	0.1111	0.1579	0.5928	0.6679	0.6282	0.8625	0.8364	0.8492	0.4375	0.1556	0.2295	0.3	0.12	0.1714	0.3357	0.4172	0.3720	0.0	0.0	0.0	0.7875	0.7636	0.7754	0.1667	0.0938	0.1200	0.0	0.0	0.0	0.3146	0.5366
0.3019	9.0	1143	0.3872	0.4463	0.4719	0.4587	0.8845	0.3939	0.4495	0.4199	0.7530	0.7576	0.7553	0.1333	0.0889	0.1067	0.2667	0.1481	0.1905	0.6309	0.6430	0.6369	0.8571	0.8364	0.8466	0.4375	0.1556	0.2295	0.3077	0.16	0.2105	0.3893	0.4349	0.4108	0.0	0.0	0.0	0.7764	0.7576	0.7669	0.16	0.125	0.1404	0.6667	0.1	0.1739	0.3416	0.5540
0.3019	10.0	1270	0.3874	0.4370	0.4719	0.4538	0.8849	0.3917	0.4477	0.4178	0.7184	0.7576	0.7375	0.1389	0.1111	0.1235	0.2353	0.1481	0.1818	0.6259	0.6488	0.6371	0.8589	0.8485	0.8537	0.4	0.1778	0.2462	0.2667	0.16	0.2	0.3877	0.4305	0.4079	0.0	0.0	0.0	0.7456	0.7636	0.7545	0.1429	0.125	0.1333	0.5	0.1	0.1667	0.3399	0.5527

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

mireiaplalis/roberta-basefinetuned-ner-cadec

roberta-basefinetuned-ner-cadec

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种