clinico-xlm-roberta-large-finetuned-augmented1

This model is a fine-tuned version of joheras/xlm-roberta-base-finetuned-clinais on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4632
Precision: 0.5074
Recall: 0.6293
F1: 0.5618
Accuracy: 0.8560

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: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	179	0.6074	0.3003	0.5057	0.3768	0.8147
No log	2.0	358	0.5758	0.3091	0.5263	0.3895	0.8415
0.4921	3.0	537	0.7089	0.3357	0.5503	0.4170	0.8438
0.4921	4.0	716	0.8219	0.3541	0.5789	0.4394	0.8391
0.4921	5.0	895	0.8857	0.4050	0.5950	0.4819	0.8507
0.0628	6.0	1074	0.9386	0.3888	0.5961	0.4706	0.8485
0.0628	7.0	1253	1.0302	0.4072	0.6201	0.4916	0.8458
0.0628	8.0	1432	0.9960	0.4352	0.6144	0.5095	0.8535
0.0195	9.0	1611	1.0593	0.4349	0.6190	0.5109	0.8546
0.0195	10.0	1790	1.1262	0.4366	0.6190	0.5121	0.8512
0.0195	11.0	1969	1.1968	0.4675	0.6178	0.5323	0.8498
0.0085	12.0	2148	1.1940	0.4368	0.6167	0.5114	0.8472
0.0085	13.0	2327	1.1795	0.4670	0.6224	0.5336	0.8588
0.0043	14.0	2506	1.2596	0.4791	0.6281	0.5436	0.8534
0.0043	15.0	2685	1.2958	0.4580	0.6236	0.5281	0.8504
0.0043	16.0	2864	1.2891	0.4977	0.6270	0.5549	0.8533
0.0022	17.0	3043	1.2992	0.4615	0.6178	0.5284	0.8504
0.0022	18.0	3222	1.3102	0.4681	0.5961	0.5244	0.8549
0.0022	19.0	3401	1.2654	0.4485	0.6178	0.5197	0.8602
0.0027	20.0	3580	1.3123	0.4420	0.6064	0.5113	0.8479
0.0027	21.0	3759	1.3100	0.4877	0.6350	0.5517	0.8554
0.0027	22.0	3938	1.3696	0.4683	0.6247	0.5353	0.8532
0.0013	23.0	4117	1.3392	0.4851	0.5973	0.5354	0.8536
0.0013	24.0	4296	1.3680	0.4946	0.6270	0.5530	0.8509
0.0013	25.0	4475	1.4145	0.4914	0.6236	0.5497	0.8512
0.0014	26.0	4654	1.2962	0.5	0.6327	0.5586	0.8634
0.0014	27.0	4833	1.3871	0.4743	0.6327	0.5422	0.8532
0.0014	28.0	5012	1.3761	0.4982	0.6430	0.5614	0.8562
0.0014	29.0	5191	1.3929	0.4764	0.6224	0.5397	0.8501
0.0014	30.0	5370	1.3716	0.4862	0.6270	0.5477	0.8558
0.0006	31.0	5549	1.3881	0.4573	0.6247	0.5280	0.8566
0.0006	32.0	5728	1.3783	0.4688	0.6350	0.5394	0.8591
0.0006	33.0	5907	1.4211	0.5060	0.6293	0.5609	0.8585
0.001	34.0	6086	1.4034	0.4819	0.6236	0.5436	0.8566
0.001	35.0	6265	1.4026	0.5168	0.6339	0.5694	0.8592
0.001	36.0	6444	1.4153	0.4904	0.6419	0.5560	0.8586
0.0003	37.0	6623	1.4071	0.5161	0.6224	0.5643	0.8569
0.0003	38.0	6802	1.4308	0.5046	0.6293	0.5601	0.8562
0.0003	39.0	6981	1.4089	0.5083	0.6339	0.5642	0.8597
0.0001	40.0	7160	1.4522	0.5093	0.6293	0.5629	0.8543
0.0001	41.0	7339	1.4427	0.4964	0.6224	0.5523	0.8545
0.0001	42.0	7518	1.4641	0.4759	0.6213	0.5390	0.8513
0.0001	43.0	7697	1.4405	0.5014	0.6293	0.5581	0.8595
0.0001	44.0	7876	1.4584	0.5060	0.6281	0.5605	0.8555
0.0002	45.0	8055	1.4847	0.5157	0.6201	0.5631	0.8526
0.0002	46.0	8234	1.4545	0.4977	0.6270	0.5549	0.8577
0.0002	47.0	8413	1.4482	0.5106	0.6339	0.5656	0.8570
0.0001	48.0	8592	1.4639	0.5074	0.6281	0.5613	0.8563
0.0001	49.0	8771	1.4643	0.5088	0.6270	0.5618	0.8563
0.0001	50.0	8950	1.4632	0.5074	0.6293	0.5618	0.8560

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.0
Datasets 2.8.0
Tokenizers 0.12.1

joheras/clinico-xlm-roberta-large-finetuned-augmented1

clinico-xlm-roberta-large-finetuned-augmented1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种