testlink-class-3

This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1443
• Precision: 0.5833
• Recall: 0.6550
• F1: 0.6171
• Accuracy: 0.9730

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: 7.5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	29	0.2830	0.0	0.0	0.0	0.9440
No log	2.0	58	0.2789	0.0	0.0	0.0	0.9440
No log	3.0	87	0.2388	0.0	0.0	0.0	0.9440
No log	4.0	116	0.2080	0.0	0.0	0.0	0.9440
No log	5.0	145	0.2335	0.0167	0.0058	0.0087	0.9322
No log	6.0	174	0.1889	0.0	0.0	0.0	0.9440
No log	7.0	203	0.1553	0.3469	0.1988	0.2528	0.9506
No log	8.0	232	0.1491	0.5	0.2339	0.3187	0.9576
No log	9.0	261	0.1604	0.4872	0.2222	0.3052	0.9605
No log	10.0	290	0.1347	0.4733	0.3626	0.4106	0.9587
No log	11.0	319	0.1391	0.5165	0.2749	0.3588	0.9605
No log	12.0	348	0.1392	0.4848	0.3743	0.4224	0.9633
No log	13.0	377	0.1306	0.4706	0.3743	0.4169	0.9636
No log	14.0	406	0.1382	0.4774	0.4327	0.4540	0.9642
No log	15.0	435	0.1368	0.4734	0.5205	0.4958	0.9655
No log	16.0	464	0.1316	0.5052	0.5731	0.5370	0.9666
No log	17.0	493	0.1333	0.4852	0.6725	0.5637	0.9660
0.1607	18.0	522	0.1379	0.56	0.5731	0.5665	0.9695
0.1607	19.0	551	0.1534	0.5941	0.5906	0.5924	0.9706
0.1607	20.0	580	0.1294	0.5606	0.6491	0.6016	0.9712
0.1607	21.0	609	0.1403	0.5231	0.6608	0.5840	0.9704
0.1607	22.0	638	0.1429	0.6044	0.6433	0.6232	0.9719
0.1607	23.0	667	0.1411	0.5825	0.6608	0.6192	0.9719
0.1607	24.0	696	0.1339	0.5631	0.6784	0.6154	0.9708
0.1607	25.0	725	0.1345	0.5825	0.6608	0.6192	0.9721
0.1607	26.0	754	0.1464	0.5833	0.6550	0.6171	0.9717
0.1607	27.0	783	0.1403	0.5672	0.6667	0.6129	0.9715
0.1607	28.0	812	0.1445	0.5934	0.6316	0.6119	0.9725
0.1607	29.0	841	0.1433	0.5588	0.6667	0.608	0.9715
0.1607	30.0	870	0.1443	0.5833	0.6550	0.6171	0.9730

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3