testlink-class

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

• Loss: 0.1523
• Precision: 0.6630
• Recall: 0.7135
• F1: 0.6873
• Accuracy: 0.9745

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: 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	0.2337	0.0	0.0	0.0	0.9440
No log	2.0	58	0.2138	0.2632	0.0585	0.0957	0.9526
No log	3.0	87	0.1586	0.3824	0.1520	0.2176	0.9557
No log	4.0	116	0.1321	0.4444	0.2807	0.3441	0.9635
No log	5.0	145	0.1264	0.4422	0.3801	0.4088	0.9629
No log	6.0	174	0.1228	0.5224	0.4094	0.4590	0.9679
No log	7.0	203	0.1117	0.5706	0.5906	0.5805	0.9690
No log	8.0	232	0.1190	0.4832	0.6725	0.5623	0.9658
No log	9.0	261	0.1130	0.6022	0.6374	0.6193	0.9712
No log	10.0	290	0.1230	0.6032	0.6667	0.6333	0.9715
No log	11.0	319	0.1264	0.6122	0.7018	0.6540	0.9712
No log	12.0	348	0.1370	0.5224	0.7485	0.6154	0.9657
No log	13.0	377	0.1259	0.6122	0.7018	0.6540	0.9726
No log	14.0	406	0.1375	0.5447	0.7485	0.6305	0.9692
No log	15.0	435	0.1379	0.6384	0.6608	0.6494	0.9728
No log	16.0	464	0.1398	0.5865	0.7135	0.6438	0.9715
No log	17.0	493	0.1470	0.5775	0.7193	0.6406	0.9706
0.086	18.0	522	0.1576	0.5446	0.7135	0.6177	0.9684
0.086	19.0	551	0.1489	0.6354	0.6725	0.6534	0.9725
0.086	20.0	580	0.1544	0.6591	0.6784	0.6686	0.9730
0.086	21.0	609	0.1489	0.6349	0.7018	0.6667	0.9734
0.086	22.0	638	0.1488	0.6821	0.6901	0.6860	0.9747
0.086	23.0	667	0.1523	0.5953	0.7485	0.6632	0.9717
0.086	24.0	696	0.1475	0.6543	0.7193	0.6852	0.9747
0.086	25.0	725	0.1507	0.6740	0.7135	0.6932	0.9752
0.086	26.0	754	0.1518	0.6703	0.7135	0.6912	0.9745
0.086	27.0	783	0.1517	0.6893	0.7135	0.7011	0.9754
0.086	28.0	812	0.1521	0.6524	0.7135	0.6816	0.9739
0.086	29.0	841	0.1521	0.6595	0.7135	0.6854	0.9743
0.086	30.0	870	0.1523	0.6630	0.7135	0.6873	0.9745

Framework versions

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