This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the Rodrigo1771/symptemist-fasttext-9-ner dataset. It achieves the following results on the evaluation set:

Loss: 0.2450
Precision: 0.6660
Recall: 0.7258
F1: 0.6946
Accuracy: 0.9497

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
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.9968	155	0.1485	0.5669	0.6218	0.5931	0.9436
No log	2.0	311	0.1609	0.5623	0.7159	0.6299	0.9409
No log	2.9968	466	0.1635	0.6210	0.7219	0.6677	0.9487
0.1246	4.0	622	0.2047	0.6659	0.6765	0.6712	0.9493
0.1246	4.9968	777	0.2134	0.6562	0.7115	0.6828	0.9480
0.1246	6.0	933	0.2259	0.6518	0.7099	0.6796	0.9494
0.0242	6.9968	1088	0.2450	0.6660	0.7258	0.6946	0.9497
0.0242	8.0	1244	0.2650	0.6491	0.7230	0.6841	0.9491
0.0242	8.9968	1399	0.2745	0.6646	0.7126	0.6878	0.9498
0.0083	9.9678	1550	0.2774	0.6628	0.7187	0.6896	0.9503

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Rodrigo1771/bsc-bio-ehr-es-symptemist-fasttext-9-ner

output

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Rodrigo1771/
bsc-bio-ehr-es-symptemist-fasttext-9-ner