Rodrigo1771/bsc-bio-ehr-es-distemist-word2vec-85-ner

output

This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the Rodrigo1771/distemist-85-ner dataset. It achieves the following results on the evaluation set:

• Loss: 0.1424
• Precision: 0.8032
• Recall: 0.8049
• F1: 0.8040
• Accuracy: 0.9765

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	0.9990	499	0.0739	0.7271	0.7953	0.7596	0.9731
0.105	2.0	999	0.0908	0.7436	0.7890	0.7656	0.9729
0.0448	2.9990	1498	0.0930	0.7676	0.7990	0.7830	0.9744
0.0255	4.0	1998	0.1052	0.7806	0.7983	0.7894	0.9757
0.0164	4.9990	2497	0.1100	0.7756	0.8007	0.7879	0.9750
0.0112	6.0	2997	0.1266	0.7869	0.8124	0.7994	0.9768
0.0073	6.9990	3496	0.1288	0.7929	0.8009	0.7969	0.9763
0.0054	8.0	3996	0.1424	0.8032	0.8049	0.8040	0.9765
0.0038	8.9990	4495	0.1455	0.7901	0.8042	0.7971	0.9765
0.0028	9.9900	4990	0.1497	0.7898	0.8072	0.7984	0.9768

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1