final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds-ner

This model is a fine-tuned version of manucos/final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3148
• Precision: 0.8725
• Recall: 0.9022
• F1: 0.8871
• Accuracy: 0.9419

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	280	0.3056	0.7819	0.8444	0.8120	0.9198
0.4846	2.0	560	0.2545	0.8126	0.88	0.8450	0.9360
0.4846	3.0	840	0.2269	0.8671	0.8889	0.8778	0.9414
0.1366	4.0	1120	0.2519	0.8225	0.8993	0.8592	0.9372
0.1366	5.0	1400	0.2449	0.8472	0.9037	0.8746	0.9445
0.0788	6.0	1680	0.2839	0.8725	0.9022	0.8871	0.9419
0.0788	7.0	1960	0.2849	0.8631	0.8963	0.8794	0.9386
0.0441	8.0	2240	0.2987	0.8736	0.9007	0.8869	0.9397
0.0335	9.0	2520	0.3192	0.8602	0.9022	0.8807	0.9377
0.0335	10.0	2800	0.3094	0.8734	0.8993	0.8861	0.9414
0.0242	11.0	3080	0.3233	0.8748	0.9007	0.8876	0.9383
0.0242	12.0	3360	0.3215	0.8764	0.9037	0.8899	0.9417
0.0189	13.0	3640	0.3155	0.8684	0.8993	0.8836	0.9405
0.0189	14.0	3920	0.3156	0.8725	0.9022	0.8871	0.9425
0.0172	15.0	4200	0.3148	0.8725	0.9022	0.8871	0.9419

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1