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

This model is a fine-tuned version of BSC-LT/roberta-base-biomedical-clinical-es on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5971

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.9978	229	0.9388
No log	2.0	459	0.8139
No log	2.9978	688	0.7544
0.9622	4.0	918	0.7302
0.9622	4.9978	1147	0.6878
0.9622	6.0	1377	0.6754
0.9622	6.9978	1606	0.6625
0.715	8.0	1836	0.6431
0.715	8.9978	2065	0.6278
0.715	10.0	2295	0.6361
0.715	10.9978	2524	0.6296
0.6597	12.0	2754	0.6164
0.6597	12.9978	2983	0.6117
0.6597	14.0	3213	0.6052
0.6597	14.9978	3442	0.6064
0.6354	16.0	3672	0.6225
0.6354	16.9978	3901	0.5974
0.6354	18.0	4131	0.6010
0.6354	18.9978	4360	0.5816
0.6354	19.9564	4580	0.5971

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1