finetuned__roberta-clinical-wl-es__augmented-ultrasounds

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

• Loss: 0.6340

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	1.0	198	0.9956
No log	2.0	396	0.8742
No log	3.0	594	0.8004
1.0236	4.0	792	0.7610
1.0236	5.0	990	0.7348
1.0236	6.0	1188	0.7259
1.0236	7.0	1386	0.7036
0.7694	8.0	1584	0.6969
0.7694	9.0	1782	0.6789
0.7694	10.0	1980	0.6774
0.7694	11.0	2178	0.6756
0.7115	12.0	2376	0.6663
0.7115	13.0	2574	0.6564
0.7115	14.0	2772	0.6517
0.7115	15.0	2970	0.6511
0.6834	16.0	3168	0.6383
0.6834	17.0	3366	0.6400
0.6834	18.0	3564	0.6483
0.6834	19.0	3762	0.6439
0.6716	20.0	3960	0.6340

Framework versions

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