final-ft__beto-clinical-wl-es__70k-ultrasounds

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

• Loss: 0.5271

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	254	0.8908
No log	2.0	508	0.7526
No log	3.0	762	0.6801
0.9011	4.0	1016	0.6608
0.9011	5.0	1270	0.6265
0.9011	6.0	1524	0.6014
0.9011	7.0	1778	0.5934
0.6433	8.0	2032	0.5762
0.6433	9.0	2286	0.5650
0.6433	10.0	2540	0.5667
0.6433	11.0	2794	0.5629
0.5899	12.0	3048	0.5446
0.5899	13.0	3302	0.5390
0.5899	14.0	3556	0.5454
0.5899	15.0	3810	0.5270
0.5625	16.0	4064	0.5277
0.5625	17.0	4318	0.5387
0.5625	18.0	4572	0.5206
0.5625	19.0	4826	0.5150
0.5508	20.0	5080	0.5271

Framework versions

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