README.md

metadata

license: cc-by-4.0
tags:
  - generated_from_trainer
model-index:
  - name: DISO_SINAI_test1
    results: []

DISO_SINAI_test1

This model is a fine-tuned version of chizhikchi/Spanish_disease_finder on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0807
• Diso Precision: 0.8260
• Diso Recall: 0.8247
• Diso F1: 0.8253
• Diso Number: 4552
• Overall Precision: 0.8260
• Overall Recall: 0.8247
• Overall F1: 0.8253
• Overall Accuracy: 0.9815

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Diso Precision	Diso Recall	Diso F1	Diso Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0629	1.0	2799	0.0573	0.8315	0.8014	0.8162	4552	0.8315	0.8014	0.8162	0.9813
0.0429	2.0	5598	0.0622	0.8228	0.8264	0.8246	4552	0.8228	0.8264	0.8246	0.9815
0.0299	3.0	8397	0.0689	0.8217	0.8251	0.8234	4552	0.8217	0.8251	0.8234	0.9814
0.0214	4.0	11196	0.0807	0.8260	0.8247	0.8253	4552	0.8260	0.8247	0.8253	0.9815

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2