base_model_finetuned_pro_emit_correlations

This model is a fine-tuned version of lupobricco/feel_it_finetuned_pro_emit_multilabel2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2775
• F1: 0.5752
• Roc Auc: 0.7586
• Accuracy: 0.4141

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2322	1.0	1037	0.2371	0.3962	0.6595	0.3436
0.1911	2.0	2074	0.2222	0.4864	0.7128	0.3935
0.1604	3.0	3111	0.2283	0.5354	0.7387	0.3952
0.1339	4.0	4148	0.2300	0.5566	0.7443	0.4261
0.1105	5.0	5185	0.2477	0.5545	0.7438	0.3986
0.0934	6.0	6222	0.2502	0.5723	0.7547	0.4192
0.0781	7.0	7259	0.2584	0.5676	0.7505	0.4158
0.0664	8.0	8296	0.2661	0.5617	0.7513	0.4124
0.0605	9.0	9333	0.2750	0.5684	0.7554	0.4141
0.0516	10.0	10370	0.2775	0.5752	0.7586	0.4141

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1