roberta_reman

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

• Loss: 0.4272
• F1: 0.7004
• Roc Auc: 0.7862
• Accuracy: 0.4330
• Recall: 0.6831
• Precision: 0.7185

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy	Recall	Precision
No log	1.0	113	0.4673	0.5668	0.6955	0.2990	0.4930	0.6667
No log	2.0	226	0.4187	0.6397	0.7403	0.3918	0.5563	0.7524
No log	3.0	339	0.4272	0.7004	0.7862	0.4330	0.6831	0.7185
No log	4.0	452	0.4191	0.6566	0.7539	0.3918	0.6127	0.7073
0.3529	5.0	565	0.4246	0.6788	0.7706	0.4124	0.6549	0.7045

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+rocm5.2
• Datasets 2.8.0
• Tokenizers 0.13.2