distilkobert-KEmoFact-0925

This model is a fine-tuned version of monologg/distilkobert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7166
• Precision: 0.0137
• Recall: 0.0022
• F1: 0.0039
• Accuracy: 0.6299
• Jaccard Scores: 0.0916
• Cls Accuracy: 0.0345

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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	Precision	Recall	F1	Accuracy	Jaccard Scores	Cls Accuracy
No log	1.0	414	1.7574	0.0	0.0	0.0	0.6440	0.0022	0.0048
1.87	2.0	828	1.7244	0.0135	0.0017	0.0030	0.6446	0.0675	0.0315
1.7332	3.0	1242	1.6964	0.0	0.0	0.0	0.6450	0.0172	0.0127
1.7095	4.0	1656	1.6881	0.0212	0.0023	0.0041	0.6461	0.0578	0.0309
1.6899	5.0	2070	1.6827	0.0163	0.0023	0.0040	0.6455	0.0732	0.0357

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3