distilbert-helpdesk-sentiment

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2184
• Accuracy: 0.9444
• F1: 0.9438

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: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.8850	100	0.3924	0.8333	0.8306
No log	1.7699	200	0.2473	0.9111	0.9099
No log	2.6549	300	0.2417	0.9	0.8965
No log	3.5398	400	0.1576	0.9556	0.9552
0.3432	4.4248	500	0.1598	0.9556	0.9552
0.3432	5.3097	600	0.2184	0.9444	0.9438

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1