DistilBERT_trainer_irony

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

• Loss: 1.7540
• Accuracy: 0.6964

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: 16
• 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	Accuracy
No log	1.0	179	1.2815	0.6827
No log	2.0	358	1.4685	0.7047
0.092	3.0	537	1.6756	0.6754
0.092	4.0	716	1.8278	0.6712
0.092	5.0	895	1.8939	0.6723

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2