dal-bert-finetuned-emotion

This model is a fine-tuned version of sharif-dal/dal-bert on snappfood's comments dataset.

• 0 -> Positive sentiment
• 1 -> Negative sentiment

It achieves the following results on the evaluation set:

• Loss: 0.2893
• Accuracy: 0.8821
• F1: 0.8820

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: 48
• eval_batch_size: 48
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3131	1.0	1086	0.2859	0.8810	0.8808
0.2506	2.0	2172	0.2893	0.8821	0.8820

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2