vit5-base_sentiment

This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8273
• F1: 0.6438
• Accuracy: 0.6875

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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	Accuracy
0.8932	0.9984	312	0.7780	0.6134	0.669
0.7353	2.0	625	0.7549	0.6252	0.6745
0.6538	2.9984	937	0.7768	0.6320	0.6805
0.5827	4.0	1250	0.7904	0.6379	0.6865
0.5204	4.992	1560	0.8273	0.6438	0.6875

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.19.1