results

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

• Loss: 0.7842
• Accuracy: 0.6945

Model description

classify text to ["very negative", "negative", "neutral", "positive", "very positive"] if corresponding to labels [0,1,2,3,4]

Intended uses & limitations

More information needed

Training and evaluation data

used dataset from stanford sentiment analysis

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8692	1.0	11962	0.7449	0.6901
0.6567	2.0	23924	0.7272	0.6992
0.5388	3.0	35886	0.7842	0.6945

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1