finetune-bert-sentiment-analysis

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: 0.2378
• Accuracy: 0.94
• F1score: 0.9455

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1score
0.5361	1.0	100	0.4738	0.865	0.8811
0.1125	2.0	200	0.2378	0.94	0.9455
0.0357	3.0	300	0.2857	0.945	0.9507

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.0
• Datasets 3.0.2
• Tokenizers 0.20.1