sefa-alper/turkish-sentiment-distilbert-v3

Bert Turkish Sentiment

This model is a fine-tuned version of dbmdz/distilbert-base-turkish-cased on the Sentiment-Analysis-Turkish-DistiBert dataset. It achieves the following results on the evaluation set:

• Loss: 0.4475

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4537	0.5663	500	0.3643
0.3209	1.1325	1000	0.4112
0.2617	1.6988	1500	0.3926
0.207	2.2650	2000	0.4289
0.1546	2.8313	2500	0.4475

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1