bert-finnish-sentiment-analysis-v2

This model is a fine-tuned version of TurkuNLP/bert-base-finnish-uncased-v1 on the nisancoskun/finnish_sentiment_data dataset. It achieves the following results on the evaluation set:

• Loss: 0.2362
• Accuracy: 0.9578

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	Accuracy
0.3163	1.0	994	0.2892	0.9283
0.1355	2.0	1988	0.2663	0.9470
0.037	3.0	2982	0.2362	0.9578

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.13.3