bert-base-multilingual-cased-finetuned-twitter_sentiment

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

• Loss: 0.0045
• F1-score: 0.9985

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1-score
0.1961	1.0	1080	0.0873	0.9819
0.0918	2.0	2160	0.0252	0.9935
0.0737	3.0	3240	0.0073	0.9985
0.0298	4.0	4320	0.0087	0.9981
0.01	5.0	5400	0.0045	0.9985

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1