NEW_trained_serbian

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

• Loss: 0.0749
• Precision: 0.8652
• Recall: 0.9028
• F1: 0.8836
• Accuracy: 0.9820

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	208	0.0799	0.8002	0.8599	0.8290	0.9742
No log	2.0	416	0.0733	0.8322	0.8979	0.8638	0.9802
0.0902	3.0	624	0.0709	0.8736	0.9003	0.8867	0.9829
0.0902	4.0	832	0.0749	0.8652	0.9028	0.8836	0.9820

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2