MBERT_uncased_GeneralizedCrossEntropy_full_ft

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

• Accuracy: 0.802
• F1: 0.8584
• Precision: 0.8310
• Recall: 0.8876
• Roc Auc: 0.7555
• Loss: 0.2729

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
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Accuracy	F1	Precision	Recall	Roc Auc	Validation Loss
No log	0.992	62	0.77	0.8487	0.7642	0.9541	0.6700	0.3336
0.3578	2.0	125	0.805	0.8567	0.8511	0.8624	0.7738	0.2695
0.3578	2.976	186	0.802	0.8584	0.8310	0.8876	0.7555	0.2729

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3