MBERT_uncased_SquaredBCEWithLogitsLoss_lora

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:

• Loss: 0.2549
• Accuracy: 0.626
• F1: 0.7674
• Precision: 0.6980
• Recall: 0.8522
• Roc Auc: 0.4424

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: 4
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
No log	0.992	31	0.2593	0.333	0.4007	0.5733	0.3080	0.3533
No log	1.984	62	0.2560	0.584	0.7309	0.6873	0.7804	0.4246
No log	2.976	93	0.2549	0.626	0.7674	0.6980	0.8522	0.4424

Framework versions

• PEFT 0.13.3.dev0
• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3