murat_nerscratch2604model

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1060
• Precision: 0.9449
• Recall: 0.9513
• F1: 0.9481

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: 1e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.8129	0.9999	5060	0.1675	0.9275	0.9131	0.9201
0.329	1.9999	10120	0.1140	0.9424	0.9458	0.9441
0.329	2.9998	15180	0.1060	0.9449	0.9513	0.9481

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1