gpad-v22-taskA-entropy-only

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0287
• Accuracy: 0.9934
• F1 Macro: 0.9933
• F1 Weighted: 0.9934
• Precision Macro: 0.9948
• Recall Macro: 0.9917

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: 16
• eval_batch_size: 12
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Recall Macro
0.0413	1.0	2736	0.0266	0.9929	0.9927	0.9929	0.9935	0.9918
0.0206	2.0	5472	0.0258	0.9935	0.9933	0.9935	0.9946	0.9920
0.0133	3.0	8208	0.0258	0.9939	0.9938	0.9939	0.9954	0.9922
0.0095	4.0	10944	0.0287	0.9934	0.9933	0.9934	0.9948	0.9917

Framework versions

• Transformers 4.41.0
• Pytorch 2.8.0+cu126
• Datasets 4.3.0
• Tokenizers 0.19.1