results

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.1652
• Accuracy: 0.0431

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• 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
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.6185	0.9970	82	2.6059	0.0323
2.4398	1.9939	164	2.6266	0.0582
2.4161	2.9909	246	2.3381	0.0905
2.3511	4.0	329	2.2989	0.1013
2.2733	4.9970	411	2.2880	0.0323
2.3463	5.9939	493	2.1652	0.0431
2.253	6.9909	575	2.1971	0.0431
2.2243	7.9757	656	2.1854	0.1272

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3