llama-3.2-350M-fourier_multiplication_dataset_pert

This model is a fine-tuned version of llama_small_config.json on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7478

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: 0.0005
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.3155	0.1415	1000	2.3163
1.9908	0.2831	2000	1.9850
1.9252	0.4246	3000	1.9291
1.8977	0.5661	4000	1.8920
1.7984	0.7076	5000	1.7951
1.7595	0.8492	6000	1.7590
1.7511	0.9907	7000	1.7478

Framework versions

• Transformers 4.48.2
• Pytorch 2.3.1+cu118
• Datasets 3.2.0
• Tokenizers 0.21.0