llama-3.1-fine-tuned-model

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5942

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7852	0.2004	386	1.6317
1.6943	0.4008	772	1.6113
1.6306	0.6012	1158	1.6008
1.4606	0.8017	1544	1.5942

Framework versions

• PEFT 0.13.1
• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 3.0.0
• Tokenizers 0.19.1