Llama3-8B-lora-r-32-finetuned-epoch-3

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

• Loss: 2.3045

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.2164	0.4598	20	2.8644
2.9259	0.9195	40	2.5928
2.6599	1.3793	60	2.4429
2.5461	1.8391	80	2.3427
2.3522	2.2989	100	2.3239
2.3404	2.7586	120	2.3045

Framework versions

• PEFT 0.15.2
• Transformers 4.45.2
• Pytorch 2.5.0+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3