llama-3-8b-hf-sm-lora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 2.3198

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
2.7527	1.0	208	2.7346
2.4709	2.0	416	2.4446
2.3948	3.0	624	2.3475
2.2662	4.0	832	2.3198

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1