Bigglz/dedup_lora_llama3bllossom

dedup-llama3blossom

This model is a fine-tuned version of MLP-KTLim/llama-3-Korean-Bllossom-8B on the pogny_dedup_instruction, the hana_dedup_instruction and the mango_dedup_instruction datasets. It achieves the following results on the evaluation set:

• Loss: 0.7135
• Accuracy: 0.7834

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 3
• gradient_accumulation_steps: 8
• total_train_batch_size: 384
• total_eval_batch_size: 3
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10.0

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.2.0a0+81ea7a4
• Datasets 2.17.1
• Tokenizers 0.20.1