bzhang0426/LLaMA3-70B-qlora-bnb-G06F17-30

sft

This model is a fine-tuned version of unsloth/llama-3-70b-Instruct-bnb-4bit on the patents_G06F17-30_cla_abs_det_sample_940_balance_train_llama-factory dataset. It achieves the following results on the evaluation set:

• Loss: 0.3383

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3548	1.3378	100	0.3388
0.271	2.6756	200	0.3383

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1