bzhang0426/LLaMA3-70B-qlora-bnb-A61K

A61K

This model is a fine-tuned version of unsloth/llama-3-70b-Instruct-bnb-4bit on the patents_A61K_cla_abs_det_sample_2100_balance_train_llama-factory dataset. It achieves the following results on the evaluation set:

• Loss: 0.3475

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: 0.0003
• 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
• lr_scheduler_warmup_steps: 100
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3573	0.4938	100	0.3475
0.3841	0.9877	200	0.3884
0.3648	1.4815	300	0.3678
0.3604	1.9753	400	0.3584
0.3435	2.4691	500	0.3570
0.3379	2.9630	600	0.3496

Framework versions

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