llama3-biofunction-finetuned

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5720

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.7553	0.2189	50	2.6617
2.6516	0.4379	100	2.6396
2.7112	0.6568	150	2.6192
2.6746	0.8758	200	2.6106
2.706	1.0920	250	2.6007
2.5584	1.3109	300	2.5934
2.5746	1.5298	350	2.5920
2.587	1.7488	400	2.5800
2.5857	1.9677	450	2.5795
2.4667	2.1839	500	2.5818
2.6714	2.4028	550	2.5705
2.5687	2.6218	600	2.5813
2.5423	2.8407	650	2.5720

Framework versions

• PEFT 0.17.1
• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1