Llama-3.1-8B-Instruct_sft_sg_values_p025_OA_gold

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the sft_sg_values_p025_OA_gold dataset. It achieves the following results on the evaluation set:

• Loss: 0.1856

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.3381	0.1495	250	0.3681
1.0391	0.2990	500	0.2566
1.0006	0.4486	750	0.2180
1.0381	0.5981	1000	0.1998
0.9019	0.7476	1250	0.1898
0.9862	0.8971	1500	0.1862

Framework versions

• PEFT 0.15.2
• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 2.21.0
• Tokenizers 0.21.1