Llama-3.1-8B-Instruct-SFT-500

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_sft_500 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0781

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8493	1.7778	50	0.8185
0.1595	3.5556	100	0.1123
0.0797	5.3333	150	0.0811
0.0997	7.1111	200	0.0789
0.0896	8.8889	250	0.0781

Framework versions

• PEFT 0.12.0
• Transformers 4.45.2
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.20.0