Llama-3.1-8B-Instruct-SFT-600

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_sft_600 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0599

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
0.996	1.4815	50	0.7778
0.1326	2.9630	100	0.0880
0.0931	4.4444	150	0.0636
0.0915	5.9259	200	0.0614
0.0888	7.4074	250	0.0600
0.0653	8.8889	300	0.0599

Framework versions

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