Llama-3.1-8B-Instruct-SFT-700

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_sft_700 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0484

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
1.0723	1.2698	50	0.8589
0.1579	2.5397	100	0.0773
0.0839	3.8095	150	0.0536
0.0861	5.0794	200	0.0506
0.0624	6.3492	250	0.0495
0.0824	7.6190	300	0.0486
0.0931	8.8889	350	0.0484

Framework versions

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