SFT-unsloth-Llama-3-8B-Instruct

This model is a fine-tuned version of unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2950

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.053	0.4129	20	0.8088
0.757	0.8258	40	0.7216
0.6764	1.2387	60	0.6206
0.5476	1.6516	80	0.4872
0.4231	2.0645	100	0.3801
0.3276	2.4774	120	0.3222
0.2932	2.8903	140	0.2950

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1