SFT-unsloth-mrd3-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: 0.5939

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: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2461	0.2139	10	0.9010
0.8442	0.4278	20	0.7990
0.7786	0.6417	30	0.7539
0.7424	0.8556	40	0.7238
0.7116	1.0695	50	0.6946
0.6793	1.2834	60	0.6642
0.6488	1.4973	70	0.6347
0.6163	1.7112	80	0.6082
0.5921	1.9251	90	0.5939

Framework versions

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