shawgpt-ft

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1847

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2637	0.9992	652	1.1808
1.142	2.0	1305	1.1452
1.0811	2.9992	1957	1.1300
1.0268	4.0	2610	1.1262
0.9815	4.9992	3262	1.1269
0.9389	6.0	3915	1.1323
0.9061	6.9992	4567	1.1498
0.8749	8.0	5220	1.1575
0.8523	8.9992	5872	1.1676
0.8351	9.9923	6520	1.1847

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.1.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1