shawgpt-ft

This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5731

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: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
3.4192	1.0	4	3.1584
3.1603	2.0	8	3.0056
3.0463	3.0	12	2.8691
2.908	4.0	16	2.7622
2.8747	5.0	20	2.6774
2.7089	6.0	24	2.6155
2.6608	7.0	28	2.5795
2.6804	7.6154	30	2.5731

Framework versions

• PEFT 0.14.0
• Transformers 4.48.2
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0