qlora

This model is a fine-tuned version of TheBloke/Llama-2-13B-chat-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1030

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
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0135	0.9412	12	0.4043
0.145	1.9608	25	0.1342
0.0703	2.9804	38	0.1080
0.0531	4.0	51	0.1023
0.0532	4.9412	63	0.1040
0.0476	5.9608	76	0.1037
0.0459	6.9804	89	0.1028
0.0449	7.8431	100	0.1030

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1