Finetune-test4

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1223

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.767	0.9956	56	0.5333
0.4313	1.9911	112	0.4449
0.3107	2.9867	168	0.4640
0.2198	4.0	225	0.5196
0.1633	4.9956	281	0.5811
0.1209	5.9911	337	0.6468
0.0944	6.9867	393	0.6891
0.0745	8.0	450	0.7297
0.064	8.9956	506	0.7844
0.0557	9.9911	562	0.8384
0.0489	10.9867	618	0.8632
0.0433	12.0	675	0.9223
0.0413	12.9956	731	0.9526
0.0389	13.9911	787	0.9552
0.0375	14.9867	843	1.0303
0.0355	16.0	900	1.0489
0.0355	16.9956	956	1.0804
0.0347	17.9911	1012	1.0983
0.0341	18.9867	1068	1.1147
0.0328	19.9111	1120	1.1223

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.0.1+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1