Mistral-7B-Instruct-v0.2-GPTQ_retrained_NF_ToN_IoT_and_IoV

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2868

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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
3.3006	1.0	6	2.3850
2.7433	2.0	12	2.2173
2.0996	3.0	18	2.0360
1.8643	4.0	24	1.8737
1.6957	5.0	30	1.6282
1.5218	6.0	36	1.3941
1.3533	7.0	42	1.1838
1.2254	8.0	48	0.9170
1.0833	9.0	54	0.7903
0.9952	10.0	60	0.6717
0.9268	11.0	66	0.5796
0.8677	12.0	72	0.5221
0.8085	13.0	78	0.4615
0.7681	14.0	84	0.3964
0.7376	15.0	90	0.3510
0.7131	16.0	96	0.3303
0.6965	17.0	102	0.3086
0.6863	18.0	108	0.2997
0.677	19.0	114	0.2917
0.6732	20.0	120	0.2868

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.1.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1