privacygpt-1.2

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: 1.3523

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
1.38	1.0000	5772	1.3702
1.3384	1.9999	11544	1.3626
1.325	2.9999	17316	1.3594
1.3157	4.0	23089	1.3574
1.3085	5.0000	28861	1.3557
1.3021	5.9999	34633	1.3546
1.2962	6.9999	40405	1.3538
1.2906	8.0	46178	1.3529
1.2858	9.0000	51950	1.3523
1.2811	9.9996	57720	1.3523

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1