Mistral-7B-Instruct-v0.2-GPTQ_finetune_s1000

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: 0.6456

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
1.2303	0.9829	43	0.8563
0.6964	1.9886	87	0.7045
0.6032	2.9943	131	0.6661
0.558	4.0	175	0.6472
0.5376	4.9829	218	0.6400
0.4962	5.9886	262	0.6360
0.4754	6.9943	306	0.6359
0.4593	8.0	350	0.6393
0.456	8.9829	393	0.6430
0.4305	9.8286	430	0.6456

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1