shawgpt-ft

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: 0.7806

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
1.1706	0.9919	92	1.0061
0.9987	1.9946	185	0.9524
0.9563	2.9973	278	0.9146
0.9325	3.9919	368	0.8862
0.9031	4.9919	460	0.8586
0.8689	5.9946	553	0.8344
0.8449	6.9973	646	0.8135
0.8345	7.9919	736	0.7974
0.8167	8.9919	828	0.7855
0.7919	9.9838	920	0.7806

Framework versions

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