labmate-mistral-7b-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: 1.4153

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
0.7983	1.0	1	1.4848
0.7983	2.0	2	1.4791
0.7863	3.0	3	1.4653
0.7603	4.0	4	1.4518
0.7353	5.0	5	1.4395
0.7135	6.0	6	1.4299
0.6955	7.0	7	1.4232
0.6815	8.0	8	1.4188
0.6712	9.0	9	1.4165
0.6642	10.0	10	1.4153

Framework versions

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