mistral-aws-case-studies-blogs

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.6718

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
1.8733	0.0985	20	1.8334
1.7728	0.1970	40	1.7412
1.7035	0.2956	60	1.7064
1.6887	0.3941	80	1.6871
1.6354	0.4926	100	1.6718

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1