mistral-7b-instruct-v0.2-advisegpt-v0.1

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.5297

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: 2e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 15
• total_train_batch_size: 90
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2215	0.9819	47	0.6548
0.1586	1.9847	95	0.5741
0.1421	2.9875	143	0.5422
0.1334	3.9903	191	0.5308
0.1298	4.9095	235	0.5297

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.0
• Pytorch 2.2.2
• Datasets 2.19.0
• Tokenizers 0.19.1