mistral_instruct_classifyFPB

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: 0.8201

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: 6
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.1689	1.0	13	0.9276
0.9467	2.0	26	0.8534
0.8709	3.0	39	0.8265
0.7713	4.0	52	0.8196
0.7215	5.0	65	0.8201

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2