mistral_instruct_generation

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: 1.3103

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
1.5303	0.1626	20	1.3705
1.4674	0.3252	40	1.3394
1.4233	0.4878	60	1.3265
1.436	0.6504	80	1.3160
1.3967	0.8130	100	1.3103

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3