mistral_instruct_generation

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.7995

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
• lr_scheduler_warmup_ratio: 0.03
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.8374	0.1220	20	0.8620
0.7649	0.2439	40	0.8181
0.7381	0.3659	60	0.8088
0.7652	0.4878	80	0.8010
0.7265	0.6098	100	0.7995

Framework versions

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