adn0n/mistral_notes_finetuned_v2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mistralnotesfinetuned_v2

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:

• —eval_loss: 0.0042
• —eval_runtime: 3.1456
• —evalsamplesper_second: 1.907
• —evalstepsper_second: 0.318
• —epoch: 87.5
• —step: 350

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
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constant
• —lrschedulerwarmup_steps: 0.03
• —training_steps: 500
• —mixedprecisiontraining: Native AMP

Framework versions

• —PEFT 0.9.0
• —Transformers 4.38.2
• —Pytorch 2.2.1+cu121
• —Datasets 2.18.0
• —Tokenizers 0.15.2