MalikIbrar/mistral7b_langchain

<!-- 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. -->

mistral7b_langchain

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: 1.1293
• —eval_runtime: 519.9872
• —evalsamplesper_second: 0.144
• —evalstepsper_second: 0.019
• —epoch: 0.2105
• —step: 20

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: 10
• —training_steps: 80

Framework versions

• —PEFT 0.11.1
• —Transformers 4.42.3
• —Pytorch 2.3.1+cu121
• —Datasets 2.20.0
• —Tokenizers 0.19.1