mistral_medner / README.md
maazahmedsf's picture
exnrt/mistral_medner
f03c5a5 verified
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: peft
license: apache-2.0
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: mistral_medner
    results: []

mistral_medner

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

  • Loss: 0.8424

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: cosine
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
0.7809 1.0 519 0.8512
0.6832 2.0 1038 0.8424

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1