Mistral-7B-Ours-SFT / README.md
luzimu's picture
first commit
055a260
metadata
base_model: Mistral-7B-v0.1
tags:
  - math
model-index:
  - name: Mistral-7B-v0.1-lce
    results: []
license: apache-2.0
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-generation

Mistral-7B-Ours-SFT

This model is a fine-tuned version of Mistral-7B-v0.1. It achieves the following results on the evaluation set:

  • Loss: 0.2716

Model description

This is a model fine-tuned for mathematical problem-solving.

Intended uses & limitations

The model is intended for solving math problems.

Training and evaluation data

eval

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.2