mistral_gsm8k_sft_0 / README.md
weijie210's picture
Model save
782b2cf verified
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: mistral_gsm8k_sft_0
    results: []

mistral_gsm8k_sft_0

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7868

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 16
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.7482 1.0 455 0.7868

Framework versions

  • Transformers 4.36.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.16.1
  • Tokenizers 0.15.0