scottsuk0306's picture
End of training
1f778cf verified
metadata
library_name: transformers
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - EunsuKim/GSM8K
model-index:
  - name: zephyr-7b-math-case-8-fixed
    results: []

zephyr-7b-math-case-8-fixed

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the EunsuKim/GSM8K dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0279

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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 32
  • 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: 0.03
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
1.0201 1.0 4 0.8702
0.9576 2.0 8 0.6513
0.7027 3.0 12 0.4668
0.4836 4.0 16 0.2752
0.2544 5.0 20 0.1434
0.2544 6.0 24 0.0726
0.109 7.0 28 0.0441
0.0544 8.0 32 0.0341
0.0364 9.0 36 0.0290
0.0289 10.0 40 0.0279

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1