InternLM2-SFT-SCDPO / README.md
MathGenie's picture
Update README.md
c8da03c verified
metadata
base_model: InternLM2-SFT
tags:
  - math
model-index:
  - name: InternLM2-SFT-SCDPO
    results: []
license: apache-2.0
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-generation

InternLM2-SFT-SCDPO

This model is a fine-tuned version of the InternLM2-20B model using SFT and SCDPO. It achieves the following results on the evaluation set:

  • Loss: 0.2572
  • Rewards/chosen: 0.7366
  • Rewards/rejected: -2.9817
  • Rewards/accuracies: 0.8929
  • Rewards/margins: 3.7183
  • Logps/rejected: -155.1884
  • Logps/chosen: -92.5904
  • Logits/rejected: -2.3032
  • Logits/chosen: -2.4880

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

gsm8k math ape cmath mgsm_zh
InternLM2-SFT 86.4 55.8 77.1 88.4 74.8
InternLM2-SFT-DPO 87 57.6 78.7 89.9 76
InternLM2-SFT-DPO (data-equal) 88.2 57.5 78.8 89.3 76
InternLM2-SFT-SCDPO 88.5 58.1 79.3 90.3 80.4

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1.5e-07
  • train_batch_size: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 16
  • total_train_batch_size: 32
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2

Framework versions

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