CoolFace
Modelpublic

cutelemonlili/Qwen2.5-Math-7B-Instruct_lora_Teacher_forget_RL_data_QwQ-Preview

sourceHugging Faceotherupdated 1y agoView on Hugging Face
0likes7downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

TeacherforgetRLdataQwQ-Preview

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on the TeacherforgetRLdataQwQ-Preview dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3734

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: 0.0001
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 4
  • —totaltrainbatch_size: 4
  • —totalevalbatch_size: 4
  • —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.03
  • —num_epochs: 3.0

Training results

Training LossEpochStepValidation Loss
0.36120.33002000.4400
0.47580.66014000.3989
0.33830.99016000.3835
0.2651.32018000.3786
0.34791.650210000.3753
0.29341.980212000.3716
0.31672.310214000.3741
0.30172.640316000.3737
0.20652.970318000.3734

Framework versions

  • —PEFT 0.12.0
  • —Transformers 4.46.1
  • —Pytorch 2.4.0+cu121
  • —Datasets 3.1.0
  • —Tokenizers 0.20.3