CoolFace
Modelpublic

Spruteus/Qwen_32B_brevity_finetuned

sourceHugging Faceotherupdated 2y 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. -->

Qwen32Bbrevity_finetuned

This model is a fine-tuned version of Qwen/Qwen1.5-32B-Chat on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4598

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 30
  • —training_steps: 300

Training results

Training LossEpochStepValidation Loss
3.56891.0103.4447
3.38972.0203.1637
3.04193.0302.7805
2.6464.0402.3927
2.21455.0501.9464
1.61596.0601.2767
0.89477.0700.7462
0.57298.0800.6091
0.48589.0900.5534
0.433810.01000.5046
0.388511.01100.4680
0.345712.01200.4339
0.300313.01300.4091
0.257314.01400.3947
0.216715.01500.3864
0.177116.01600.3882
0.139917.01700.3901
0.108318.01800.3994
0.083519.01900.4049
0.060120.02000.4176
0.048321.02100.4301
0.036322.02200.4378
0.031323.02300.4436
0.027824.02400.4486
0.02325.02500.4504
0.020526.02600.4549
0.019927.02700.4586
0.019128.02800.4584
0.018329.02900.4593
0.020430.03000.4598

Framework versions

  • —PEFT 0.11.1
  • —Transformers 4.41.0
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1