CoolFace
Modelpublic

autoprogrammer/cc100-zh-Hans-unsupervised-20241110-165558

sourceHugging Facellama3.2updated 2y agoView on Hugging Face
0likes18downloads
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. -->

cc100-zh-Hans-unsupervised-20241110-165558

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the cc100 dataset. It achieves the following results on the evaluation set:

  • —Loss: 3.5122

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: 5e-05
  • —trainbatchsize: 24
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —training_steps: 3000

Training results

Training LossEpochStepValidation Loss
4.33310.08332504.3223
4.070.16675004.1778
3.80220.257504.1002
4.29380.333310003.9540
4.13520.416712503.9815
2.91990.515003.8021
4.39330.583317503.7528
3.61740.666720003.6856
3.58820.7522503.6198
3.8470.833325003.5746
3.51990.916727503.5320
3.7351.030003.5122

Framework versions

  • —Transformers 4.45.2
  • —Pytorch 2.4.1
  • —Datasets 2.19.1
  • —Tokenizers 0.20.1