yyx123's picture
End of training
6262422 verified
metadata
license: other
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - ruozhiba
base_model: 01-ai/Yi-6B
model-index:
  - name: Yi-6B-ruozhiba-5e-5-50
    results: []

Yi-6B-ruozhiba-5e-5-50

This model is a fine-tuned version of 01-ai/Yi-6B on the ruozhiba dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0795

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
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
1.8473 2.0 110 1.9843
1.7645 3.0 165 1.9680
1.4795 4.0 220 2.0760
1.2467 5.0 275 2.2715
1.0034 6.0 330 2.5656
0.8124 7.0 385 2.8052
0.6269 8.0 440 2.9866
0.5743 9.0 495 3.0649

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2