jazzson's picture
End of training
8ca0da7 verified
metadata
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
library_name: peft
license: gemma
tags:
  - generated_from_trainer
model-index:
  - name: adl-hw3-finetune-gemma-2-chinese-kyara-7
    results: []

adl-hw3-finetune-gemma-2-chinese-kyara-7

This model is a fine-tuned version of zake7749/gemma-2-2b-it-chinese-kyara-dpo on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5108

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
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.2682 0.3556 200 2.4560
2.2138 0.7111 400 2.1476
2.0192 1.0667 600 2.2137
1.5408 1.4222 800 2.2383
1.5706 1.7778 1000 2.2060
1.3498 2.1333 1200 2.4969
1.0847 2.4889 1400 2.5013
1.0975 2.8444 1600 2.5108

Framework versions

  • PEFT 0.13.2
  • Transformers 4.45.1
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3