Hugging Face's logo

b09501048
/
ADL_Gemma

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
ADL_Gemma / README.md
b09501048's picture
b09501048
End of training
efeb284 verified
preview code
|
raw
history blame contribute delete
2.23 kB
metadata
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
library_name: peft
license: gemma
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: ADL_Gemma
    results: []

Visualize in Weights & Biases Visualize in Weights & Biases Visualize in Weights & Biases

ADL_Gemma

This model is a fine-tuned version of zake7749/gemma-2-2b-it-chinese-kyara-dpo on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4280

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.5838 1.0 1250 1.4726
1.5041 2.0 2500 1.4400
1.4579 3.0 3750 1.4292
1.4483 4.0 5000 1.4280

Framework versions

  • PEFT 0.13.2
  • Transformers 4.45.1
  • Pytorch 2.5.0+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1