mooo16's picture
End of training
807b29f verified
|
raw
history blame
1.6 kB
metadata
license: gemma
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: google/gemma-2b
model-index:
  - name: Gemma-1000-4bit-qlora
    results: []

Gemma-1000-4bit-qlora

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

  • Loss: 1.4737

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: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.509 1.0 511 1.3390
1.4732 2.0 1022 1.2764
1.121 3.0 1533 1.2965
0.8227 4.0 2044 1.3762
0.6327 5.0 2555 1.4737

Framework versions

  • PEFT 0.10.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2