Hugging Face's logo

Tobius
/
fine-tuned_model

PEFT
TensorBoard
Safetensors
English
quote-generation
fine-tuned
gemma-2b
trl
sft
Generated from Trainer
Model card Files Metrics Community
fine-tuned_model / README.md
Tobius's picture
Tobius
End of training
c989619 verified
preview code
|
raw
history blame contribute delete
1.27 kB
metadata
base_model: google/gemma-2b
language:
  - en
library_name: peft
license: mit
tags:
  - quote-generation
  - fine-tuned
  - gemma-2b
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: fine-tuned_model
    results: []

fine-tuned_model

This model is a fine-tuned version of google/gemma-2b on the Abirate/english_quotes dataset.

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: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.12.1.dev0
  • Transformers 4.44.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1