paligemmatry3000 / README.md
mahmoudkamal105's picture
Upload folder using huggingface_hub
cbedb00 verified
metadata
base_model: google/paligemma-3b-pt-448
library_name: peft
license: other
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: train_2024-10-15-09-54-06
    results: []

train_2024-10-15-09-54-06

This model is a fine-tuned version of google/paligemma-3b-pt-448 on the my_chartQA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0002
  • Num Input Tokens Seen: 5878272

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 1
  • num_epochs: 2.0

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.20.1