Hugging Face's logo

matbee
/
weblinx-idefics-2

Safetensors
Generated from Trainer
Model card Files Community
weblinx-idefics-2 / README.md
matbee's picture
matbee
End of training
d36c8b0 verified
preview code
|
raw
history blame
1.26 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: HuggingFaceM4/idefics2-8b
model-index:
  - name: docvqa_ft_tutorial
    results: []

docvqa_ft_tutorial

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown 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: 5e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 2
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1

Training results

Framework versions

  • PEFT 0.10.1.dev0
  • Transformers 4.41.0.dev0
  • Pytorch 2.2.2
  • Datasets 2.16.1
  • Tokenizers 0.19.1