Edit model card

Visualize in Weights & Biases

paligemma-3b-odia-chat-final

This model is a fine-tuned version of google/paligemma-3b-mix-448 on the odia_llava_data 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: 3e-06
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 10.0

Training results

Framework versions

  • Transformers 4.43.2
  • Pytorch 2.1.2+git70dfd51
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
2.92B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for sam2ai/odia-paligemma-2b-9900-v1.1

Finetuned
(12)
this model