sam2ai/paligemma_hindi_vg_3b

paligemma-3b-wat2024-chat-v0.2

This model is a fine-tuned version of google/paligemma-3b-mix-448 on the llava_wat 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: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.43.2
• Pytorch 2.1.2+git70dfd51
• Datasets 2.19.1
• Tokenizers 0.19.1