paligemma-hindi

This model is a fine-tuned version of google/paligemma-3b-pt-224 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.4683
• eval_runtime: 388.3071
• eval_samples_per_second: 1.288
• eval_steps_per_second: 1.288
• epoch: 0.7111
• step: 200

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

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.19.1