Japanese_colpali

This model is a fine-tuned version of vidore/colpaligemma-3b-pt-448-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3273
• Model Preparation Time: 0.0061

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0144	1	0.3660	0.0061
0.5545	1.4440	100	0.3213	0.0061
0.3	2.8881	200	0.3279	0.0061

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1