finetune_colpali_smjain

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

• Loss: 0.0593
• Model Preparation Time: 0.0059

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 1.5

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0093	1	0.0659	0.0059
0.1062	0.9346	100	0.0593	0.0059

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0