finetune_colpali_v1_2-vdsid_french-4bit

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

• Loss: 0.0212
• Model Preparation Time: 0.0144

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: 1.5

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0034	1	0.0571	0.0144
0.0397	0.3404	100	0.0247	0.0144
0.0195	0.6809	200	0.0266	0.0144
0.0098	1.0213	300	0.0240	0.0144
0.0299	1.3617	400	0.0223	0.0144

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.2
• Tokenizers 0.20.1