metadata

library_name: transformers
license: gemma
base_model: vidore/colpaligemma-3b-pt-448-base
tags:
  - colpali
  - generated_from_trainer
pipeline_tag: visual-document-retrieval
model-index:
  - name: colpali-hockey-ft-0.3-4bit
    results: []

colpali-hockey-ft-0.3-4bit

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

Loss: 0.0460
Model Preparation Time: 0.0057

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 OptimizerNames.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	0.0086	1	0.1162	0.0057
0.0517	0.8565	100	0.0589	0.0057

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0