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