svenbl80/finetune_colpali_v1_2-vdsid_french-4bit

finetune_colpali_v1_2-german-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: 0.1351
• Model Preparation Time: 0.0074

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

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0533	1	0.2922	0.0074
1.9646	0.5333	10	0.2693	0.0074
1.1176	1.0667	20	0.2259	0.0074
1.1675	1.6	30	0.1884	0.0074
0.6123	2.1333	40	0.1618	0.0074
0.4301	2.6667	50	0.1351	0.0074

Framework versions

• Transformers 4.46.1
• Pytorch 2.3.1
• Datasets 3.1.0
• Tokenizers 0.20.1