metadata
library_name: transformers
license: gemma
base_model: vidore/colpaligemma-3b-pt-448-base
tags:
- generated_from_trainer
model-index:
- name: Japanese_colpali
results: []
Japanese_colpali
This model is a fine-tuned version of vidore/colpaligemma-3b-pt-448-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3273
- Model Preparation Time: 0.0061
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|---|---|---|---|---|
| No log | 0.0144 | 1 | 0.3660 | 0.0061 |
| 0.5545 | 1.4440 | 100 | 0.3213 | 0.0061 |
| 0.3 | 2.8881 | 200 | 0.3279 | 0.0061 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1