finetune_colpali_smjain
This model is a fine-tuned version of vidore/colpaligemma-3b-pt-448-base on the vidore/arxivqa_train dataset. It achieves the following results on the evaluation set:
- Loss: 0.0593
- Model Preparation Time: 0.0059
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 0.0093 | 1 | 0.0659 | 0.0059 |
| 0.1062 | 0.9346 | 100 | 0.0593 | 0.0059 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
Model tree for smjain/finetune_colpali_smjain
Base model
google/paligemma-3b-pt-448
Finetuned
vidore/colpaligemma-3b-pt-448-base