finetune_colpali_v1_2-context33
This model is a fine-tuned version of vidore/colpaligemma-3b-pt-448-base on the /content/drive/My Drive/colpali_top3_indices_f__f dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0544
- eval_runtime: 1044.4435
- eval_samples_per_second: 1.916
- eval_steps_per_second: 0.049
- epoch: 0.2411
- step: 1751
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 40
- 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: 3
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for MaIlz/finetune_colpali_v1_2-context33
Base model
google/paligemma-3b-pt-448
Finetuned
vidore/colpaligemma-3b-pt-448-base