Hugging Face's logo

chanyongp
/
colpali_finetuning

Transformers
Safetensors
ColPali
Generated from Trainer
Inference Endpoints
Model card Files Community
colpali_finetuning / README.md
chanyongp's picture
chanyongp
End of training
b6d984e verified
preview code
|
raw
history blame contribute delete
10.2 kB
metadata
library_name: transformers
license: gemma
base_model: vidore/colpaligemma-3b-pt-448-base
tags:
  - colpali
  - generated_from_trainer
model-index:
  - name: colpali_finetuning
    results: []

colpali_finetuning

This model is a fine-tuned version of vidore/colpaligemma-3b-pt-448-base on the vidore/colpali_train_set dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0537
  • Model Preparation Time: 0.0062

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 0.0001 1 0.0537 0.0062
0.0236 0.0135 100 0.0564 0.0062
0.0535 0.0271 200 0.0593 0.0062
0.0306 0.0406 300 0.0557 0.0062
0.034 0.0541 400 0.0695 0.0062
0.0326 0.0677 500 0.0445 0.0062
0.0465 0.0812 600 0.0527 0.0062
0.0344 0.0948 700 0.0533 0.0062
0.0634 0.1083 800 0.0438 0.0062
0.0474 0.1218 900 0.0455 0.0062
0.0383 0.1354 1000 0.0490 0.0062
0.0749 0.1489 1100 0.0460 0.0062
0.0507 0.1624 1200 0.0361 0.0062
0.05 0.1760 1300 0.0385 0.0062
0.0409 0.1895 1400 0.0451 0.0062
0.037 0.2031 1500 0.0427 0.0062
0.0593 0.2166 1600 0.0653 0.0062
0.035 0.2301 1700 0.0596 0.0062
0.0422 0.2437 1800 0.0471 0.0062
0.0356 0.2572 1900 0.0498 0.0062
0.0088 0.2707 2000 0.0608 0.0062
0.0227 0.2843 2100 0.0720 0.0062
0.0166 0.2978 2200 0.0734 0.0062
0.0348 0.3113 2300 0.0589 0.0062
0.0161 0.3249 2400 0.0596 0.0062
0.0316 0.3384 2500 0.0499 0.0062
0.0365 0.3520 2600 0.0543 0.0062
0.0304 0.3655 2700 0.0556 0.0062
0.0105 0.3790 2800 0.0545 0.0062
0.0136 0.3926 2900 0.0545 0.0062
0.015 0.4061 3000 0.0605 0.0062
0.0453 0.4196 3100 0.0611 0.0062
0.0364 0.4332 3200 0.0593 0.0062
0.0347 0.4467 3300 0.0579 0.0062
0.0225 0.4603 3400 0.0602 0.0062
0.0232 0.4738 3500 0.0505 0.0062
0.0318 0.4873 3600 0.0514 0.0062
0.0359 0.5009 3700 0.0542 0.0062
0.0366 0.5144 3800 0.0559 0.0062
0.0323 0.5279 3900 0.0584 0.0062
0.0205 0.5415 4000 0.0615 0.0062
0.0292 0.5550 4100 0.0527 0.0062
0.0458 0.5685 4200 0.0506 0.0062
0.0175 0.5821 4300 0.0503 0.0062
0.0215 0.5956 4400 0.0558 0.0062
0.0142 0.6092 4500 0.0568 0.0062
0.0312 0.6227 4600 0.0612 0.0062
0.0193 0.6362 4700 0.0630 0.0062
0.0077 0.6498 4800 0.0631 0.0062
0.0334 0.6633 4900 0.0708 0.0062
0.0247 0.6768 5000 0.0664 0.0062
0.0201 0.6904 5100 0.0546 0.0062
0.0402 0.7039 5200 0.0630 0.0062
0.0326 0.7175 5300 0.0651 0.0062
0.0127 0.7310 5400 0.0614 0.0062
0.0479 0.7445 5500 0.0599 0.0062
0.0344 0.7581 5600 0.0557 0.0062
0.016 0.7716 5700 0.0542 0.0062
0.0194 0.7851 5800 0.0546 0.0062
0.0236 0.7987 5900 0.0543 0.0062
0.0285 0.8122 6000 0.0577 0.0062
0.0128 0.8257 6100 0.0521 0.0062
0.0218 0.8393 6200 0.0539 0.0062
0.0501 0.8528 6300 0.0515 0.0062
0.0456 0.8664 6400 0.0508 0.0062
0.0247 0.8799 6500 0.0500 0.0062
0.035 0.8934 6600 0.0516 0.0062
0.0068 0.9070 6700 0.0502 0.0062
0.0257 0.9205 6800 0.0527 0.0062
0.0192 0.9340 6900 0.0513 0.0062
0.0334 0.9476 7000 0.0551 0.0062
0.0208 0.9611 7100 0.0544 0.0062
0.0668 0.9747 7200 0.0510 0.0062
0.0264 0.9882 7300 0.0481 0.0062
0.0641 1.0017 7400 0.0486 0.0062
0.0178 1.0153 7500 0.0473 0.0062
0.0206 1.0288 7600 0.0502 0.0062
0.0188 1.0423 7700 0.0537 0.0062
0.0378 1.0559 7800 0.0502 0.0062
0.0313 1.0694 7900 0.0571 0.0062
0.0169 1.0829 8000 0.0586 0.0062
0.0164 1.0965 8100 0.0580 0.0062
0.0327 1.1100 8200 0.0540 0.0062
0.0153 1.1236 8300 0.0507 0.0062
0.0305 1.1371 8400 0.0542 0.0062
0.0279 1.1506 8500 0.0532 0.0062
0.0081 1.1642 8600 0.0552 0.0062
0.027 1.1777 8700 0.0545 0.0062
0.0112 1.1912 8800 0.0551 0.0062
0.0312 1.2048 8900 0.0564 0.0062
0.0244 1.2183 9000 0.0538 0.0062
0.0274 1.2319 9100 0.0529 0.0062
0.0351 1.2454 9200 0.0531 0.0062
0.0172 1.2589 9300 0.0532 0.0062
0.005 1.2725 9400 0.0513 0.0062
0.0195 1.2860 9500 0.0549 0.0062
0.0062 1.2995 9600 0.0558 0.0062
0.0234 1.3131 9700 0.0558 0.0062
0.0157 1.3266 9800 0.0564 0.0062
0.0248 1.3401 9900 0.0556 0.0062
0.0098 1.3537 10000 0.0536 0.0062
0.0133 1.3672 10100 0.0525 0.0062
0.0187 1.3808 10200 0.0526 0.0062
0.0088 1.3943 10300 0.0509 0.0062
0.0315 1.4078 10400 0.0534 0.0062
0.0219 1.4214 10500 0.0537 0.0062
0.0225 1.4349 10600 0.0548 0.0062
0.0338 1.4484 10700 0.0545 0.0062
0.029 1.4620 10800 0.0539 0.0062
0.0354 1.4755 10900 0.0537 0.0062
0.0214 1.4891 11000 0.0536 0.0062

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1