florence_ft / README.md
jena-shreyas's picture
Model save
f4c4c36 verified
|
raw
history blame
7.76 kB
metadata
base_model: HuggingFaceM4/Florence-2-DocVQA
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: florence_ft
    results: []

Visualize in Weights & Biases

florence_ft

This model is a fine-tuned version of HuggingFaceM4/Florence-2-DocVQA on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0500
  • Accuracy: 0.0

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 7 1.4280 0.0
2.3602 2.0 14 1.2109 0.0
1.0245 3.0 21 1.2202 0.0
1.0245 4.0 28 1.2606 0.0
0.929 5.0 35 1.2130 0.0
0.8584 6.0 42 1.1525 0.0
0.8584 7.0 49 1.0689 0.0
0.7889 8.0 56 1.0324 0.0
0.7719 9.0 63 1.0274 0.0
0.7284 10.0 70 1.0232 0.0
0.7284 11.0 77 1.0275 0.0
0.6993 12.0 84 1.0357 0.0
0.688 13.0 91 1.0444 0.0
0.688 14.0 98 1.0427 0.0
0.6764 15.0 105 1.0408 0.0
0.6521 16.0 112 1.0217 0.0
0.6521 17.0 119 1.0021 0.0
0.6511 18.0 126 1.0037 0.0
0.637 19.0 133 1.0241 0.0
0.6348 20.0 140 1.0314 0.0
0.6348 21.0 147 1.0510 0.0
0.6165 22.0 154 1.0596 0.0
0.6245 23.0 161 1.0526 0.0
0.6245 24.0 168 1.0489 0.0
0.6107 25.0 175 1.0402 0.0
0.6012 26.0 182 1.0453 0.0
0.6012 27.0 189 1.0450 0.0
0.5995 28.0 196 1.0416 0.0
0.5975 29.0 203 1.0469 0.0
0.5834 30.0 210 1.0590 0.0
0.5834 31.0 217 1.0518 0.0
0.585 32.0 224 1.0644 0.0
0.5846 33.0 231 1.0692 0.0
0.5846 34.0 238 1.0526 0.0
0.5842 35.0 245 1.0608 0.0
0.5783 36.0 252 1.0644 0.0
0.5783 37.0 259 1.0479 0.0
0.5899 38.0 266 1.0503 0.0
0.5766 39.0 273 1.0502 0.0
0.575 40.0 280 1.0606 0.0
0.575 41.0 287 1.0568 0.0
0.569 42.0 294 1.0587 0.0
0.5673 43.0 301 1.0670 0.0
0.5673 44.0 308 1.0699 0.0
0.5663 45.0 315 1.0731 0.0
0.5681 46.0 322 1.0819 0.0
0.5681 47.0 329 1.0885 0.0
0.5578 48.0 336 1.0928 0.0
0.5641 49.0 343 1.0937 0.0
0.5657 50.0 350 1.0815 0.0
0.5657 51.0 357 1.0746 0.0
0.5583 52.0 364 1.0672 0.0
0.5664 53.0 371 1.0643 0.0
0.5664 54.0 378 1.0648 0.0
0.5614 55.0 385 1.0605 0.0
0.5592 56.0 392 1.0610 0.0
0.5592 57.0 399 1.0587 0.0
0.5542 58.0 406 1.0614 0.0
0.5629 59.0 413 1.0573 0.0
0.549 60.0 420 1.0573 0.0
0.549 61.0 427 1.0559 0.0
0.5573 62.0 434 1.0581 0.0
0.5656 63.0 441 1.0548 0.0
0.5656 64.0 448 1.0515 0.0
0.5489 65.0 455 1.0517 0.0
0.5531 66.0 462 1.0514 0.0
0.5531 67.0 469 1.0546 0.0
0.5463 68.0 476 1.0553 0.0
0.5527 69.0 483 1.0580 0.0
0.554 70.0 490 1.0559 0.0
0.554 71.0 497 1.0555 0.0
0.5524 72.0 504 1.0566 0.0
0.5498 73.0 511 1.0560 0.0
0.5498 74.0 518 1.0569 0.0
0.5592 75.0 525 1.0565 0.0
0.561 76.0 532 1.0515 0.0
0.561 77.0 539 1.0494 0.0
0.5473 78.0 546 1.0507 0.0
0.5493 79.0 553 1.0506 0.0
0.5532 80.0 560 1.0491 0.0
0.5532 81.0 567 1.0498 0.0
0.5484 82.0 574 1.0481 0.0
0.5523 83.0 581 1.0511 0.0
0.5523 84.0 588 1.0498 0.0
0.5496 85.0 595 1.0504 0.0
0.5485 86.0 602 1.0499 0.0
0.5485 87.0 609 1.0501 0.0
0.5418 88.0 616 1.0501 0.0
0.5547 89.0 623 1.0521 0.0
0.5435 90.0 630 1.0511 0.0
0.5435 91.0 637 1.0502 0.0
0.5488 92.0 644 1.0506 0.0
0.5472 93.0 651 1.0506 0.0
0.5472 94.0 658 1.0503 0.0
0.5521 95.0 665 1.0507 0.0
0.5485 96.0 672 1.0509 0.0
0.5485 97.0 679 1.0500 0.0
0.5611 98.0 686 1.0514 0.0
0.5517 99.0 693 1.0508 0.0
0.5574 100.0 700 1.0500 0.0

Framework versions

  • Transformers 4.42.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.19.1