中文Sign up

abdiharyadi/finbert-ft-icar-a-v0.11-aps

🤗 Hugging Face sourcetext-classificationapache-2.0109M params438 MBsafetensors✓ 4 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo abdiharyadi/finbert-ft-icar-a-v0.11-aps ./model-folder
Needs a seeder →

finbert-ft-icar-a-v0.11-aps

This model is a fine-tuned version of project-aps/finbert-finetune on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2343
  • Accuracy: 0.8904
  • Precision: 0.8787
  • Recall: 0.8542
  • F1: 0.8647

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-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 3
  • total_train_batch_size: 3
  • 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
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
3.6033 1.0 704 1.0430 0.8034 0.8146 0.7110 0.7320
1.9526 2.0 1408 0.9009 0.8261 0.8087 0.7546 0.7711
1.4631 3.0 2112 0.9722 0.8299 0.8069 0.7731 0.7824
1.0839 4.0 2816 0.8984 0.8526 0.8544 0.7870 0.8080
0.8472 5.0 3520 0.9364 0.8526 0.8534 0.7901 0.8112
0.6508 6.0 4224 0.8462 0.8677 0.8448 0.8274 0.8350
0.4698 7.0 4928 0.9436 0.8658 0.8570 0.8159 0.8313
0.3059 8.0 5632 0.9649 0.8620 0.8582 0.8190 0.8349
0.2214 9.0 6336 1.0001 0.8733 0.8521 0.8416 0.8466
0.1601 10.0 7040 1.0287 0.8620 0.8391 0.8248 0.8312
0.1301 11.0 7744 1.0760 0.8639 0.8366 0.8317 0.8340
0.1296 12.0 8448 1.1559 0.8677 0.8583 0.8250 0.8383
0.077 13.0 9152 1.1705 0.8601 0.8339 0.8315 0.8326
0.094 14.0 9856 1.1400 0.8752 0.8594 0.8409 0.8490
0.0663 15.0 10560 1.2298 0.8696 0.8565 0.8218 0.8345
0.065 16.0 11264 1.2036 0.8696 0.8429 0.8365 0.8394
0.0848 17.0 11968 1.1844 0.8752 0.8537 0.8372 0.8443
0.0742 18.0 12672 1.2367 0.8715 0.8512 0.8328 0.8403
0.0917 19.0 13376 1.2492 0.8715 0.8618 0.8261 0.8392
0.0501 20.0 14080 1.2344 0.8601 0.8325 0.8239 0.8275
0.0432 21.0 14784 1.2575 0.8752 0.8497 0.8483 0.8490
0.0407 22.0 15488 1.2300 0.8771 0.8603 0.8392 0.8484
0.0641 23.0 16192 1.2257 0.8828 0.8753 0.8400 0.8538
0.0561 24.0 16896 1.2529 0.8828 0.8718 0.8509 0.8601
0.0455 25.0 17600 1.3678 0.8639 0.8450 0.8198 0.8294
0.0374 26.0 18304 1.3127 0.8771 0.8571 0.8470 0.8517
0.0439 27.0 19008 1.2788 0.8828 0.8632 0.8552 0.8590
0.0403 28.0 19712 1.2715 0.8771 0.8572 0.8435 0.8498
0.0266 29.0 20416 1.2829 0.8752 0.8562 0.8374 0.8456
0.03 30.0 21120 1.3335 0.8733 0.8581 0.8387 0.8474
0.0455 31.0 21824 1.3037 0.8752 0.8580 0.8391 0.8471
0.0484 32.0 22528 1.2934 0.8771 0.8517 0.8541 0.8526
0.0413 33.0 23232 1.2343 0.8904 0.8787 0.8542 0.8647
0.0438 34.0 23936 1.3027 0.8847 0.8778 0.8407 0.8554
0.0319 35.0 24640 1.2800 0.8752 0.8497 0.8506 0.8501
0.0311 36.0 25344 1.2994 0.8790 0.8644 0.8368 0.8480
0.0368 37.0 26048 1.3318 0.8715 0.8594 0.8214 0.8359
0.0308 38.0 26752 1.2342 0.8885 0.8708 0.8657 0.8682
0.0412 39.0 27456 1.2783 0.8790 0.8691 0.8411 0.8528
0.0387 40.0 28160 1.2715 0.8828 0.8624 0.8539 0.8578
0.031 41.0 28864 1.2464 0.8828 0.8607 0.8533 0.8568
0.0289 42.0 29568 1.2761 0.8809 0.8569 0.8569 0.8568
0.0331 43.0 30272 1.2748 0.8809 0.8569 0.8569 0.8568
0.0276 44.0 30976 1.2644 0.8809 0.8642 0.8466 0.8544
0.0295 45.0 31680 1.2594 0.8828 0.8646 0.8528 0.8582
0.0227 46.0 32384 1.2658 0.8847 0.8671 0.8528 0.8592
0.0241 47.0 33088 1.2809 0.8828 0.8678 0.8485 0.8570
0.0314 48.0 33792 1.2853 0.8828 0.8678 0.8485 0.8570

Framework versions

  • Transformers 4.52.4
  • Pytorch 2.6.0+cu124
  • Datasets 4.4.2
  • Tokenizers 0.21.2