metadata
library_name: transformers
license: apache-2.0
base_model: sandeshrajx/bert-fraud-classification-test-mass
tags:
- generated_from_trainer
metrics:
- f1
- precision
model-index:
- name: bert-fraud-classification-test-mass-4
results: []
bert-fraud-classification-test-mass-4
This model is a fine-tuned version of sandeshrajx/bert-fraud-classification-test-mass on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3408
- F1: 0.8508
- Precision: 0.8627
- Val Accuracy: 0.8663
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: 44
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 88
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Val Accuracy |
|---|---|---|---|---|---|---|
| 0.3874 | 0.1743 | 40 | 0.3197 | 0.8579 | 0.8936 | 0.8758 |
| 0.3614 | 0.3486 | 80 | 0.3427 | 0.8382 | 0.8846 | 0.8603 |
| 0.3563 | 0.5229 | 120 | 0.3505 | 0.8435 | 0.8468 | 0.8584 |
| 0.4263 | 0.6972 | 160 | 0.3407 | 0.8454 | 0.8589 | 0.8617 |
| 0.3514 | 0.8715 | 200 | 0.3473 | 0.8413 | 0.8421 | 0.8560 |
| 0.259 | 1.0458 | 240 | 0.3378 | 0.8417 | 0.9106 | 0.8663 |
| 0.3148 | 1.2200 | 280 | 0.3543 | 0.8479 | 0.8889 | 0.8679 |
| 0.2685 | 1.3943 | 320 | 0.3507 | 0.8501 | 0.9040 | 0.8715 |
| 0.2271 | 1.5686 | 360 | 0.3773 | 0.8406 | 0.8262 | 0.8526 |
| 0.376 | 1.7429 | 400 | 0.3412 | 0.8520 | 0.8731 | 0.8687 |
| 0.2739 | 1.9172 | 440 | 0.3408 | 0.8508 | 0.8627 | 0.8663 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1