metadata
library_name: transformers
license: cc-by-4.0
base_model: mideind/IceBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: payment-codes-classifier-dev
results: []
payment-codes-classifier-dev
This model is a fine-tuned version of mideind/IceBERT-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0475
- Accuracy: 0.9795
- F1: 0.9777
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.1007 | 1.0 | 1413 | 0.0601 | 0.9728 | 0.9654 |
| 0.0494 | 2.0 | 2826 | 0.0715 | 0.9710 | 0.9643 |
| 0.0316 | 3.0 | 4239 | 0.0549 | 0.9759 | 0.9718 |
| 0.0141 | 4.0 | 5652 | 0.0540 | 0.9791 | 0.9769 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0
- Datasets 4.3.0
- Tokenizers 0.21.4