metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: category-bert-base
results: []
category-bert-base
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1447
- Accuracy: 0.5499
- Macro F1: 0.1791
- Weighted F1: 0.4714
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: 16
- eval_batch_size: 16
- seed: 13
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|---|---|---|---|---|---|---|
| 4.1538 | 1.0 | 836 | 2.8741 | 0.4259 | 0.0953 | 0.3323 |
| 2.5355 | 2.0 | 1672 | 2.3116 | 0.5296 | 0.1610 | 0.4469 |
| 2.0853 | 3.0 | 2508 | 2.1447 | 0.5499 | 0.1791 | 0.4714 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 4.3.0
- Tokenizers 0.22.1