metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: patent-bert-classifier
results: []
patent-bert-classifier
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9548
- Accuracy: 0.681
- F1: 0.6557
- Precision: 0.6499
- Recall: 0.681
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: 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_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.0317 | 1.0 | 1563 | 0.9973 | 0.6568 | 0.6323 | 0.6319 | 0.6568 |
| 0.8575 | 2.0 | 3126 | 0.9251 | 0.6888 | 0.6641 | 0.6592 | 0.6888 |
| 0.6298 | 3.0 | 4689 | 0.9880 | 0.6736 | 0.6604 | 0.6533 | 0.6736 |
| 0.4886 | 4.0 | 6252 | 1.0900 | 0.6764 | 0.6678 | 0.6615 | 0.6764 |
| 0.3765 | 5.0 | 7815 | 1.1712 | 0.6688 | 0.6601 | 0.6545 | 0.6688 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1