metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-base-uncased_flang-bert
results: []
bert-base-uncased_flang-bert
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: 0.4846
- Accuracy: 0.8534
- F1: 0.8536
- Precision: 0.8540
- Recall: 0.8534
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.8287 | 1.0 | 91 | 0.7780 | 0.6505 | 0.6243 | 0.6320 | 0.6505 |
| 0.5677 | 2.0 | 182 | 0.5107 | 0.8066 | 0.8053 | 0.8080 | 0.8066 |
| 0.358 | 3.0 | 273 | 0.4485 | 0.8206 | 0.8215 | 0.8246 | 0.8206 |
| 0.2877 | 4.0 | 364 | 0.5203 | 0.8222 | 0.8219 | 0.8267 | 0.8222 |
| 0.1916 | 5.0 | 455 | 0.4846 | 0.8534 | 0.8536 | 0.8540 | 0.8534 |
| 0.1707 | 6.0 | 546 | 0.4713 | 0.8487 | 0.8483 | 0.8507 | 0.8487 |
| 0.1168 | 7.0 | 637 | 0.5647 | 0.8440 | 0.8443 | 0.8531 | 0.8440 |
| 0.0993 | 8.0 | 728 | 0.5702 | 0.8424 | 0.8425 | 0.8433 | 0.8424 |
| 0.1333 | 9.0 | 819 | 0.7214 | 0.8346 | 0.8338 | 0.8348 | 0.8346 |
| 0.1002 | 10.0 | 910 | 0.6407 | 0.8284 | 0.8258 | 0.8304 | 0.8284 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1