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_roberta-base
results: []
bert-base-uncased_roberta-base
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: 0.4695
- Accuracy: 0.8705
- F1: 0.8700
- Precision: 0.8734
- Recall: 0.8705
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 |
|---|---|---|---|---|---|---|---|
| 0.8895 | 1.0 | 91 | 0.8628 | 0.6147 | 0.5774 | 0.5987 | 0.6147 |
| 0.5526 | 2.0 | 182 | 0.5921 | 0.7722 | 0.7705 | 0.7856 | 0.7722 |
| 0.3669 | 3.0 | 273 | 0.4204 | 0.8346 | 0.8328 | 0.8359 | 0.8346 |
| 0.282 | 4.0 | 364 | 0.4526 | 0.8471 | 0.8475 | 0.8487 | 0.8471 |
| 0.1444 | 5.0 | 455 | 0.4695 | 0.8705 | 0.8700 | 0.8734 | 0.8705 |
| 0.1611 | 6.0 | 546 | 0.5552 | 0.8502 | 0.8503 | 0.8541 | 0.8502 |
| 0.0951 | 7.0 | 637 | 0.6573 | 0.8440 | 0.8430 | 0.8457 | 0.8440 |
| 0.1256 | 8.0 | 728 | 0.5882 | 0.8393 | 0.8411 | 0.8569 | 0.8393 |
| 0.1021 | 9.0 | 819 | 0.5695 | 0.8612 | 0.8614 | 0.8632 | 0.8612 |
| 0.0762 | 10.0 | 910 | 0.8848 | 0.8003 | 0.7958 | 0.8109 | 0.8003 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1