metadata
license: cc-by-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: nb-bert-base-user-needs
results: []
nb-bert-base-user-needs
This model is a fine-tuned version of NbAiLab/nb-bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6468
- Accuracy: 0.8582
- F1: 0.8388
- Precision: 0.8295
- Recall: 0.8582
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 98 | 1.2122 | 0.6005 | 0.4506 | 0.3606 | 0.6005 |
| No log | 2.0 | 196 | 0.9735 | 0.7113 | 0.6231 | 0.5549 | 0.7113 |
| No log | 3.0 | 294 | 0.7894 | 0.7655 | 0.6996 | 0.7399 | 0.7655 |
| No log | 4.0 | 392 | 0.9499 | 0.6933 | 0.6584 | 0.6617 | 0.6933 |
| No log | 5.0 | 490 | 0.7529 | 0.7784 | 0.7217 | 0.7107 | 0.7784 |
| 0.9006 | 6.0 | 588 | 0.7510 | 0.7964 | 0.7491 | 0.7370 | 0.7964 |
| 0.9006 | 7.0 | 686 | 0.5963 | 0.8273 | 0.8044 | 0.7960 | 0.8273 |
| 0.9006 | 8.0 | 784 | 0.6918 | 0.8351 | 0.8071 | 0.8096 | 0.8351 |
| 0.9006 | 9.0 | 882 | 0.7391 | 0.8273 | 0.8017 | 0.8042 | 0.8273 |
| 0.9006 | 10.0 | 980 | 0.6468 | 0.8582 | 0.8388 | 0.8295 | 0.8582 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.2+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1