metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
base_model: bert-base-uncased
model-index:
- name: bert-base-uncased-finetuned-detests
results: []
bert-base-uncased-finetuned-detests
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: 1.5026
- Accuracy: 0.7856
- F1-score: 0.7175
- Precision: 0.7058
- Recall: 0.7369
- Auc: 0.7369
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc |
---|---|---|---|---|---|---|---|---|
0.271 | 1.0 | 174 | 0.4648 | 0.7954 | 0.7005 | 0.7070 | 0.6950 | 0.6950 |
0.2246 | 2.0 | 348 | 0.5229 | 0.7987 | 0.7053 | 0.7119 | 0.6997 | 0.6997 |
0.3814 | 3.0 | 522 | 0.7043 | 0.7676 | 0.7018 | 0.6896 | 0.7278 | 0.7278 |
0.1343 | 4.0 | 696 | 0.8843 | 0.7938 | 0.7217 | 0.7124 | 0.7346 | 0.7346 |
0.0063 | 5.0 | 870 | 1.0890 | 0.7807 | 0.7040 | 0.6955 | 0.7159 | 0.7159 |
0.063 | 6.0 | 1044 | 1.1208 | 0.8101 | 0.7378 | 0.7316 | 0.7452 | 0.7452 |
0.0022 | 7.0 | 1218 | 1.1989 | 0.8249 | 0.7318 | 0.7543 | 0.7166 | 0.7166 |
0.0356 | 8.0 | 1392 | 1.5295 | 0.7758 | 0.7151 | 0.7016 | 0.7457 | 0.7457 |
0.0002 | 9.0 | 1566 | 1.4269 | 0.8003 | 0.7202 | 0.7171 | 0.7236 | 0.7236 |
0.0004 | 10.0 | 1740 | 1.5026 | 0.7856 | 0.7175 | 0.7058 | 0.7369 | 0.7369 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3