metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-large-uncased-detect-dep-v5
results: []
bert-large-uncased-detect-dep-v5
This model is a fine-tuned version of bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8207
- Accuracy: 0.702
- F1: 0.7806
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6404 | 1.0 | 751 | 0.5949 | 0.739 | 0.8065 |
| 0.6075 | 2.0 | 1502 | 0.5335 | 0.758 | 0.8296 |
| 0.5722 | 3.0 | 2253 | 0.5041 | 0.777 | 0.8327 |
| 0.539 | 4.0 | 3004 | 0.5608 | 0.744 | 0.8158 |
| 0.4922 | 5.0 | 3755 | 0.6350 | 0.711 | 0.7765 |
| 0.4296 | 6.0 | 4506 | 0.6518 | 0.732 | 0.7938 |
| 0.3761 | 7.0 | 5257 | 0.7428 | 0.711 | 0.7864 |
| 0.3356 | 8.0 | 6008 | 0.8207 | 0.702 | 0.7806 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3