seed_1
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: 0.0251
- Macro-f1: 0.7620
- Micro-f1: 0.9517
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: 8
- eval_batch_size: 8
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
|---|---|---|---|---|---|
| 0.0965 | 1.0 | 692 | 0.0395 | 0.3257 | 0.9201 |
| 0.0428 | 2.0 | 1384 | 0.0300 | 0.5948 | 0.9260 |
| 0.0202 | 3.0 | 2076 | 0.0251 | 0.7620 | 0.9517 |
| 0.0136 | 4.0 | 2768 | 0.0285 | 0.7234 | 0.9372 |
| 0.01 | 5.0 | 3460 | 0.0300 | 0.7252 | 0.9452 |
| 0.0068 | 6.0 | 4152 | 0.0286 | 0.7559 | 0.9501 |
Framework versions
- Transformers 4.40.0
- Pytorch 1.13.1
- Datasets 2.19.0
- Tokenizers 0.19.1