metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-bert-base-uncased-label_category
results: []
edos-2023-baseline-bert-base-uncased-label_category
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: 0.2451
- F1: 0.9381
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: 1e-05
- train_batch_size: 32
- 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: 5
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.1697 | 1.18 | 100 | 1.0664 | 0.2453 |
| 1.0088 | 2.35 | 200 | 0.8489 | 0.5693 |
| 0.8497 | 3.53 | 300 | 0.6923 | 0.7455 |
| 0.672 | 4.71 | 400 | 0.5471 | 0.7865 |
| 0.5973 | 5.88 | 500 | 0.4108 | 0.8800 |
| 0.4801 | 7.06 | 600 | 0.3330 | 0.9068 |
| 0.4047 | 8.24 | 700 | 0.2728 | 0.9263 |
| 0.3612 | 9.41 | 800 | 0.2451 | 0.9381 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2