metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_uncased_twitter
results: []
bert_base_uncased_twitter
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4780
- Accuracy: 0.7767
- F1 Macro: 0.7415
- F1 Micro: 0.7767
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: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 0.4689 | 0.37 | 50 | 0.4876 | 0.7583 | 0.7185 | 0.7583 |
| 0.4675 | 0.74 | 100 | 0.4780 | 0.7767 | 0.7415 | 0.7767 |
| 0.4489 | 1.1 | 150 | 0.4803 | 0.7776 | 0.7440 | 0.7776 |
| 0.457 | 1.47 | 200 | 0.4820 | 0.7757 | 0.7482 | 0.7757 |
| 0.44 | 1.84 | 250 | 0.4857 | 0.7831 | 0.7429 | 0.7831 |
| 0.3905 | 2.21 | 300 | 0.4835 | 0.7739 | 0.7406 | 0.7739 |
| 0.4276 | 2.57 | 350 | 0.4898 | 0.7711 | 0.7452 | 0.7711 |
| 0.3413 | 2.94 | 400 | 0.4929 | 0.7757 | 0.7468 | 0.7757 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2