metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: newsdata-bert
results: []
newsdata-bert
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0878
- Accuracy: 0.8087
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3096 | 0.0859 | 5000 | 1.4907 | 0.7014 |
| 1.2402 | 0.1718 | 10000 | 1.2411 | 0.7285 |
| 1.1273 | 0.2577 | 15000 | 1.3464 | 0.7514 |
| 1.0028 | 0.3436 | 20000 | 1.4583 | 0.7323 |
| 0.9333 | 0.4295 | 25000 | 1.2102 | 0.7713 |
| 0.9045 | 0.5155 | 30000 | 1.1515 | 0.7801 |
| 0.7642 | 0.6014 | 35000 | 1.1968 | 0.7873 |
| 0.8657 | 0.6873 | 40000 | 1.0961 | 0.7967 |
| 0.8082 | 0.7732 | 45000 | 1.1199 | 0.7977 |
| 0.7657 | 0.8591 | 50000 | 1.1115 | 0.8029 |
| 0.7556 | 0.9450 | 55000 | 1.0878 | 0.8087 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1