newsdata-bert / README.md
tiagoblima's picture
End of training
3e958e0 verified
|
raw
history blame
1.99 kB
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: newsdata-bert
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# newsdata-bert
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7534
- Accuracy: 0.8531
## 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 |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 1.4704 | 0.0859 | 5000 | 1.4487 | 0.6858 |
| 1.1946 | 0.1718 | 10000 | 1.2197 | 0.7417 |
| 1.1323 | 0.2577 | 15000 | 0.9984 | 0.7733 |
| 0.9926 | 0.3436 | 20000 | 1.0195 | 0.7901 |
| 0.9232 | 0.4295 | 25000 | 0.9879 | 0.8089 |
| 0.9273 | 0.5155 | 30000 | 0.8956 | 0.8224 |
| 1.0023 | 0.6014 | 35000 | 0.8435 | 0.8277 |
| 0.7566 | 0.6873 | 40000 | 0.8668 | 0.8331 |
| 0.9032 | 0.7732 | 45000 | 0.8221 | 0.8408 |
| 0.7227 | 0.8591 | 50000 | 0.7653 | 0.8456 |
| 0.8159 | 0.9450 | 55000 | 0.7534 | 0.8531 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1