|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: dumitrescustefan/bert-base-romanian-cased-v1 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: teacher_sst2 |
|
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. --> |
|
|
|
# teacher_sst2 |
|
|
|
This model is a fine-tuned version of [dumitrescustefan/bert-base-romanian-cased-v1](https://huggingface.co/dumitrescustefan/bert-base-romanian-cased-v1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5451 |
|
- F1: 0.8648 |
|
- Roc Auc: 0.8646 |
|
- Accuracy: 0.8635 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.3669 | 1.0 | 1053 | 0.4399 | 0.8248 | 0.8238 | 0.8211 | |
|
| 0.2433 | 2.0 | 2106 | 0.4043 | 0.8457 | 0.8458 | 0.8417 | |
|
| 0.1811 | 3.0 | 3159 | 0.4268 | 0.8625 | 0.8622 | 0.8612 | |
|
| 0.1373 | 4.0 | 4212 | 0.4359 | 0.8537 | 0.8545 | 0.8521 | |
|
| 0.1157 | 5.0 | 5265 | 0.4812 | 0.8681 | 0.8684 | 0.8681 | |
|
| 0.0949 | 6.0 | 6318 | 0.5003 | 0.8607 | 0.8604 | 0.8601 | |
|
| 0.0774 | 7.0 | 7371 | 0.5142 | 0.8643 | 0.8641 | 0.8624 | |
|
| 0.0713 | 8.0 | 8424 | 0.5451 | 0.8648 | 0.8646 | 0.8635 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
