asparius's picture
update model card README.md
72c1a26
---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: convbert-combined-large
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. -->
# convbert-combined-large
This model is a fine-tuned version of [dbmdz/convbert-base-turkish-mc4-uncased](https://huggingface.co/dbmdz/convbert-base-turkish-mc4-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2848
- Accuracy: 0.8952
- F1: 0.8955
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.289 | 1.0 | 3077 | 0.3342 | 0.8910 | 0.8891 |
| 0.2466 | 2.0 | 6154 | 0.2898 | 0.8921 | 0.8910 |
| 0.2182 | 3.0 | 9231 | 0.2848 | 0.8952 | 0.8955 |
### Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1