---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_10_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_km_10_v2_rte
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE RTE
      type: glue
      args: rte
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.5234657039711191
---

<!-- 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. -->

# bert_base_km_10_v2_rte

This model is a fine-tuned version of [Hartunka/bert_base_km_10_v2](https://huggingface.co/Hartunka/bert_base_km_10_v2) on the GLUE RTE dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7182
- Accuracy: 0.5235

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.7122        | 1.0   | 10   | 0.7220          | 0.5054   |
| 0.6651        | 2.0   | 20   | 0.7182          | 0.5235   |
| 0.6283        | 3.0   | 30   | 0.7291          | 0.5523   |
| 0.558         | 4.0   | 40   | 0.7983          | 0.5126   |
| 0.4573        | 5.0   | 50   | 0.8778          | 0.5343   |
| 0.3427        | 6.0   | 60   | 1.0947          | 0.5054   |
| 0.2296        | 7.0   | 70   | 1.2676          | 0.5162   |


### Framework versions

- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1