metadata
library_name: transformers
base_model: Hartunka/tiny_bert_km_5_v2
tags:
- generated_from_trainer
metrics:
- matthews_correlation
- accuracy
model-index:
- name: tiny_bert_km_5_v2_cola
results: []
tiny_bert_km_5_v2_cola
This model is a fine-tuned version of Hartunka/tiny_bert_km_5_v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7225
- Matthews Correlation: 0.0664
- Accuracy: 0.6433
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 | Matthews Correlation | Accuracy |
|---|---|---|---|---|---|
| 0.6164 | 1.0 | 34 | 0.6186 | 0.0 | 0.6913 |
| 0.6071 | 2.0 | 68 | 0.6137 | 0.0 | 0.6913 |
| 0.6025 | 3.0 | 102 | 0.6132 | 0.0 | 0.6913 |
| 0.5865 | 4.0 | 136 | 0.6316 | 0.0464 | 0.6922 |
| 0.5525 | 5.0 | 170 | 0.6342 | 0.1771 | 0.7028 |
| 0.5122 | 6.0 | 204 | 0.6610 | 0.0883 | 0.6318 |
| 0.4796 | 7.0 | 238 | 0.7213 | 0.0713 | 0.6779 |
| 0.446 | 8.0 | 272 | 0.7225 | 0.0664 | 0.6433 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1