metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
- accuracy
model-index:
- name: tiny_bert_rand_100_v2_cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE COLA
type: glue
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0
- name: Accuracy
type: accuracy
value: 0.6912751793861389
tiny_bert_rand_100_v2_cola
This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v2 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6166
- Matthews Correlation: 0.0
- Accuracy: 0.6913
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 |
|---|---|---|---|---|---|
| 0.6142 | 1.0 | 34 | 0.6166 | 0.0 | 0.6913 |
| 0.6003 | 2.0 | 68 | 0.6185 | 0.0 | 0.6913 |
| 0.5794 | 3.0 | 102 | 0.6215 | 0.0179 | 0.6874 |
| 0.5396 | 4.0 | 136 | 0.6724 | 0.0597 | 0.6711 |
| 0.4923 | 5.0 | 170 | 0.6689 | 0.0786 | 0.6453 |
| 0.4541 | 6.0 | 204 | 0.7376 | 0.0804 | 0.6261 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1