metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
- accuracy
model-index:
- name: tiny_bert_rand_5_v1_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: 0.09519669889219669
- name: Accuracy
type: accuracy
value: 0.6960690021514893
tiny_bert_rand_5_v1_cola
This model is a fine-tuned version of Hartunka/tiny_bert_rand_5_v1 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6064
- Matthews Correlation: 0.0952
- Accuracy: 0.6961
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 | 0.6149 | 0.0 | 0.6913 |
| 0.5989 | 2.0 | 68 | 0.6079 | -0.0207 | 0.6903 |
| 0.5773 | 3.0 | 102 | 0.6064 | 0.0952 | 0.6961 |
| 0.5337 | 4.0 | 136 | 0.6351 | 0.0957 | 0.6587 |
| 0.4901 | 5.0 | 170 | 0.6574 | 0.1104 | 0.6683 |
| 0.4479 | 6.0 | 204 | 0.7045 | 0.1023 | 0.6500 |
| 0.4082 | 7.0 | 238 | 0.7739 | 0.0996 | 0.6385 |
| 0.3751 | 8.0 | 272 | 0.7742 | 0.1153 | 0.6405 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1