metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_train_book_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
- accuracy
model-index:
- name: tinybert_train_book_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: 0.35481258251848646
- name: Accuracy
type: accuracy
value: 0.7497603297233582
tinybert_train_book_v2_cola
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_v2 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.5581
- Matthews Correlation: 0.3548
- Accuracy: 0.7498
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 |
|---|---|---|---|---|---|
| 0.6023 | 1.0 | 34 | 0.5807 | 0.1550 | 0.7018 |
| 0.5434 | 2.0 | 68 | 0.5668 | 0.2171 | 0.7133 |
| 0.4545 | 3.0 | 102 | 0.5581 | 0.3548 | 0.7498 |
| 0.3891 | 4.0 | 136 | 0.5984 | 0.2945 | 0.7315 |
| 0.3257 | 5.0 | 170 | 0.5831 | 0.3679 | 0.7402 |
| 0.2676 | 6.0 | 204 | 0.6336 | 0.3452 | 0.7354 |
| 0.2335 | 7.0 | 238 | 0.6995 | 0.3774 | 0.7555 |
| 0.2028 | 8.0 | 272 | 0.7774 | 0.3592 | 0.7488 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3