metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_km_50_v2_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8069997526589167
- name: F1
type: f1
value: 0.7304197616168595
tiny_bert_km_50_v2_qqp
This model is a fine-tuned version of Hartunka/tiny_bert_km_50_v2 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4256
- Accuracy: 0.8070
- F1: 0.7304
- Combined Score: 0.7687
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.4993 | 1.0 | 1422 | 0.4612 | 0.7790 | 0.6616 | 0.7203 |
| 0.4141 | 2.0 | 2844 | 0.4278 | 0.7986 | 0.7121 | 0.7554 |
| 0.3569 | 3.0 | 4266 | 0.4256 | 0.8070 | 0.7304 | 0.7687 |
| 0.3108 | 4.0 | 5688 | 0.4395 | 0.8137 | 0.7326 | 0.7732 |
| 0.273 | 5.0 | 7110 | 0.4447 | 0.8171 | 0.7535 | 0.7853 |
| 0.2403 | 6.0 | 8532 | 0.4629 | 0.8187 | 0.7591 | 0.7889 |
| 0.2117 | 7.0 | 9954 | 0.4907 | 0.8172 | 0.7564 | 0.7868 |
| 0.1871 | 8.0 | 11376 | 0.5383 | 0.8219 | 0.7543 | 0.7881 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1