metadata
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_km_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert_km_5_v2_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8230521889685877
- name: F1
type: f1
value: 0.7504012281069011
distilbert_km_5_v2_qqp
This model is a fine-tuned version of Hartunka/distilbert_km_5_v2 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3882
- Accuracy: 0.8231
- F1: 0.7504
- Combined Score: 0.7867
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 |
|---|---|---|---|---|---|---|
| 0.466 | 1.0 | 1422 | 0.4240 | 0.7976 | 0.6967 | 0.7472 |
| 0.3554 | 2.0 | 2844 | 0.3882 | 0.8231 | 0.7504 | 0.7867 |
| 0.2749 | 3.0 | 4266 | 0.4049 | 0.8299 | 0.7661 | 0.7980 |
| 0.2101 | 4.0 | 5688 | 0.4614 | 0.8359 | 0.7609 | 0.7984 |
| 0.1628 | 5.0 | 7110 | 0.4931 | 0.8395 | 0.7771 | 0.8083 |
| 0.1295 | 6.0 | 8532 | 0.5082 | 0.8379 | 0.7819 | 0.8099 |
| 0.1044 | 7.0 | 9954 | 0.5692 | 0.8408 | 0.7836 | 0.8122 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1