metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/distilbert_lda_100_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert_lda_100_v1_book_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6911764705882353
- name: F1
type: f1
value: 0.8061538461538461
distilbert_lda_100_v1_book_mrpc
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_100_v1_book on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5726
- Accuracy: 0.6912
- F1: 0.8062
- Combined Score: 0.7487
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 OptimizerNames.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 |
|---|---|---|---|---|---|---|
| 0.6251 | 1.0 | 15 | 0.5960 | 0.6838 | 0.8054 | 0.7446 |
| 0.5807 | 2.0 | 30 | 0.5726 | 0.6912 | 0.8062 | 0.7487 |
| 0.516 | 3.0 | 45 | 0.5825 | 0.7181 | 0.8223 | 0.7702 |
| 0.4062 | 4.0 | 60 | 0.5988 | 0.7255 | 0.8108 | 0.7682 |
| 0.2808 | 5.0 | 75 | 0.6600 | 0.7525 | 0.8279 | 0.7902 |
| 0.1683 | 6.0 | 90 | 0.9784 | 0.7353 | 0.8302 | 0.7827 |
| 0.1568 | 7.0 | 105 | 0.9396 | 0.7328 | 0.8239 | 0.7784 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1