metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_20_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_20_v1_book_qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.8169503935566539
bert_tiny_lda_20_v1_book_qnli
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_20_v1_book on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4112
- Accuracy: 0.8170
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 |
|---|---|---|---|---|
| 0.5552 | 1.0 | 410 | 0.5006 | 0.7705 |
| 0.4442 | 2.0 | 820 | 0.4149 | 0.8155 |
| 0.378 | 3.0 | 1230 | 0.4112 | 0.8170 |
| 0.3178 | 4.0 | 1640 | 0.4808 | 0.8021 |
| 0.2591 | 5.0 | 2050 | 0.4954 | 0.7992 |
| 0.2115 | 6.0 | 2460 | 0.5165 | 0.8072 |
| 0.1671 | 7.0 | 2870 | 0.6289 | 0.7983 |
| 0.1377 | 8.0 | 3280 | 0.6667 | 0.7957 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3