metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_100_v1_book_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.7589503661513426
bert_tiny_lda_100_v1_book_mnli
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_100_v1_book on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6109
- Accuracy: 0.7590
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 |
|---|---|---|---|---|
| 0.7993 | 1.0 | 1534 | 0.6938 | 0.7060 |
| 0.6472 | 2.0 | 3068 | 0.6425 | 0.7343 |
| 0.5649 | 3.0 | 4602 | 0.6277 | 0.7479 |
| 0.4986 | 4.0 | 6136 | 0.6238 | 0.7495 |
| 0.4399 | 5.0 | 7670 | 0.6533 | 0.7545 |
| 0.3857 | 6.0 | 9204 | 0.7154 | 0.7527 |
| 0.3351 | 7.0 | 10738 | 0.7138 | 0.7572 |
| 0.2914 | 8.0 | 12272 | 0.7700 | 0.7533 |
| 0.2533 | 9.0 | 13806 | 0.8576 | 0.7496 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3