metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_100_v1_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.7035191212367778
bert_tiny_lda_100_v1_mnli
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_100_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6947
- Accuracy: 0.7035
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 |
|---|---|---|---|---|
| 0.9642 | 1.0 | 1534 | 0.8561 | 0.6113 |
| 0.8313 | 2.0 | 3068 | 0.7812 | 0.6520 |
| 0.757 | 3.0 | 4602 | 0.7462 | 0.6743 |
| 0.6957 | 4.0 | 6136 | 0.7300 | 0.6888 |
| 0.6441 | 5.0 | 7670 | 0.7240 | 0.6961 |
| 0.5971 | 6.0 | 9204 | 0.7375 | 0.6971 |
| 0.5545 | 7.0 | 10738 | 0.7476 | 0.7041 |
| 0.5132 | 8.0 | 12272 | 0.7632 | 0.7020 |
| 0.4736 | 9.0 | 13806 | 0.8263 | 0.7010 |
| 0.4355 | 10.0 | 15340 | 0.8340 | 0.7018 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3