metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_book_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7034313725490197
- name: F1
type: f1
value: 0.8129829984544049
bert_tiny_lda_book_mrpc
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_book on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5716
- Accuracy: 0.7034
- F1: 0.8130
- Combined Score: 0.7582
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 |
|---|---|---|---|---|---|---|
| 0.6221 | 1.0 | 15 | 0.5848 | 0.6961 | 0.8069 | 0.7515 |
| 0.5828 | 2.0 | 30 | 0.5716 | 0.7034 | 0.8130 | 0.7582 |
| 0.5377 | 3.0 | 45 | 0.5735 | 0.7230 | 0.8248 | 0.7739 |
| 0.4735 | 4.0 | 60 | 0.6391 | 0.7206 | 0.8257 | 0.7731 |
| 0.3841 | 5.0 | 75 | 0.6508 | 0.7034 | 0.8082 | 0.7558 |
| 0.3243 | 6.0 | 90 | 0.7159 | 0.7255 | 0.8233 | 0.7744 |
| 0.2591 | 7.0 | 105 | 0.9398 | 0.7181 | 0.8255 | 0.7718 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3