metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_5_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7009803921568627
- name: F1
type: f1
value: 0.8063492063492063
bert_tiny_lda_5_v1_mrpc
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_5_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5857
- Accuracy: 0.7010
- F1: 0.8063
- Combined Score: 0.7537
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 |
|---|---|---|---|---|---|---|
| 0.6309 | 1.0 | 15 | 0.5940 | 0.7108 | 0.8150 | 0.7629 |
| 0.5923 | 2.0 | 30 | 0.5857 | 0.7010 | 0.8063 | 0.7537 |
| 0.558 | 3.0 | 45 | 0.5883 | 0.6863 | 0.8006 | 0.7434 |
| 0.5259 | 4.0 | 60 | 0.6008 | 0.7010 | 0.7852 | 0.7431 |
| 0.456 | 5.0 | 75 | 0.6626 | 0.6716 | 0.7607 | 0.7161 |
| 0.3586 | 6.0 | 90 | 0.7173 | 0.6887 | 0.7776 | 0.7332 |
| 0.258 | 7.0 | 105 | 0.8888 | 0.6618 | 0.7621 | 0.7119 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3