|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- en |
|
|
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: bert_tiny_lda_100_v1_mrpc |
|
|
results: |
|
|
- task: |
|
|
name: Text Classification |
|
|
type: text-classification |
|
|
dataset: |
|
|
name: GLUE MRPC |
|
|
type: glue |
|
|
args: mrpc |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.6813725490196079 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.7916666666666669 |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# bert_tiny_lda_100_v1_mrpc |
|
|
|
|
|
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE MRPC dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5925 |
|
|
- Accuracy: 0.6814 |
|
|
- F1: 0.7917 |
|
|
- Combined Score: 0.7365 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:| |
|
|
| 0.631 | 1.0 | 15 | 0.5996 | 0.6961 | 0.8171 | 0.7566 | |
|
|
| 0.5947 | 2.0 | 30 | 0.5925 | 0.6814 | 0.7917 | 0.7365 | |
|
|
| 0.5708 | 3.0 | 45 | 0.5934 | 0.7010 | 0.8135 | 0.7572 | |
|
|
| 0.5419 | 4.0 | 60 | 0.5990 | 0.6912 | 0.7961 | 0.7436 | |
|
|
| 0.4984 | 5.0 | 75 | 0.6380 | 0.6789 | 0.7950 | 0.7370 | |
|
|
| 0.4277 | 6.0 | 90 | 0.7020 | 0.6495 | 0.7386 | 0.6940 | |
|
|
| 0.3467 | 7.0 | 105 | 0.8055 | 0.6299 | 0.7318 | 0.6808 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.2.1+cu118 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
