|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- spearmanr |
|
model-index: |
|
- name: bert_tiny_lda_100_v1_book_stsb |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE STSB |
|
type: glue |
|
args: stsb |
|
metrics: |
|
- name: Spearmanr |
|
type: spearmanr |
|
value: 0.801612109444843 |
|
--- |
|
|
|
<!-- 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_book_stsb |
|
|
|
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE STSB dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7928 |
|
- Pearson: 0.8049 |
|
- Spearmanr: 0.8016 |
|
- Combined Score: 0.8033 |
|
|
|
## 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 | Pearson | Spearmanr | Combined Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| |
|
| 3.1938 | 1.0 | 23 | 2.4088 | 0.1233 | 0.1363 | 0.1298 | |
|
| 1.724 | 2.0 | 46 | 1.3509 | 0.6695 | 0.6702 | 0.6698 | |
|
| 1.1162 | 3.0 | 69 | 0.9383 | 0.7654 | 0.7625 | 0.7639 | |
|
| 0.8449 | 4.0 | 92 | 0.8558 | 0.7876 | 0.7849 | 0.7863 | |
|
| 0.7011 | 5.0 | 115 | 0.9826 | 0.7761 | 0.7835 | 0.7798 | |
|
| 0.6154 | 6.0 | 138 | 0.8605 | 0.7884 | 0.7859 | 0.7871 | |
|
| 0.5011 | 7.0 | 161 | 0.7928 | 0.8049 | 0.8016 | 0.8033 | |
|
| 0.4464 | 8.0 | 184 | 0.8498 | 0.8009 | 0.7998 | 0.8003 | |
|
| 0.3985 | 9.0 | 207 | 0.8156 | 0.7999 | 0.7968 | 0.7984 | |
|
| 0.3519 | 10.0 | 230 | 0.8549 | 0.8050 | 0.8028 | 0.8039 | |
|
| 0.366 | 11.0 | 253 | 0.8143 | 0.8063 | 0.8037 | 0.8050 | |
|
| 0.3156 | 12.0 | 276 | 0.8117 | 0.8090 | 0.8066 | 0.8078 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.2.1+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.20.3 |
|
|
