|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
base_model: gokulsrinivasagan/bert_tiny_lda_20_v1 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- spearmanr |
|
model-index: |
|
- name: bert_tiny_lda_20_v1_stsb |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE STSB |
|
type: glue |
|
args: stsb |
|
metrics: |
|
- name: Spearmanr |
|
type: spearmanr |
|
value: 0.206178007684053 |
|
--- |
|
|
|
<!-- 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_20_v1_stsb |
|
|
|
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE STSB dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4012 |
|
- Pearson: 0.2090 |
|
- Spearmanr: 0.2062 |
|
- Combined Score: 0.2076 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| |
|
| 2.8045 | 1.0 | 23 | 2.5136 | 0.0649 | 0.0635 | 0.0642 | |
|
| 2.0273 | 2.0 | 46 | 2.7011 | 0.1058 | 0.0988 | 0.1023 | |
|
| 1.9624 | 3.0 | 69 | 2.5059 | 0.1401 | 0.1321 | 0.1361 | |
|
| 1.7728 | 4.0 | 92 | 2.4245 | 0.1928 | 0.1900 | 0.1914 | |
|
| 1.5681 | 5.0 | 115 | 2.5047 | 0.2058 | 0.2035 | 0.2046 | |
|
| 1.3579 | 6.0 | 138 | 2.4012 | 0.2090 | 0.2062 | 0.2076 | |
|
| 1.1855 | 7.0 | 161 | 2.8718 | 0.2028 | 0.2035 | 0.2031 | |
|
| 0.9932 | 8.0 | 184 | 2.7053 | 0.2054 | 0.2051 | 0.2052 | |
|
| 0.8913 | 9.0 | 207 | 2.7462 | 0.1946 | 0.1937 | 0.1941 | |
|
| 0.8264 | 10.0 | 230 | 3.2676 | 0.1870 | 0.1825 | 0.1848 | |
|
| 0.7553 | 11.0 | 253 | 2.8757 | 0.1997 | 0.1970 | 0.1984 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.2.1+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.20.3 |
|
|
