|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
base_model: gokulsrinivasagan/bert_base_lda_100_v1 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- spearmanr |
|
model-index: |
|
- name: bert_base_lda_100_v1_stsb |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE STSB |
|
type: glue |
|
args: stsb |
|
metrics: |
|
- name: Spearmanr |
|
type: spearmanr |
|
value: 0.5325439607950028 |
|
--- |
|
|
|
<!-- 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_base_lda_100_v1_stsb |
|
|
|
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE STSB dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6844 |
|
- Pearson: 0.5330 |
|
- Spearmanr: 0.5325 |
|
- Combined Score: 0.5328 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| |
|
| 2.7331 | 1.0 | 23 | 2.6189 | 0.0643 | 0.0760 | 0.0701 | |
|
| 1.9804 | 2.0 | 46 | 2.0897 | 0.2818 | 0.2688 | 0.2753 | |
|
| 1.7486 | 3.0 | 69 | 1.9471 | 0.4158 | 0.4153 | 0.4155 | |
|
| 1.2963 | 4.0 | 92 | 2.3058 | 0.4520 | 0.4674 | 0.4597 | |
|
| 1.0162 | 5.0 | 115 | 1.8442 | 0.4887 | 0.4888 | 0.4888 | |
|
| 0.8446 | 6.0 | 138 | 1.7664 | 0.5228 | 0.5290 | 0.5259 | |
|
| 0.6767 | 7.0 | 161 | 1.7574 | 0.5152 | 0.5185 | 0.5168 | |
|
| 0.5349 | 8.0 | 184 | 1.6844 | 0.5330 | 0.5325 | 0.5328 | |
|
| 0.4606 | 9.0 | 207 | 1.9862 | 0.5039 | 0.5084 | 0.5062 | |
|
| 0.3951 | 10.0 | 230 | 1.8024 | 0.5266 | 0.5275 | 0.5270 | |
|
| 0.3624 | 11.0 | 253 | 2.0157 | 0.5342 | 0.5423 | 0.5382 | |
|
| 0.3087 | 12.0 | 276 | 2.4094 | 0.5227 | 0.5385 | 0.5306 | |
|
| 0.2879 | 13.0 | 299 | 2.0560 | 0.5304 | 0.5350 | 0.5327 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.2.1+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.20.3 |
|
|
