|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- en |
|
|
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- spearmanr |
|
|
model-index: |
|
|
- name: bert_tiny_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: 0.22878969383272044 |
|
|
--- |
|
|
|
|
|
<!-- 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_stsb |
|
|
|
|
|
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 STSB dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.3632 |
|
|
- Pearson: 0.2350 |
|
|
- Spearmanr: 0.2288 |
|
|
- Combined Score: 0.2319 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:| |
|
|
| 2.8077 | 1.0 | 23 | 2.3850 | 0.0667 | 0.0654 | 0.0661 | |
|
|
| 2.042 | 2.0 | 46 | 2.6089 | 0.0834 | 0.0848 | 0.0841 | |
|
|
| 1.9254 | 3.0 | 69 | 2.3926 | 0.1539 | 0.1394 | 0.1466 | |
|
|
| 1.8381 | 4.0 | 92 | 2.5560 | 0.1744 | 0.1720 | 0.1732 | |
|
|
| 1.6974 | 5.0 | 115 | 3.0257 | 0.1812 | 0.1757 | 0.1784 | |
|
|
| 1.5776 | 6.0 | 138 | 2.3632 | 0.2350 | 0.2288 | 0.2319 | |
|
|
| 1.2951 | 7.0 | 161 | 2.4535 | 0.2594 | 0.2573 | 0.2584 | |
|
|
| 1.0896 | 8.0 | 184 | 2.5246 | 0.2652 | 0.2622 | 0.2637 | |
|
|
| 0.9372 | 9.0 | 207 | 2.9827 | 0.2716 | 0.2570 | 0.2643 | |
|
|
| 0.7915 | 10.0 | 230 | 2.6918 | 0.3056 | 0.2926 | 0.2991 | |
|
|
| 0.673 | 11.0 | 253 | 2.7520 | 0.3013 | 0.2887 | 0.2950 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.2.1+cu118 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
