|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- spearmanr |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-stsb |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: glue |
|
type: glue |
|
args: stsb |
|
metrics: |
|
- name: Spearmanr |
|
type: spearmanr |
|
value: 0.8651841336703003 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert-base-uncased-finetuned-stsb |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5634 |
|
- Pearson: 0.8680 |
|
- Spearmanr: 0.8652 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:| |
|
| No log | 1.0 | 360 | 0.6646 | 0.8516 | 0.8494 | |
|
| 1.0238 | 2.0 | 720 | 0.5617 | 0.8666 | 0.8637 | |
|
| 0.3952 | 3.0 | 1080 | 0.6533 | 0.8649 | 0.8646 | |
|
| 0.3952 | 4.0 | 1440 | 0.5889 | 0.8651 | 0.8625 | |
|
| 0.2488 | 5.0 | 1800 | 0.5634 | 0.8680 | 0.8652 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|
