|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_sa_GLUE_Experiment_logit_kd_qnli |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE QNLI |
|
type: glue |
|
config: qnli |
|
split: validation |
|
args: qnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.5905180303862346 |
|
--- |
|
|
|
<!-- 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_sa_GLUE_Experiment_logit_kd_qnli |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3865 |
|
- Accuracy: 0.5905 |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4069 | 1.0 | 410 | 0.3914 | 0.5680 | |
|
| 0.3877 | 2.0 | 820 | 0.3865 | 0.5905 | |
|
| 0.3741 | 3.0 | 1230 | 0.3917 | 0.5971 | |
|
| 0.3604 | 4.0 | 1640 | 0.3893 | 0.5929 | |
|
| 0.3432 | 5.0 | 2050 | 0.3908 | 0.5922 | |
|
| 0.3194 | 6.0 | 2460 | 0.4251 | 0.5861 | |
|
| 0.2938 | 7.0 | 2870 | 0.4414 | 0.5940 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.14.0a0+410ce96 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|