|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: small-mlm-glue-qnli-target-glue-mnli |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# small-mlm-glue-qnli-target-glue-mnli |
|
|
|
This model is a fine-tuned version of [muhtasham/small-mlm-glue-qnli](https://huggingface.co/muhtasham/small-mlm-glue-qnli) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6485 |
|
- Accuracy: 0.7301 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- training_steps: 5000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.9061 | 0.04 | 500 | 0.8129 | 0.6436 | |
|
| 0.8051 | 0.08 | 1000 | 0.7717 | 0.6652 | |
|
| 0.7687 | 0.12 | 1500 | 0.7466 | 0.6765 | |
|
| 0.7454 | 0.16 | 2000 | 0.7259 | 0.6920 | |
|
| 0.7392 | 0.2 | 2500 | 0.7105 | 0.6953 | |
|
| 0.7297 | 0.24 | 3000 | 0.6978 | 0.6995 | |
|
| 0.7117 | 0.29 | 3500 | 0.6829 | 0.7105 | |
|
| 0.7004 | 0.33 | 4000 | 0.6710 | 0.7146 | |
|
| 0.6787 | 0.37 | 4500 | 0.6734 | 0.7186 | |
|
| 0.6787 | 0.41 | 5000 | 0.6485 | 0.7301 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
