|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qnli |
|
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. --> |
|
|
|
# tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qnli |
|
|
|
This model is a fine-tuned version of [muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer](https://huggingface.co/muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6504 |
|
- Accuracy: 0.6180 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6935 | 0.15 | 500 | 0.6924 | 0.5634 | |
|
| 0.6894 | 0.31 | 1000 | 0.6736 | 0.5960 | |
|
| 0.672 | 0.46 | 1500 | 0.6572 | 0.6127 | |
|
| 0.6634 | 0.61 | 2000 | 0.6543 | 0.6112 | |
|
| 0.6616 | 0.76 | 2500 | 0.6527 | 0.6090 | |
|
| 0.6597 | 0.92 | 3000 | 0.6489 | 0.6158 | |
|
| 0.6507 | 1.07 | 3500 | 0.6505 | 0.6156 | |
|
| 0.6504 | 1.22 | 4000 | 0.6477 | 0.6134 | |
|
| 0.6443 | 1.37 | 4500 | 0.6496 | 0.6163 | |
|
| 0.646 | 1.53 | 5000 | 0.6504 | 0.6180 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
