|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
base_model: muhtasham/small-mlm-glue-qnli |
|
model-index: |
|
- name: small-mlm-glue-qnli-target-glue-sst2 |
|
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-sst2 |
|
|
|
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: 0.4217 |
|
- Accuracy: 0.8716 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.3912 | 0.24 | 500 | 0.3462 | 0.8406 | |
|
| 0.3049 | 0.48 | 1000 | 0.3246 | 0.8544 | |
|
| 0.2574 | 0.71 | 1500 | 0.3264 | 0.8739 | |
|
| 0.2381 | 0.95 | 2000 | 0.2983 | 0.8807 | |
|
| 0.1836 | 1.19 | 2500 | 0.3447 | 0.8784 | |
|
| 0.1681 | 1.43 | 3000 | 0.3553 | 0.8819 | |
|
| 0.1656 | 1.66 | 3500 | 0.3758 | 0.8784 | |
|
| 0.1701 | 1.9 | 4000 | 0.3134 | 0.8991 | |
|
| 0.1337 | 2.14 | 4500 | 0.5031 | 0.8521 | |
|
| 0.1232 | 2.38 | 5000 | 0.4217 | 0.8716 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
