metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: muhtasham/tiny-mlm-glue-stsb
model-index:
- name: tiny-mlm-glue-stsb-target-glue-qnli
results: []
tiny-mlm-glue-stsb-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4694
- Accuracy: 0.7802
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6099 | 0.15 | 500 | 0.5424 | 0.7315 |
| 0.5423 | 0.31 | 1000 | 0.5368 | 0.7338 |
| 0.5201 | 0.46 | 1500 | 0.4987 | 0.7624 |
| 0.5152 | 0.61 | 2000 | 0.5225 | 0.7494 |
| 0.512 | 0.76 | 2500 | 0.4830 | 0.7763 |
| 0.505 | 0.92 | 3000 | 0.4704 | 0.7833 |
| 0.4908 | 1.07 | 3500 | 0.4560 | 0.7921 |
| 0.4805 | 1.22 | 4000 | 0.4691 | 0.7818 |
| 0.4682 | 1.37 | 4500 | 0.4733 | 0.7780 |
| 0.4739 | 1.53 | 5000 | 0.4694 | 0.7802 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2