small-mlm-glue-stsb-target-glue-qnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3477
- Accuracy: 0.8547
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 |
---|---|---|---|---|
0.4913 | 0.15 | 500 | 0.3941 | 0.8287 |
0.4468 | 0.31 | 1000 | 0.3872 | 0.8303 |
0.4246 | 0.46 | 1500 | 0.3619 | 0.8411 |
0.4133 | 0.61 | 2000 | 0.3757 | 0.8375 |
0.4133 | 0.76 | 2500 | 0.3445 | 0.8503 |
0.3958 | 0.92 | 3000 | 0.3340 | 0.8574 |
0.3576 | 1.07 | 3500 | 0.3426 | 0.8558 |
0.318 | 1.22 | 4000 | 0.3568 | 0.8559 |
0.3166 | 1.37 | 4500 | 0.3477 | 0.8547 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.