small-mlm-glue-qnli-target-glue-cola
This model is a fine-tuned version of muhtasham/small-mlm-glue-qnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5412
- Matthews Correlation: 0.4140
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 | Matthews Correlation |
---|---|---|---|---|
0.5329 | 1.87 | 500 | 0.6440 | 0.2518 |
0.3419 | 3.73 | 1000 | 0.7266 | 0.3317 |
0.2216 | 5.6 | 1500 | 0.8836 | 0.3327 |
0.1539 | 7.46 | 2000 | 1.0337 | 0.3419 |
0.1183 | 9.33 | 2500 | 1.1863 | 0.3833 |
0.1029 | 11.19 | 3000 | 1.2204 | 0.3612 |
0.0913 | 13.06 | 3500 | 1.2910 | 0.3900 |
0.0736 | 14.93 | 4000 | 1.3354 | 0.3878 |
0.0615 | 16.79 | 4500 | 1.4930 | 0.3735 |
0.058 | 18.66 | 5000 | 1.5412 | 0.4140 |
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.