tiny-mlm-glue-cola-custom-tokenizer-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5086
- Accuracy: 0.7511
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 |
---|---|---|---|---|
0.6301 | 0.15 | 500 | 0.5812 | 0.6989 |
0.5891 | 0.31 | 1000 | 0.5807 | 0.6996 |
0.5748 | 0.46 | 1500 | 0.5480 | 0.7263 |
0.5642 | 0.61 | 2000 | 0.5706 | 0.7137 |
0.5622 | 0.76 | 2500 | 0.5364 | 0.7346 |
0.5575 | 0.92 | 3000 | 0.5056 | 0.7562 |
0.5462 | 1.07 | 3500 | 0.5127 | 0.7490 |
0.5427 | 1.22 | 4000 | 0.5157 | 0.7507 |
0.529 | 1.37 | 4500 | 0.5086 | 0.7511 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 2
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.