tiny-mlm-glue-cola-from-scratch-custom-tokenizer-target-glue-rte
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9954
- Accuracy: 0.4729
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 |
---|---|---|---|---|
0.693 | 6.41 | 500 | 0.6947 | 0.4549 |
0.6248 | 12.82 | 1000 | 0.8627 | 0.4729 |
0.4602 | 19.23 | 1500 | 1.1278 | 0.4657 |
0.3484 | 25.64 | 2000 | 1.3214 | 0.4801 |
0.2599 | 32.05 | 2500 | 1.6232 | 0.4693 |
0.2052 | 38.46 | 3000 | 1.7684 | 0.4801 |
0.1667 | 44.87 | 3500 | 1.9954 | 0.4729 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 8
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.