tiny-mlm-glue-cola-from-scratch-custom-tokenizer-expand-vocab-target-glue-mnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-from-scratch-custom-tokenizer-expand-vocab on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0276
- Accuracy: 0.4674
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 |
---|---|---|---|---|
1.0986 | 0.04 | 500 | 1.0969 | 0.3718 |
1.0962 | 0.08 | 1000 | 1.0945 | 0.3666 |
1.0855 | 0.12 | 1500 | 1.0747 | 0.4085 |
1.0653 | 0.16 | 2000 | 1.0666 | 0.4193 |
1.0599 | 0.2 | 2500 | 1.0542 | 0.4371 |
1.0522 | 0.24 | 3000 | 1.0414 | 0.4413 |
1.0435 | 0.29 | 3500 | 1.0455 | 0.4278 |
1.0359 | 0.33 | 4000 | 1.0366 | 0.4463 |
1.0339 | 0.37 | 4500 | 1.0327 | 0.4582 |
1.0275 | 0.41 | 5000 | 1.0276 | 0.4674 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 2