<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
tiny-mlm-glue-qqp-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qqp-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5278
- Accuracy: 0.7438
- F1: 0.6220
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 | F1 |
|---|---|---|---|---|---|
| 0.6326 | 0.04 | 500 | 0.6031 | 0.6840 | 0.4888 |
| 0.5912 | 0.09 | 1000 | 0.5873 | 0.6955 | 0.5272 |
| 0.5854 | 0.13 | 1500 | 0.5739 | 0.7054 | 0.5911 |
| 0.57 | 0.18 | 2000 | 0.5590 | 0.7193 | 0.5856 |
| 0.5567 | 0.22 | 2500 | 0.5493 | 0.7283 | 0.5868 |
| 0.5521 | 0.26 | 3000 | 0.5407 | 0.7335 | 0.5945 |
| 0.5456 | 0.31 | 3500 | 0.5367 | 0.7354 | 0.6157 |
| 0.5396 | 0.35 | 4000 | 0.5352 | 0.7360 | 0.6261 |
| 0.5397 | 0.4 | 4500 | 0.5301 | 0.7388 | 0.6279 |
| 0.5322 | 0.44 | 5000 | 0.5278 | 0.7438 | 0.6220 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
