<!-- 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-sst2-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5353
- Accuracy: 0.7384
- F1: 0.5955
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 |
|---|---|---|---|---|---|
| 0.6477 | 0.04 | 500 | 0.6218 | 0.6595 | 0.4548 |
| 0.6065 | 0.09 | 1000 | 0.5942 | 0.6828 | 0.4779 |
| 0.5835 | 0.13 | 1500 | 0.5717 | 0.7023 | 0.5821 |
| 0.5634 | 0.18 | 2000 | 0.5592 | 0.7181 | 0.5572 |
| 0.5579 | 0.22 | 2500 | 0.5512 | 0.7242 | 0.5639 |
| 0.5485 | 0.26 | 3000 | 0.5452 | 0.7285 | 0.5903 |
| 0.5478 | 0.31 | 3500 | 0.5432 | 0.7328 | 0.5845 |
| 0.5421 | 0.35 | 4000 | 0.5411 | 0.7310 | 0.6136 |
| 0.5475 | 0.4 | 4500 | 0.5372 | 0.7349 | 0.6120 |
| 0.5421 | 0.44 | 5000 | 0.5353 | 0.7384 | 0.5955 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
