<!-- 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-rte-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-rte-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5373
- Accuracy: 0.7328
- F1: 0.5855
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 |
|---|---|---|---|---|---|
| 0.6428 | 0.04 | 500 | 0.6240 | 0.6395 | 0.3516 |
| 0.6172 | 0.09 | 1000 | 0.6064 | 0.6580 | 0.4484 |
| 0.6041 | 0.13 | 1500 | 0.5965 | 0.6694 | 0.5605 |
| 0.5893 | 0.18 | 2000 | 0.5841 | 0.6870 | 0.4890 |
| 0.5831 | 0.22 | 2500 | 0.5723 | 0.6989 | 0.5243 |
| 0.5722 | 0.26 | 3000 | 0.5665 | 0.7023 | 0.5678 |
| 0.5666 | 0.31 | 3500 | 0.5607 | 0.7109 | 0.5612 |
| 0.5573 | 0.35 | 4000 | 0.5504 | 0.7196 | 0.5974 |
| 0.5547 | 0.4 | 4500 | 0.5430 | 0.7261 | 0.5975 |
| 0.5477 | 0.44 | 5000 | 0.5373 | 0.7328 | 0.5855 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
