<!-- 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. -->
small-mlm-glue-cola-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/small-mlm-glue-cola-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5380
- Accuracy: 0.7325
- F1: 0.6504
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 |
|---|---|---|---|---|---|
| 0.6189 | 0.04 | 500 | 0.5841 | 0.6894 | 0.5378 |
| 0.5752 | 0.09 | 1000 | 0.5877 | 0.7141 | 0.5171 |
| 0.5632 | 0.13 | 1500 | 0.5486 | 0.7209 | 0.5983 |
| 0.5514 | 0.18 | 2000 | 0.5407 | 0.7277 | 0.5486 |
| 0.5475 | 0.22 | 2500 | 0.5317 | 0.7350 | 0.5728 |
| 0.539 | 0.26 | 3000 | 0.5265 | 0.7353 | 0.5817 |
| 0.534 | 0.31 | 3500 | 0.5307 | 0.7375 | 0.5567 |
| 0.5297 | 0.35 | 4000 | 0.5605 | 0.7085 | 0.6476 |
| 0.5288 | 0.4 | 4500 | 0.5188 | 0.7438 | 0.5954 |
| 0.5166 | 0.44 | 5000 | 0.5380 | 0.7325 | 0.6504 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
