<!-- 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-mnli-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5250
- Accuracy: 0.7449
- F1: 0.6058
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 |
|---|---|---|---|---|---|
| 0.6373 | 0.04 | 500 | 0.6162 | 0.6563 | 0.3793 |
| 0.6053 | 0.09 | 1000 | 0.5908 | 0.6817 | 0.4690 |
| 0.5843 | 0.13 | 1500 | 0.5700 | 0.7007 | 0.5850 |
| 0.5672 | 0.18 | 2000 | 0.5554 | 0.7173 | 0.5632 |
| 0.5562 | 0.22 | 2500 | 0.5462 | 0.7277 | 0.5585 |
| 0.5484 | 0.26 | 3000 | 0.5382 | 0.7325 | 0.5848 |
| 0.5411 | 0.31 | 3500 | 0.5327 | 0.7384 | 0.6064 |
| 0.5388 | 0.35 | 4000 | 0.5335 | 0.7334 | 0.6310 |
| 0.5409 | 0.4 | 4500 | 0.5267 | 0.7416 | 0.6232 |
| 0.5322 | 0.44 | 5000 | 0.5250 | 0.7449 | 0.6058 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
