<!-- 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-rte
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: 2.3426
- Accuracy: 0.5199
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 |
|---|---|---|---|---|
| 0.694 | 6.41 | 500 | 0.6929 | 0.5271 |
| 0.6741 | 12.82 | 1000 | 0.7605 | 0.5415 |
| 0.378 | 19.23 | 1500 | 1.1333 | 0.5523 |
| 0.2169 | 25.64 | 2000 | 1.5213 | 0.5415 |
| 0.1388 | 32.05 | 2500 | 1.8631 | 0.5560 |
| 0.1043 | 38.46 | 3000 | 2.0940 | 0.5307 |
| 0.0916 | 44.87 | 3500 | 2.2488 | 0.5307 |
| 0.072 | 51.28 | 4000 | 2.3426 | 0.5199 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
