<!-- 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-wnli-custom-tokenizer-expand-vocab
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6887
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 |
|---|---|---|---|
| 4.719 | 6.25 | 500 | 3.7847 |
| 4.0062 | 12.5 | 1000 | 3.4790 |
| 3.5607 | 18.75 | 1500 | 3.3417 |
| 3.3 | 25.0 | 2000 | 2.9815 |
| 3.0174 | 31.25 | 2500 | 2.7710 |
| 2.8668 | 37.5 | 3000 | 2.5395 |
| 2.6312 | 43.75 | 3500 | 2.4257 |
| 2.4138 | 50.0 | 4000 | 1.9615 |
| 2.2602 | 56.25 | 4500 | 2.1444 |
| 2.1614 | 62.5 | 5000 | 1.6887 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
