tiny-mlm-glue-stsb-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: 4.4684
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 |
|---|---|---|---|
| 6.4557 | 0.7 | 500 | 5.4720 |
| 5.7672 | 1.39 | 1000 | 5.1064 |
| 5.4426 | 2.09 | 1500 | 5.0087 |
| 5.1495 | 2.78 | 2000 | 4.8300 |
| 5.186 | 3.48 | 2500 | 4.6170 |
| 5.0339 | 4.17 | 3000 | 4.6473 |
| 4.9093 | 4.87 | 3500 | 4.5680 |
| 4.9144 | 5.56 | 4000 | 4.6118 |
| 4.8143 | 6.26 | 4500 | 4.4421 |
| 4.8065 | 6.95 | 5000 | 4.4684 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2