tiny-mlm-glue-rte-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: 4.4372
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 |
|---|---|---|---|
| 6.249 | 1.6 | 500 | 5.5560 |
| 5.5772 | 3.21 | 1000 | 5.2693 |
| 5.3637 | 4.81 | 1500 | 5.0609 |
| 5.1969 | 6.41 | 2000 | 4.9263 |
| 5.1287 | 8.01 | 2500 | 4.8379 |
| 4.98 | 9.62 | 3000 | 4.6589 |
| 4.8837 | 11.22 | 3500 | 4.6109 |
| 4.8127 | 12.82 | 4000 | 4.5723 |
| 4.6909 | 14.42 | 4500 | 4.4488 |
| 4.5862 | 16.03 | 5000 | 4.4372 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2