<!-- 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. -->
small-mlm-glue-wnli-from-scratch-custom-tokenizer-expand-vocab
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4922
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 |
|---|---|---|---|
| 7.1384 | 6.25 | 500 | 5.9999 |
| 5.8428 | 12.5 | 1000 | 5.6581 |
| 5.4846 | 18.75 | 1500 | 5.4843 |
| 5.1716 | 25.0 | 2000 | 5.3955 |
| 4.8633 | 31.25 | 2500 | 4.9234 |
| 4.6185 | 37.5 | 3000 | 4.6246 |
| 4.2975 | 43.75 | 3500 | 4.3933 |
| 4.0116 | 50.0 | 4000 | 4.1432 |
| 3.7556 | 56.25 | 4500 | 3.8816 |
| 3.5262 | 62.5 | 5000 | 3.4922 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
