<!-- 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-mnli-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: 3.1856
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 |
---|---|---|---|
5.3498 | 0.4 | 500 | 4.6711 |
4.5654 | 0.8 | 1000 | 4.2629 |
4.2559 | 1.2 | 1500 | 3.9821 |
3.999 | 1.6 | 2000 | 3.8151 |
3.797 | 2.0 | 2500 | 3.6281 |
3.6349 | 2.4 | 3000 | 3.5233 |
3.4583 | 2.8 | 3500 | 3.4021 |
3.3824 | 3.2 | 4000 | 3.3251 |
3.2693 | 3.6 | 4500 | 3.2472 |
3.2468 | 4.0 | 5000 | 3.1856 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2