<!-- 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-cola-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: 2.7408
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 |
---|---|---|---|
4.9517 | 0.47 | 500 | 4.2375 |
4.2066 | 0.94 | 1000 | 3.8797 |
3.7476 | 1.4 | 1500 | 3.7590 |
3.6681 | 1.87 | 2000 | 3.5806 |
3.4312 | 2.34 | 2500 | 3.3642 |
3.3021 | 2.81 | 3000 | 3.0777 |
3.143 | 3.27 | 3500 | 3.2374 |
2.9997 | 3.74 | 4000 | 2.9701 |
2.9106 | 4.21 | 4500 | 3.0228 |
2.7981 | 4.68 | 5000 | 2.7408 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2