<!-- 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-stsb-custom-tokenizer
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: 6.2898
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
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
7.2965 | 0.7 | 500 | 6.5781 |
6.4256 | 1.39 | 1000 | 6.4717 |
6.184 | 2.09 | 1500 | 6.2234 |
5.8599 | 2.78 | 2000 | 6.2671 |
5.895 | 3.48 | 2500 | 6.2723 |
5.7225 | 4.17 | 3000 | 6.2898 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2