<!-- 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-rte-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: 2.9781
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 |
---|---|---|---|
5.366 | 1.6 | 500 | 4.5434 |
4.5071 | 3.21 | 1000 | 4.1161 |
4.0413 | 4.81 | 1500 | 3.7831 |
3.6922 | 6.41 | 2000 | 3.4965 |
3.4951 | 8.01 | 2500 | 3.3765 |
3.2834 | 9.62 | 3000 | 3.1673 |
3.1036 | 11.22 | 3500 | 3.1155 |
2.9958 | 12.82 | 4000 | 3.0351 |
2.8456 | 14.42 | 4500 | 2.9650 |
2.6968 | 16.03 | 5000 | 2.9781 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2