<!-- 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-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: 6.1948
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 |
---|---|---|---|
7.6424 | 1.6 | 500 | 6.8053 |
6.6181 | 3.21 | 1000 | 6.5627 |
6.4748 | 4.81 | 1500 | 6.3601 |
6.3349 | 6.41 | 2000 | 6.3216 |
6.3151 | 8.01 | 2500 | 6.2345 |
6.2423 | 9.62 | 3000 | 6.1586 |
6.207 | 11.22 | 3500 | 6.1533 |
6.1629 | 12.82 | 4000 | 6.1586 |
6.12 | 14.42 | 4500 | 6.1554 |
6.0923 | 16.03 | 5000 | 6.1948 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2