<!-- 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. -->
tiny-mlm-glue-rte-from-scratch-custom-tokenizer-expand-vocab
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.5942
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 |
---|---|---|---|
9.3942 | 1.6 | 500 | 8.2703 |
7.5709 | 3.21 | 1000 | 7.0859 |
6.8768 | 4.81 | 1500 | 6.7010 |
6.676 | 6.41 | 2000 | 6.6826 |
6.667 | 8.01 | 2500 | 6.6476 |
6.6276 | 9.62 | 3000 | 6.6067 |
6.61 | 11.22 | 3500 | 6.5808 |
6.5894 | 12.82 | 4000 | 6.6076 |
6.5616 | 14.42 | 4500 | 6.5696 |
6.544 | 16.03 | 5000 | 6.5942 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2