<!-- 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-qnli-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: 3.0716
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 |
---|---|---|---|
5.5339 | 0.4 | 500 | 4.7224 |
4.6477 | 0.8 | 1000 | 4.3242 |
4.3146 | 1.2 | 1500 | 3.9988 |
4.0046 | 1.6 | 2000 | 3.7777 |
3.7942 | 2.0 | 2500 | 3.5976 |
3.5684 | 2.4 | 3000 | 3.4426 |
3.4406 | 2.8 | 3500 | 3.3275 |
3.332 | 3.2 | 4000 | 3.2361 |
3.1941 | 3.6 | 4500 | 3.1616 |
3.0981 | 4.0 | 5000 | 3.0716 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2