| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: tiny-mlm-wikitext |
| | results: [] |
| | --- |
| | |
| | <!-- 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-wikitext |
| |
|
| | This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the None dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 4.5199 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 4.7982 | 0.4 | 500 | 4.4742 | |
| | | 4.7026 | 0.8 | 1000 | 4.4777 | |
| | | 4.6986 | 1.2 | 1500 | nan | |
| | | 4.6637 | 1.6 | 2000 | 4.4275 | |
| | | 4.6296 | 2.0 | 2500 | 4.4281 | |
| | | 4.6003 | 2.4 | 3000 | 4.4543 | |
| | | 4.5936 | 2.8 | 3500 | 4.5199 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.26.0.dev0 |
| | - Pytorch 1.13.0+cu116 |
| | - Datasets 2.8.1.dev0 |
| | - Tokenizers 0.13.2 |
| |
|
