| --- |
| tags: |
| - generated_from_trainer |
| datasets: |
| - Hartunka/processed_wikitext-103-raw-v1-km-20 |
| metrics: |
| - accuracy |
| model-index: |
| - name: tiny_bert_km_20_v1 |
| results: |
| - task: |
| name: Masked Language Modeling |
| type: fill-mask |
| dataset: |
| name: Hartunka/processed_wikitext-103-raw-v1-km-20 |
| type: Hartunka/processed_wikitext-103-raw-v1-km-20 |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.15358535344973726 |
| --- |
| |
| <!-- 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_bert_km_20_v1 |
|
|
| This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-km-20 dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 6.7550 |
| - Accuracy: 0.1536 |
| |
| ## 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: 0.0001 |
| - train_batch_size: 96 |
| - eval_batch_size: 96 |
| - seed: 10 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 10000 |
| - num_epochs: 25 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-------:|:-----:|:---------------:|:--------:| |
| | 6.7928 | 4.1982 | 10000 | 6.8629 | 0.1481 | |
| | 6.4284 | 8.3963 | 20000 | 6.7387 | 0.1528 | |
| | 6.2528 | 12.5945 | 30000 | 6.7938 | 0.1534 | |
| | 6.135 | 16.7926 | 40000 | 6.9908 | 0.1522 | |
| | 6.0725 | 20.9908 | 50000 | 7.0723 | 0.1516 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.40.0 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 3.5.0 |
| - Tokenizers 0.19.1 |
|
|
