| | --- |
| | language: |
| | - en |
| | base_model: Hartunka/tiny_bert_km_50_v1 |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - glue |
| | metrics: |
| | - accuracy |
| | - f1 |
| | model-index: |
| | - name: tiny_bert_km_50_v1_mrpc |
| | results: |
| | - task: |
| | name: Text Classification |
| | type: text-classification |
| | dataset: |
| | name: GLUE MRPC |
| | type: glue |
| | args: mrpc |
| | metrics: |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.7034313725490197 |
| | - name: F1 |
| | type: f1 |
| | value: 0.8141321044546851 |
| | --- |
| | |
| | <!-- 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_50_v1_mrpc |
| | |
| | This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v1](https://huggingface.co/Hartunka/tiny_bert_km_50_v1) on the GLUE MRPC dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.5948 |
| | - Accuracy: 0.7034 |
| | - F1: 0.8141 |
| | - Combined Score: 0.7588 |
| | |
| | ## 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: 5e-05 |
| | - train_batch_size: 256 |
| | - eval_batch_size: 256 |
| | - seed: 10 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 50 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:| |
| | | 0.6321 | 1.0 | 15 | 0.6046 | 0.6961 | 0.8086 | 0.7524 | |
| | | 0.5989 | 2.0 | 30 | 0.6043 | 0.6936 | 0.8143 | 0.7539 | |
| | | 0.5748 | 3.0 | 45 | 0.5989 | 0.7010 | 0.8185 | 0.7597 | |
| | | 0.5524 | 4.0 | 60 | 0.5948 | 0.7034 | 0.8141 | 0.7588 | |
| | | 0.5052 | 5.0 | 75 | 0.6063 | 0.6936 | 0.7934 | 0.7435 | |
| | | 0.4327 | 6.0 | 90 | 0.6554 | 0.6887 | 0.7776 | 0.7332 | |
| | | 0.3584 | 7.0 | 105 | 0.7307 | 0.7059 | 0.7924 | 0.7491 | |
| | | 0.258 | 8.0 | 120 | 0.8256 | 0.6936 | 0.7856 | 0.7396 | |
| | | 0.1754 | 9.0 | 135 | 0.9983 | 0.6765 | 0.7617 | 0.7191 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.40.0 |
| | - Pytorch 2.6.0+cu124 |
| | - Datasets 3.5.0 |
| | - Tokenizers 0.19.1 |
| | |
