| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: distilbert/distilroberta-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - rouge |
| model-index: |
| - name: d4642015f9fa8db06d31232a6745c19f |
| 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. --> |
|
|
| # d4642015f9fa8db06d31232a6745c19f |
|
|
| This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the google/boolq dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9388 |
| - Data Size: 1.0 |
| - Epoch Runtime: 13.8599 |
| - Accuracy: 0.7215 |
| - F1 Macro: 0.7022 |
| - Rouge1: 0.7218 |
| - Rouge2: 0.0 |
| - Rougel: 0.7209 |
| - Rougelsum: 0.7209 |
|
|
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - num_devices: 4 |
| - total_train_batch_size: 32 |
| - total_eval_batch_size: 32 |
| - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: constant |
| - num_epochs: 50 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro | Rouge1 | Rouge2 | Rougel | Rougelsum | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------------:|:--------:|:--------:|:------:|:------:|:------:|:---------:| |
| | No log | 0 | 0 | 0.7378 | 0 | 2.0385 | 0.3787 | 0.2747 | 0.3787 | 0.0 | 0.3793 | 0.3790 | |
| | No log | 1 | 294 | 0.6905 | 0.0078 | 2.6280 | 0.5643 | 0.5106 | 0.5650 | 0.0 | 0.5646 | 0.5646 | |
| | No log | 2 | 588 | 0.6615 | 0.0156 | 2.5438 | 0.6213 | 0.3832 | 0.6213 | 0.0 | 0.6207 | 0.6210 | |
| | No log | 3 | 882 | 0.6658 | 0.0312 | 2.8860 | 0.6198 | 0.3857 | 0.6201 | 0.0 | 0.6195 | 0.6198 | |
| | 0.027 | 4 | 1176 | 0.6602 | 0.0625 | 3.4238 | 0.6213 | 0.3832 | 0.6213 | 0.0 | 0.6207 | 0.6210 | |
| | 0.0552 | 5 | 1470 | 0.6547 | 0.125 | 4.1016 | 0.6213 | 0.3832 | 0.6213 | 0.0 | 0.6207 | 0.6210 | |
| | 0.0935 | 6 | 1764 | 0.6467 | 0.25 | 5.5563 | 0.6471 | 0.5745 | 0.6471 | 0.0 | 0.6468 | 0.6474 | |
| | 0.6078 | 7 | 2058 | 0.6134 | 0.5 | 8.3762 | 0.6838 | 0.6222 | 0.6841 | 0.0 | 0.6829 | 0.6841 | |
| | 0.5437 | 8.0 | 2352 | 0.5814 | 1.0 | 14.4086 | 0.6952 | 0.6273 | 0.6955 | 0.0 | 0.6949 | 0.6953 | |
| | 0.4424 | 9.0 | 2646 | 0.6237 | 1.0 | 13.7459 | 0.7255 | 0.6899 | 0.7255 | 0.0 | 0.7255 | 0.7258 | |
| | 0.293 | 10.0 | 2940 | 0.7580 | 1.0 | 13.7696 | 0.7117 | 0.7017 | 0.7119 | 0.0 | 0.7114 | 0.7111 | |
| | 0.1986 | 11.0 | 3234 | 0.8660 | 1.0 | 13.5540 | 0.7390 | 0.7105 | 0.7393 | 0.0 | 0.7390 | 0.7384 | |
| | 0.162 | 12.0 | 3528 | 0.9388 | 1.0 | 13.8599 | 0.7215 | 0.7022 | 0.7218 | 0.0 | 0.7209 | 0.7209 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.57.0 |
| - Pytorch 2.8.0+cu128 |
| - Datasets 4.3.0 |
| - Tokenizers 0.22.1 |
|
|
