| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: distilbert/distilbert-base-cased |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - rouge |
| model-index: |
| - name: df545d64e2eee43eeeab91c8bb51fb25 |
| 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. --> |
|
|
| # df545d64e2eee43eeeab91c8bb51fb25 |
|
|
| This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on the nyu-mll/glue [mnli] dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7537 |
| - Data Size: 1.0 |
| - Epoch Runtime: 325.9256 |
| - Accuracy: 0.7797 |
| - F1 Macro: 0.7793 |
| - Rouge1: 0.7798 |
| - Rouge2: 0.0 |
| - Rougel: 0.7798 |
| - Rougelsum: 0.7798 |
|
|
| ## 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 | 1.1005 | 0 | 2.9869 | 0.3545 | 0.1745 | 0.3544 | 0.0 | 0.3545 | 0.3543 | |
| | 1.0605 | 1 | 12271 | 0.9454 | 0.0078 | 5.8974 | 0.5638 | 0.5620 | 0.5640 | 0.0 | 0.5638 | 0.5639 | |
| | 0.8949 | 2 | 24542 | 0.8368 | 0.0156 | 8.2417 | 0.6395 | 0.6349 | 0.6397 | 0.0 | 0.6397 | 0.6396 | |
| | 0.7852 | 3 | 36813 | 0.7743 | 0.0312 | 13.3493 | 0.6633 | 0.6577 | 0.6632 | 0.0 | 0.6634 | 0.6633 | |
| | 0.7373 | 4 | 49084 | 0.6952 | 0.0625 | 23.0806 | 0.7144 | 0.7138 | 0.7145 | 0.0 | 0.7145 | 0.7143 | |
| | 0.6321 | 5 | 61355 | 0.6261 | 0.125 | 43.0151 | 0.7362 | 0.7354 | 0.7363 | 0.0 | 0.7361 | 0.7362 | |
| | 0.6133 | 6 | 73626 | 0.6297 | 0.25 | 79.9808 | 0.7430 | 0.7436 | 0.7429 | 0.0 | 0.7432 | 0.7430 | |
| | 0.5218 | 7 | 85897 | 0.5868 | 0.5 | 160.8165 | 0.7641 | 0.7628 | 0.7640 | 0.0 | 0.7642 | 0.7643 | |
| | 0.5068 | 8.0 | 98168 | 0.5666 | 1.0 | 319.1719 | 0.7797 | 0.7798 | 0.7795 | 0.0 | 0.7797 | 0.7798 | |
| | 0.4137 | 9.0 | 110439 | 0.5714 | 1.0 | 321.2843 | 0.7796 | 0.7780 | 0.7795 | 0.0 | 0.7796 | 0.7795 | |
| | 0.3429 | 10.0 | 122710 | 0.6298 | 1.0 | 332.5481 | 0.7815 | 0.7795 | 0.7814 | 0.0 | 0.7816 | 0.7816 | |
| | 0.2739 | 11.0 | 134981 | 0.7452 | 1.0 | 341.5238 | 0.7786 | 0.7785 | 0.7786 | 0.0 | 0.7784 | 0.7785 | |
| | 0.2477 | 12.0 | 147252 | 0.7537 | 1.0 | 325.9256 | 0.7797 | 0.7793 | 0.7798 | 0.0 | 0.7798 | 0.7798 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.57.0 |
| - Pytorch 2.8.0+cu128 |
| - Datasets 4.3.0 |
| - Tokenizers 0.22.1 |
|
|
