| --- |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: bart_test_p2 |
| 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. --> |
|
|
| # bart_test_p2 |
|
|
| This model was trained from scratch on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0076 |
|
|
| ## 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: 1e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 0.018 | 0.18 | 500 | 0.0096 | |
| | 0.0189 | 0.35 | 1000 | 0.0097 | |
| | 0.0184 | 0.53 | 1500 | 0.0098 | |
| | 0.0167 | 0.7 | 2000 | 0.0094 | |
| | 0.0162 | 0.88 | 2500 | 0.0092 | |
| | 0.0162 | 1.05 | 3000 | 0.0086 | |
| | 0.0124 | 1.23 | 3500 | 0.0086 | |
| | 0.0127 | 1.4 | 4000 | 0.0084 | |
| | 0.0129 | 1.58 | 4500 | 0.0083 | |
| | 0.0123 | 1.75 | 5000 | 0.0080 | |
| | 0.0123 | 1.93 | 5500 | 0.0081 | |
| | 0.0104 | 2.1 | 6000 | 0.0079 | |
| | 0.0094 | 2.28 | 6500 | 0.0079 | |
| | 0.0103 | 2.45 | 7000 | 0.0077 | |
| | 0.01 | 2.63 | 7500 | 0.0077 | |
| | 0.0098 | 2.8 | 8000 | 0.0077 | |
| | 0.0095 | 2.98 | 8500 | 0.0076 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.37.0.dev0 |
| - Pytorch 2.1.0.dev20230621+cu117 |
| - Datasets 2.17.0 |
| - Tokenizers 0.15.0 |
|
|
