| --- |
| library_name: transformers |
| license: bsd-3-clause |
| base_model: Salesforce/codet5p-220m |
| tags: |
| - generated_from_trainer |
| metrics: |
| - rouge |
| model-index: |
| - name: constrative_cont |
| 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. --> |
|
|
| # constrative_cont |
| |
| This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 3.0823 |
| - Rouge1: 12.5556 |
| - Rouge2: 3.25 |
| - Rougel: 10.4444 |
| - Rougelsum: 10.2222 |
| - Gen Len: 11.8 |
| |
| ## 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: 10 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - gradient_accumulation_steps: 32 |
| - total_train_batch_size: 320 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 8 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
| |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
| | No log | 1.0 | 1 | 5.1699 | 5.6856 | 0.0 | 4.8309 | 5.0576 | 20.0 | |
| | No log | 2.0 | 2 | 5.1699 | 5.6856 | 0.0 | 4.8309 | 5.0576 | 20.0 | |
| | No log | 3.0 | 3 | 5.1699 | 5.6856 | 0.0 | 4.8309 | 5.0576 | 20.0 | |
| | No log | 4.0 | 4 | 4.0622 | 2.4 | 0.0 | 1.6 | 1.6 | 18.7 | |
| | No log | 5.0 | 5 | 3.5637 | 6.7206 | 1.0526 | 6.0343 | 6.0343 | 14.7 | |
| | No log | 6.0 | 6 | 3.3110 | 8.5233 | 0.0 | 6.575 | 6.9583 | 10.8 | |
| | No log | 7.0 | 7 | 3.1320 | 14.0635 | 3.0526 | 12.1905 | 12.1905 | 13.5 | |
| | No log | 8.0 | 8 | 3.0823 | 12.5556 | 3.25 | 10.4444 | 10.2222 | 11.8 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.55.4 |
| - Pytorch 2.8.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.21.4 |
|
|
