| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/flan-t5-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - rouge |
| model-index: |
| - name: flan-t5-rouge-durga-q5-2 |
| 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. --> |
|
|
| # flan-t5-rouge-durga-q5-2 |
|
|
| This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0003 |
| - Rouge1: 0.4074 |
| - Rouge2: 0.3623 |
| - Rougel: 0.4073 |
| - Rougelsum: 0.4069 |
|
|
| ## 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: 0.0003 |
| - train_batch_size: 2 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - optimizer: Use 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: 30 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
| | 1.7277 | 1.0 | 170 | 1.6638 | 0.2259 | 0.1090 | 0.2030 | 0.2028 | |
| | 1.3022 | 2.0 | 340 | 1.2132 | 0.2330 | 0.1179 | 0.2093 | 0.2098 | |
| | 0.6794 | 3.0 | 510 | 0.8780 | 0.2513 | 0.1356 | 0.2275 | 0.2272 | |
| | 0.8604 | 4.0 | 680 | 0.6176 | 0.2754 | 0.1583 | 0.2487 | 0.2488 | |
| | 0.7036 | 5.0 | 850 | 0.4172 | 0.2856 | 0.1794 | 0.2654 | 0.2649 | |
| | 1.1999 | 6.0 | 1020 | 0.2687 | 0.2964 | 0.2057 | 0.2832 | 0.2827 | |
| | 0.5163 | 7.0 | 1190 | 0.1663 | 0.3011 | 0.2204 | 0.2913 | 0.2907 | |
| | 0.4279 | 8.0 | 1360 | 0.1198 | 0.3225 | 0.2403 | 0.3127 | 0.3123 | |
| | 0.0776 | 9.0 | 1530 | 0.0814 | 0.3335 | 0.2551 | 0.3241 | 0.3227 | |
| | 0.3049 | 10.0 | 1700 | 0.0485 | 0.3348 | 0.2651 | 0.3244 | 0.3240 | |
| | 0.1698 | 11.0 | 1870 | 0.0325 | 0.3505 | 0.2912 | 0.3459 | 0.3448 | |
| | 0.0392 | 12.0 | 2040 | 0.0258 | 0.3602 | 0.3025 | 0.3569 | 0.3569 | |
| | 0.0872 | 13.0 | 2210 | 0.0229 | 0.3714 | 0.3169 | 0.3697 | 0.3690 | |
| | 0.3979 | 14.0 | 2380 | 0.0141 | 0.3778 | 0.3236 | 0.3764 | 0.3758 | |
| | 0.1664 | 15.0 | 2550 | 0.0094 | 0.3897 | 0.3392 | 0.3890 | 0.3881 | |
| | 0.1912 | 16.0 | 2720 | 0.0065 | 0.3936 | 0.3441 | 0.3929 | 0.3921 | |
| | 0.1382 | 17.0 | 2890 | 0.0052 | 0.4003 | 0.3521 | 0.4003 | 0.3997 | |
| | 0.0843 | 18.0 | 3060 | 0.0028 | 0.4010 | 0.3541 | 0.4010 | 0.4008 | |
| | 0.307 | 19.0 | 3230 | 0.0023 | 0.4046 | 0.3585 | 0.4049 | 0.4042 | |
| | 0.0365 | 20.0 | 3400 | 0.0017 | 0.4052 | 0.3599 | 0.4056 | 0.4049 | |
| | 0.0067 | 21.0 | 3570 | 0.0014 | 0.4045 | 0.3588 | 0.4051 | 0.4044 | |
| | 0.0326 | 22.0 | 3740 | 0.0013 | 0.4055 | 0.3595 | 0.4059 | 0.4054 | |
| | 0.0979 | 23.0 | 3910 | 0.0009 | 0.4067 | 0.3613 | 0.4066 | 0.4062 | |
| | 0.001 | 24.0 | 4080 | 0.0005 | 0.4071 | 0.3618 | 0.4070 | 0.4066 | |
| | 0.0119 | 25.0 | 4250 | 0.0006 | 0.4064 | 0.3614 | 0.4067 | 0.4059 | |
| | 0.0481 | 26.0 | 4420 | 0.0003 | 0.4074 | 0.3623 | 0.4073 | 0.4069 | |
| | 0.0051 | 27.0 | 4590 | 0.0004 | 0.4074 | 0.3623 | 0.4073 | 0.4069 | |
| | 0.0053 | 28.0 | 4760 | 0.0003 | 0.4074 | 0.3623 | 0.4073 | 0.4069 | |
| | 0.0274 | 29.0 | 4930 | 0.0003 | 0.4074 | 0.3623 | 0.4073 | 0.4069 | |
| | 0.0129 | 30.0 | 5100 | 0.0003 | 0.4074 | 0.3623 | 0.4073 | 0.4069 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.46.0 |
| - Pytorch 2.5.0+cu121 |
| - Datasets 3.0.2 |
| - Tokenizers 0.20.1 |
|
|
