|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: sMPNG_t5_base_test |
|
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. --> |
|
|
|
# sMPNG_t5_base_test |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3948 |
|
- Bleu: 61.2155 |
|
- Gen Len: 7.3325 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:| |
|
| 0.889 | 1.0 | 5246 | 0.7274 | 43.8011 | 7.0999 | |
|
| 0.7403 | 2.0 | 10492 | 0.6177 | 48.5778 | 7.2271 | |
|
| 0.6483 | 3.0 | 15738 | 0.5612 | 51.6132 | 7.131 | |
|
| 0.5839 | 4.0 | 20984 | 0.5213 | 53.6657 | 7.2675 | |
|
| 0.5613 | 5.0 | 26230 | 0.4986 | 55.0196 | 7.2437 | |
|
| 0.5172 | 6.0 | 31476 | 0.4797 | 56.0442 | 7.3339 | |
|
| 0.4929 | 7.0 | 36722 | 0.4588 | 56.7114 | 7.3136 | |
|
| 0.4786 | 8.0 | 41968 | 0.4452 | 57.7053 | 7.3036 | |
|
| 0.4382 | 9.0 | 47214 | 0.4341 | 57.9617 | 7.2889 | |
|
| 0.4214 | 10.0 | 52460 | 0.4268 | 58.3971 | 7.3519 | |
|
| 0.4187 | 11.0 | 57706 | 0.4178 | 58.9582 | 7.3124 | |
|
| 0.397 | 12.0 | 62952 | 0.4115 | 59.5624 | 7.2993 | |
|
| 0.3848 | 13.0 | 68198 | 0.4049 | 60.4898 | 7.3177 | |
|
| 0.3635 | 14.0 | 73444 | 0.4037 | 60.5544 | 7.3293 | |
|
| 0.3669 | 15.0 | 78690 | 0.4015 | 60.8635 | 7.3081 | |
|
| 0.3675 | 16.0 | 83936 | 0.3968 | 60.8527 | 7.3213 | |
|
| 0.3548 | 17.0 | 89182 | 0.3974 | 60.8292 | 7.3292 | |
|
| 0.3534 | 18.0 | 94428 | 0.3944 | 61.1633 | 7.3402 | |
|
| 0.35 | 19.0 | 99674 | 0.3947 | 61.1179 | 7.3329 | |
|
| 0.3299 | 20.0 | 104920 | 0.3948 | 61.2155 | 7.3325 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
