|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/flan-t5-small |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-base |
|
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-base |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7474 |
|
- Rouge1: 15.6258 |
|
- Rouge2: 5.8684 |
|
- Rougel: 13.5135 |
|
- Rougelsum: 14.5266 |
|
- Gen Len: 19.0 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.3424 | 0.27 | 500 | 2.0519 | 13.8547 | 4.8819 | 12.0331 | 12.8514 | 19.0 | |
|
| 2.1616 | 0.53 | 1000 | 1.9535 | 14.7848 | 5.382 | 12.8365 | 13.6475 | 19.0 | |
|
| 2.0723 | 0.8 | 1500 | 1.9142 | 14.6906 | 5.434 | 12.8341 | 13.6491 | 19.0 | |
|
| 2.0202 | 1.07 | 2000 | 1.8883 | 14.8456 | 5.5148 | 12.7977 | 13.7626 | 19.0 | |
|
| 1.9921 | 1.33 | 2500 | 1.8473 | 14.8381 | 5.555 | 12.791 | 13.6959 | 19.0 | |
|
| 1.9539 | 1.6 | 3000 | 1.8293 | 15.2161 | 5.7276 | 13.1915 | 14.1315 | 19.0 | |
|
| 1.9455 | 1.87 | 3500 | 1.8166 | 15.2705 | 5.6751 | 13.2908 | 14.2064 | 19.0 | |
|
| 1.9266 | 2.13 | 4000 | 1.8018 | 15.303 | 5.7225 | 13.2318 | 14.1942 | 19.0 | |
|
| 1.8949 | 2.4 | 4500 | 1.7904 | 15.7181 | 6.0653 | 13.6993 | 14.5572 | 19.0 | |
|
| 1.906 | 2.67 | 5000 | 1.7814 | 15.7143 | 5.9897 | 13.6178 | 14.5986 | 19.0 | |
|
| 1.8737 | 2.93 | 5500 | 1.7706 | 15.4469 | 5.8011 | 13.3005 | 14.3128 | 19.0 | |
|
| 1.8779 | 3.2 | 6000 | 1.7668 | 15.6243 | 5.9534 | 13.5025 | 14.5397 | 19.0 | |
|
| 1.8638 | 3.47 | 6500 | 1.7629 | 15.3433 | 5.6495 | 13.251 | 14.3 | 19.0 | |
|
| 1.8644 | 3.73 | 7000 | 1.7559 | 15.4275 | 5.6924 | 13.2484 | 14.3135 | 19.0 | |
|
| 1.8389 | 4.0 | 7500 | 1.7522 | 15.5374 | 5.8713 | 13.4588 | 14.4702 | 19.0 | |
|
| 1.8467 | 4.27 | 8000 | 1.7507 | 15.47 | 5.7876 | 13.3985 | 14.4401 | 19.0 | |
|
| 1.8287 | 4.53 | 8500 | 1.7502 | 15.4761 | 5.7342 | 13.3502 | 14.4118 | 19.0 | |
|
| 1.8439 | 4.8 | 9000 | 1.7474 | 15.6258 | 5.8684 | 13.5135 | 14.5266 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
