|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-base-insights |
|
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-insights |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9344 |
|
- Rouge1: 8.8258 |
|
- Rouge2: 6.8021 |
|
- Rougel: 8.5566 |
|
- Rougelsum: 8.7828 |
|
- 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.6073 | 1.0 | 172 | 1.2435 | 8.9196 | 6.9144 | 8.8527 | 8.7692 | 19.0 | |
|
| 1.3038 | 2.0 | 344 | 1.0558 | 8.9196 | 6.9144 | 8.8527 | 8.7692 | 19.0 | |
|
| 1.14 | 3.0 | 516 | 0.9817 | 8.7663 | 6.5345 | 8.4648 | 8.731 | 19.0 | |
|
| 1.1009 | 4.0 | 688 | 0.9463 | 8.6299 | 6.3863 | 8.2671 | 8.6138 | 19.0 | |
|
| 1.0771 | 5.0 | 860 | 0.9344 | 8.8258 | 6.8021 | 8.5566 | 8.7828 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
