|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-small-asap_t4_f2_prompt_adherence |
|
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-small-asap_t4_f2_prompt_adherence |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0621 |
|
- Rouge1: 82.6646 |
|
- Rouge2: 78.018 |
|
- Rougel: 82.6132 |
|
- Rougelsum: 82.6206 |
|
- Gen Len: 12.1479 |
|
|
|
## 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 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 266 | 0.0875 | 79.5052 | 73.4411 | 79.5255 | 79.4473 | 12.2169 | |
|
| 0.396 | 2.0 | 532 | 0.0694 | 80.9177 | 75.9474 | 80.9177 | 80.8659 | 12.1817 | |
|
| 0.396 | 3.0 | 798 | 0.0619 | 82.55 | 77.8505 | 82.5292 | 82.4624 | 12.1437 | |
|
| 0.0734 | 4.0 | 1064 | 0.0611 | 82.5957 | 77.9529 | 82.5931 | 82.5353 | 12.1380 | |
|
| 0.0734 | 5.0 | 1330 | 0.0621 | 82.6646 | 78.018 | 82.6132 | 82.6206 | 12.1479 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
