|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-small-asap_t4_f1_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_f1_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: 0.0578 |
|
- Rouge1: 84.443 |
|
- Rouge2: 80.3833 |
|
- Rougel: 84.4646 |
|
- Rougelsum: 84.4359 |
|
- Gen Len: 12.1859 |
|
|
|
## 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 | 0.0936 | 79.5741 | 73.0518 | 79.6566 | 79.6486 | 12.0859 | |
|
| 0.4018 | 2.0 | 532 | 0.0670 | 83.6269 | 79.3655 | 83.6546 | 83.6338 | 12.1887 | |
|
| 0.4018 | 3.0 | 798 | 0.0596 | 83.4438 | 79.1374 | 83.4652 | 83.5119 | 12.2239 | |
|
| 0.0771 | 4.0 | 1064 | 0.0600 | 84.8381 | 80.8793 | 84.8927 | 84.9041 | 12.1549 | |
|
| 0.0771 | 5.0 | 1330 | 0.0578 | 84.443 | 80.3833 | 84.4646 | 84.4359 | 12.1859 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
