|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/flan-t5-base |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the [BYC-Sophie/samsum-chatgpt-summary](https://huggingface.co/datasets/BYC-Sophie/samsum-chatgpt-summary) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8634 |
|
|
|
## Model description |
|
|
|
Fine-tuned FLAN-T5 on a derivative of the `samsum` dataset. |
|
|
|
## Intended uses & limitations |
|
|
|
Summarisation of dialogue text. |
|
|
|
## Training and evaluation data |
|
|
|
Fine tuned with the `BYC-Sophie/samsum-chatgpt-summary` dataset, which has improved summaries generated by ChatGPT. |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0001 |
|
- 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: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.7323 | 1.0 | 1842 | 1.8218 | |
|
| 1.6814 | 2.0 | 3684 | 1.8469 | |
|
| 1.6481 | 3.0 | 5526 | 1.8574 | |
|
| 1.6333 | 4.0 | 7368 | 1.8634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
