|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/flan-t5-large |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flant5-large-lora |
|
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. --> |
|
|
|
# flant5-large-lora |
|
|
|
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co./google/flan-t5-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6119 |
|
- Rouge1: 8.9675 |
|
- Rouge2: 0.6714 |
|
- Rougel: 8.0407 |
|
- Rougelsum: 8.3753 |
|
- Gen Len: 18.37 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.8402 | 1.0 | 1538 | 0.7486 | 8.8441 | 0.6859 | 7.9731 | 8.3103 | 19.502 | |
|
| 0.8152 | 2.0 | 3076 | 0.6119 | 8.9675 | 0.6714 | 8.0407 | 8.3753 | 18.37 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.36.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.15.2 |
