|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
base_model: Falconsai/text_summarization |
|
model-index: |
|
- name: model |
|
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. --> |
|
|
|
# model |
|
|
|
This model is a fine-tuned version of [Falconsai/text_summarization](https://huggingface.co/Falconsai/text_summarization) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.2990 |
|
- Rouge1: 0.1186 |
|
- Rouge2: 0.0198 |
|
- Rougel: 0.094 |
|
- Rougelsum: 0.094 |
|
- Gen Len: 19.9958 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 3.896 | 1.0 | 600 | 3.3871 | 0.1105 | 0.0171 | 0.0874 | 0.0874 | 20.0 | |
|
| 3.6922 | 2.0 | 1200 | 3.3257 | 0.116 | 0.0196 | 0.0921 | 0.0921 | 20.0 | |
|
| 3.6451 | 3.0 | 1800 | 3.3037 | 0.1189 | 0.0203 | 0.0947 | 0.0947 | 19.9972 | |
|
| 3.6179 | 4.0 | 2400 | 3.2990 | 0.1186 | 0.0198 | 0.094 | 0.094 | 19.9958 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
