|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/bart-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: summarize_model_2 |
|
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. --> |
|
|
|
# summarize_model_2 |
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9198 |
|
- Rouge1: 0.2393 |
|
- Rouge2: 0.1023 |
|
- Rougel: 0.1976 |
|
- Rougelsum: 0.2243 |
|
- Gen Len: 20.0 |
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 100 | 1.9729 | 0.2374 | 0.099 | 0.1962 | 0.2216 | 20.0 | |
|
| No log | 2.0 | 200 | 1.9565 | 0.2398 | 0.1018 | 0.1972 | 0.2238 | 20.0 | |
|
| No log | 3.0 | 300 | 1.9241 | 0.2377 | 0.0991 | 0.1959 | 0.2215 | 20.0 | |
|
| No log | 4.0 | 400 | 1.9198 | 0.2393 | 0.1023 | 0.1976 | 0.2243 | 20.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
