|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: LLM_Teached_Bart |
|
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. --> |
|
|
|
# LLM_Teached_Bart |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6728 |
|
- Rouge1: 0.3966 |
|
- Rouge2: 0.1905 |
|
- Rougel: 0.3321 |
|
- Rougelsum: 0.3322 |
|
- Gen Len: 19.9855 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.851 | 1.0 | 1250 | 1.6235 | 0.3808 | 0.1775 | 0.3177 | 0.318 | 19.9855 | |
|
| 1.5876 | 2.0 | 2500 | 1.5937 | 0.389 | 0.1866 | 0.3271 | 0.3274 | 19.9782 | |
|
| 1.3922 | 3.0 | 3750 | 1.5800 | 0.3899 | 0.182 | 0.3244 | 0.3246 | 19.9918 | |
|
| 1.2551 | 4.0 | 5000 | 1.6044 | 0.3852 | 0.1854 | 0.3223 | 0.3227 | 19.9982 | |
|
| 1.1329 | 5.0 | 6250 | 1.6191 | 0.3978 | 0.1923 | 0.3342 | 0.3344 | 19.9855 | |
|
| 1.042 | 6.0 | 7500 | 1.6453 | 0.3956 | 0.192 | 0.3333 | 0.3335 | 19.9864 | |
|
| 0.9665 | 7.0 | 8750 | 1.6554 | 0.3945 | 0.1898 | 0.331 | 0.3312 | 19.9909 | |
|
| 0.9206 | 8.0 | 10000 | 1.6728 | 0.3966 | 0.1905 | 0.3321 | 0.3322 | 19.9855 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.15.0 |
|
|