|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: LLM_Teached_Bart_FromScratch |
|
|
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_FromScratch |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.7504 |
|
|
- Rouge1: 0.3746 |
|
|
- Rouge2: 0.1776 |
|
|
- Rougel: 0.3165 |
|
|
- Rougelsum: 0.3164 |
|
|
- Gen Len: 19.9727 |
|
|
|
|
|
## 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: 4 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
|
| 1.0692 | 1.0 | 625 | 1.7369 | 0.3826 | 0.1796 | 0.3166 | 0.3164 | 19.9691 | |
|
|
| 0.9466 | 2.0 | 1250 | 1.7602 | 0.3738 | 0.1772 | 0.3142 | 0.3143 | 20.0 | |
|
|
| 0.8898 | 3.0 | 1875 | 1.7657 | 0.3778 | 0.1751 | 0.3156 | 0.3157 | 19.9727 | |
|
|
| 0.8871 | 4.0 | 2500 | 1.7504 | 0.3746 | 0.1776 | 0.3165 | 0.3164 | 19.9727 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.0 |
|
|
- Pytorch 2.0.1+cu117 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.15.0 |
|
|
|
