|
--- |
|
license: other |
|
base_model: aubmindlab/aragpt2-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
- rouge |
|
model-index: |
|
- name: res_nw_yem_aragpt2-large |
|
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. --> |
|
|
|
# res_nw_yem_aragpt2-large |
|
|
|
This model is a fine-tuned version of [aubmindlab/aragpt2-large](https://huggingface.co/aubmindlab/aragpt2-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0469 |
|
- Bleu: 0.0733 |
|
- Rouge1: 0.3956 |
|
- Rouge2: 0.1677 |
|
- Rougel: 0.3901 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 20.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:| |
|
| 0.8644 | 1.0 | 305 | 0.0499 | 0.0310 | 0.2976 | 0.0825 | 0.2932 | |
|
| 0.0439 | 2.0 | 610 | 0.0469 | 0.0733 | 0.3956 | 0.1677 | 0.3901 | |
|
| 0.0307 | 3.0 | 915 | 0.0474 | 0.0901 | 0.4411 | 0.2093 | 0.4361 | |
|
| 0.0212 | 4.0 | 1220 | 0.0497 | 0.1039 | 0.4643 | 0.2315 | 0.4591 | |
|
| 0.016 | 5.0 | 1525 | 0.0541 | 0.0923 | 0.4641 | 0.2229 | 0.4600 | |
|
| 0.0134 | 6.0 | 1830 | 0.0531 | 0.1160 | 0.4746 | 0.2503 | 0.4699 | |
|
| 0.0118 | 7.0 | 2135 | 0.0578 | 0.1113 | 0.4976 | 0.2714 | 0.4940 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
