|
|
--- |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
base_model: allenai/led-base-16384 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
- bleu |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: LoRA_LED_all_aspects |
|
|
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. --> |
|
|
|
|
|
# LoRA_LED_all_aspects |
|
|
|
|
|
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.2585 |
|
|
- Rouge1: 0.2961 |
|
|
- Rouge2: 0.1042 |
|
|
- Rougel: 0.234 |
|
|
- Rougelsum: 0.2333 |
|
|
- Gen Len: 29.3933 |
|
|
- Bleu: 0.0577 |
|
|
- Precisions: 0.1023 |
|
|
- Brevity Penalty: 0.9031 |
|
|
- Length Ratio: 0.9075 |
|
|
- Translation Length: 3268.0 |
|
|
- Reference Length: 3601.0 |
|
|
- Precision: 0.8752 |
|
|
- Recall: 0.8737 |
|
|
- F1: 0.8744 |
|
|
- Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) |
|
|
|
|
|
## 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: 0.002 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.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: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:| |
|
|
| 5.0003 | 1.0 | 38 | 3.3632 | 0.2751 | 0.1031 | 0.2271 | 0.2265 | 26.0267 | 0.0601 | 0.113 | 0.7896 | 0.8089 | 2913.0 | 3601.0 | 0.8795 | 0.8705 | 0.8749 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) | |
|
|
| 3.4616 | 2.0 | 76 | 3.2445 | 0.3023 | 0.104 | 0.237 | 0.2372 | 30.3467 | 0.065 | 0.1086 | 0.9019 | 0.9064 | 3264.0 | 3601.0 | 0.872 | 0.874 | 0.8729 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) | |
|
|
| 3.1933 | 3.0 | 114 | 3.2125 | 0.282 | 0.0998 | 0.2276 | 0.2264 | 29.2733 | 0.0576 | 0.1018 | 0.8859 | 0.892 | 3212.0 | 3601.0 | 0.8732 | 0.8729 | 0.873 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) | |
|
|
| 3.0156 | 4.0 | 152 | 3.2279 | 0.2848 | 0.1012 | 0.2294 | 0.2287 | 28.92 | 0.0611 | 0.1059 | 0.8862 | 0.8923 | 3213.0 | 3601.0 | 0.8769 | 0.8742 | 0.8755 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) | |
|
|
| 2.874 | 5.0 | 190 | 3.2585 | 0.2961 | 0.1042 | 0.234 | 0.2333 | 29.3933 | 0.0577 | 0.1023 | 0.9031 | 0.9075 | 3268.0 | 3601.0 | 0.8752 | 0.8737 | 0.8744 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1) | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.15.2 |
|
|
- Transformers 4.53.1 |
|
|
- Pytorch 2.7.0+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
