|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: allenai/led-base-16384 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
- bleu |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: LED_sum_approach |
|
|
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. --> |
|
|
|
|
|
# LED_sum_approach |
|
|
|
|
|
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: 3.3340 |
|
|
- Rouge1: 0.4569 |
|
|
- Rouge2: 0.2272 |
|
|
- Rougel: 0.3918 |
|
|
- Rougelsum: 0.3927 |
|
|
- Gen Len: 20.82 |
|
|
- Bleu: 0.1112 |
|
|
- Precisions: 0.2401 |
|
|
- Brevity Penalty: 0.5852 |
|
|
- Length Ratio: 0.6511 |
|
|
- Translation Length: 795.0 |
|
|
- Reference Length: 1221.0 |
|
|
- Precision: 0.9098 |
|
|
- Recall: 0.8906 |
|
|
- F1: 0.9 |
|
|
- Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 16 |
|
|
- 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: 10 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:----------:|:---------------:|:------------:|:------------------:|:----------------:|:---------:|:------:|:------:|:---------------------------------------------------------:| |
|
|
| No log | 1.0 | 7 | 7.6476 | 0.348 | 0.1355 | 0.2757 | 0.274 | 21.0 | 0.0602 | 0.1436 | 0.6232 | 0.679 | 829.0 | 1221.0 | 0.8935 | 0.8759 | 0.8845 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 2.0 | 14 | 6.4676 | 0.4218 | 0.2049 | 0.3597 | 0.3592 | 20.94 | 0.1008 | 0.2063 | 0.6419 | 0.6929 | 846.0 | 1221.0 | 0.9027 | 0.8839 | 0.8932 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 3.0 | 21 | 5.0145 | 0.4189 | 0.2067 | 0.362 | 0.3612 | 20.5 | 0.0945 | 0.2152 | 0.5919 | 0.656 | 801.0 | 1221.0 | 0.9087 | 0.8846 | 0.8964 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 4.0 | 28 | 4.2719 | 0.44 | 0.2299 | 0.3791 | 0.3778 | 20.48 | 0.1052 | 0.2337 | 0.5852 | 0.6511 | 795.0 | 1221.0 | 0.9087 | 0.8882 | 0.8982 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 5.0 | 35 | 3.9222 | 0.4538 | 0.238 | 0.3919 | 0.3917 | 20.7 | 0.1062 | 0.2404 | 0.5795 | 0.647 | 790.0 | 1221.0 | 0.9126 | 0.891 | 0.9016 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 6.0 | 42 | 3.6730 | 0.4582 | 0.2266 | 0.3926 | 0.3922 | 20.82 | 0.1093 | 0.236 | 0.5908 | 0.6552 | 800.0 | 1221.0 | 0.9099 | 0.8895 | 0.8995 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 7.0 | 49 | 3.5177 | 0.4639 | 0.2385 | 0.4037 | 0.4033 | 20.76 | 0.117 | 0.2484 | 0.5863 | 0.6519 | 796.0 | 1221.0 | 0.9101 | 0.8901 | 0.8999 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 8.0 | 56 | 3.4234 | 0.4564 | 0.2345 | 0.398 | 0.3978 | 20.72 | 0.1148 | 0.247 | 0.5806 | 0.6478 | 791.0 | 1221.0 | 0.9094 | 0.8891 | 0.899 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 9.0 | 63 | 3.3645 | 0.4518 | 0.2273 | 0.3912 | 0.3913 | 20.82 | 0.1111 | 0.2376 | 0.5886 | 0.6536 | 798.0 | 1221.0 | 0.9087 | 0.8899 | 0.8991 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
| No log | 10.0 | 70 | 3.3340 | 0.4569 | 0.2272 | 0.3918 | 0.3927 | 20.82 | 0.1112 | 0.2401 | 0.5852 | 0.6511 | 795.0 | 1221.0 | 0.9098 | 0.8906 | 0.9 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.0 |
|
|
- Pytorch 2.7.0+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
