|
--- |
|
license: apache-2.0 |
|
base_model: lidiya/bart-large-xsum-samsum |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: cnn_xsum_samsum_model |
|
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. --> |
|
|
|
# cnn_xsum_samsum_model |
|
|
|
This model is a fine-tuned version of [lidiya/bart-large-xsum-samsum](https://huggingface.co/lidiya/bart-large-xsum-samsum) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6585 |
|
- Rouge1: 0.4194 |
|
- Rouge2: 0.1959 |
|
- Rougel: 0.2948 |
|
- Rougelsum: 0.3902 |
|
- Gen Len: 60.8916 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 1.6501 | 1.0 | 836 | 1.6017 | 0.4143 | 0.194 | 0.2912 | 0.3845 | 60.7718 | |
|
| 1.3162 | 2.0 | 1672 | 1.5954 | 0.4113 | 0.1908 | 0.2891 | 0.3819 | 61.3206 | |
|
| 1.1452 | 3.0 | 2508 | 1.5853 | 0.4196 | 0.1964 | 0.2945 | 0.3899 | 60.928 | |
|
| 1.012 | 4.0 | 3344 | 1.6293 | 0.4201 | 0.1967 | 0.2952 | 0.3911 | 60.7965 | |
|
| 0.9368 | 5.0 | 4180 | 1.6585 | 0.4194 | 0.1959 | 0.2948 | 0.3902 | 60.8916 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
