metadata
language: en
license: apache-2.0
tags:
- summarization
datasets:
- cnn_dailymail
metrics:
- R1
- R2
- RL
model-index:
- name: echarlaix/bart-base-cnn-r2-18.7-d23-hybrid
results:
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail
type: cnn_dailymail
config: 3.0.0
split: test
metrics:
- name: ROUGE-1
type: rouge
value: 23.7908
verified: true
- name: ROUGE-2
type: rouge
value: 11.3439
verified: true
- name: ROUGE-L
type: rouge
value: 19.7608
verified: true
- name: ROUGE-LSUM
type: rouge
value: 22.3485
verified: true
- name: loss
type: loss
value: 2.0443272590637207
verified: true
- name: gen_len
type: gen_len
value: 19.9996
verified: true
facebook/bart-base model fine-tuned on CNN/DailyMail
This model was created using the nn_pruning python library: the linear layers contains 23% of the original weights.
The model contains 45% of the original weights overall (the embeddings account for a significant part of the model, and they are not pruned by this method).
Fine-Pruning details
This model was fine-tuned from the HuggingFace model. A side-effect of block pruning is that some of the attention heads are completely removed: 61 heads were removed on a total of 216 (28.2%).
Details of the CNN/DailyMail dataset
| Dataset | Split | # samples |
|---|---|---|
| CNN/DailyMail | train | 287K |
| CNN/DailyMail | eval | 13K |
Results
| Metric | # Value |
|---|---|
| Rouge 1 | 41.43 |
| Rouge 2 | 18.72 |
| Rouge L | 38.35 |