Commit
•
5969ae4
1
Parent(s):
b205fc2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- pub_med_summarization_dataset
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
model-index:
|
| 10 |
+
- name: bart-large-finetuned-pubmed
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Sequence-to-sequence Language Modeling
|
| 14 |
+
type: text2text-generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: pub_med_summarization_dataset
|
| 17 |
+
type: pub_med_summarization_dataset
|
| 18 |
+
args: document
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Rouge1
|
| 21 |
+
type: rouge
|
| 22 |
+
value: 10.946
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# bart-large-finetuned-pubmed
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the pub_med_summarization_dataset dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 1.8135
|
| 33 |
+
- Rouge1: 10.946
|
| 34 |
+
- Rouge2: 5.0933
|
| 35 |
+
- Rougel: 9.5608
|
| 36 |
+
- Rougelsum: 10.4259
|
| 37 |
+
- Gen Len: 19.0495
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 2e-05
|
| 57 |
+
- train_batch_size: 2
|
| 58 |
+
- eval_batch_size: 2
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- num_epochs: 5
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
|
| 69 |
+
| 2.0861 | 1.0 | 4000 | 1.8909 | 8.7344 | 3.6919 | 7.8804 | 8.3305 | 20.0 |
|
| 70 |
+
| 1.8996 | 2.0 | 8000 | 1.8261 | 10.2124 | 4.6212 | 8.9842 | 9.7417 | 17.632 |
|
| 71 |
+
| 1.7459 | 3.0 | 12000 | 1.8160 | 9.4933 | 4.4117 | 8.3977 | 9.0758 | 16.4775 |
|
| 72 |
+
| 1.6258 | 4.0 | 16000 | 1.8136 | 10.8248 | 5.0335 | 9.4286 | 10.3123 | 18.724 |
|
| 73 |
+
| 1.5214 | 5.0 | 20000 | 1.8135 | 10.946 | 5.0933 | 9.5608 | 10.4259 | 19.0495 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.16.2
|
| 79 |
+
- Pytorch 1.10.0+cu111
|
| 80 |
+
- Datasets 1.18.3
|
| 81 |
+
- Tokenizers 0.11.6
|