update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: bart-mlm-pubmed-15
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# bart-mlm-pubmed-15
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4822
|
| 18 |
+
- Rouge2 Precision: 0.7578
|
| 19 |
+
- Rouge2 Recall: 0.5933
|
| 20 |
+
- Rouge2 Fmeasure: 0.6511
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
| 52 |
+
| 0.7006 | 1.0 | 663 | 0.5062 | 0.7492 | 0.5855 | 0.6434 |
|
| 53 |
+
| 0.5709 | 2.0 | 1326 | 0.4811 | 0.7487 | 0.5879 | 0.6447 |
|
| 54 |
+
| 0.5011 | 3.0 | 1989 | 0.4734 | 0.7541 | 0.5906 | 0.6483 |
|
| 55 |
+
| 0.4164 | 4.0 | 2652 | 0.4705 | 0.7515 | 0.5876 | 0.6452 |
|
| 56 |
+
| 0.3888 | 5.0 | 3315 | 0.4703 | 0.7555 | 0.5946 | 0.6515 |
|
| 57 |
+
| 0.3655 | 6.0 | 3978 | 0.4725 | 0.7572 | 0.5943 | 0.6516 |
|
| 58 |
+
| 0.319 | 7.0 | 4641 | 0.4733 | 0.7557 | 0.5911 | 0.6491 |
|
| 59 |
+
| 0.3089 | 8.0 | 5304 | 0.4792 | 0.7577 | 0.5936 | 0.6513 |
|
| 60 |
+
| 0.2907 | 9.0 | 5967 | 0.4799 | 0.7577 | 0.5931 | 0.6509 |
|
| 61 |
+
| 0.275 | 10.0 | 6630 | 0.4822 | 0.7578 | 0.5933 | 0.6511 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.12.5
|
| 67 |
+
- Pytorch 1.10.0+cu111
|
| 68 |
+
- Datasets 1.15.1
|
| 69 |
+
- Tokenizers 0.10.3
|