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: t5-small-paraphrasing-mlm-med-mask-filling-cm0
|
| 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 |
+
# t5-small-paraphrasing-mlm-med-mask-filling-cm0
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [gayanin/t5-small-paraphrase-pubmed](https://huggingface.co/gayanin/t5-small-paraphrase-pubmed) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.6697
|
| 18 |
+
- Rouge2 Precision: 0.6929
|
| 19 |
+
- Rouge2 Recall: 0.4742
|
| 20 |
+
- Rouge2 Fmeasure: 0.5443
|
| 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: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 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 |
+
| 0.9213 | 1.0 | 13915 | 0.8075 | 0.6708 | 0.4603 | 0.5281 |
|
| 53 |
+
| 0.8573 | 2.0 | 27830 | 0.7534 | 0.6802 | 0.4671 | 0.5356 |
|
| 54 |
+
| 0.8127 | 3.0 | 41745 | 0.7254 | 0.684 | 0.468 | 0.5373 |
|
| 55 |
+
| 0.7809 | 4.0 | 55660 | 0.7071 | 0.6867 | 0.4702 | 0.5397 |
|
| 56 |
+
| 0.7651 | 5.0 | 69575 | 0.6939 | 0.6886 | 0.4711 | 0.5409 |
|
| 57 |
+
| 0.7598 | 6.0 | 83490 | 0.6849 | 0.6904 | 0.4721 | 0.5422 |
|
| 58 |
+
| 0.7429 | 7.0 | 97405 | 0.6778 | 0.6917 | 0.4725 | 0.5427 |
|
| 59 |
+
| 0.7438 | 8.0 | 111320 | 0.6731 | 0.6917 | 0.4723 | 0.5426 |
|
| 60 |
+
| 0.743 | 9.0 | 125235 | 0.6707 | 0.6935 | 0.4748 | 0.545 |
|
| 61 |
+
| 0.7349 | 10.0 | 139150 | 0.6697 | 0.6929 | 0.4742 | 0.5443 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.21.1
|
| 67 |
+
- Pytorch 1.12.1+cu113
|
| 68 |
+
- Datasets 2.4.0
|
| 69 |
+
- Tokenizers 0.12.1
|