Commit ·
64d1d2f
1
Parent(s): a174d0f
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,61 +5,23 @@ tags:
|
|
| 5 |
metrics:
|
| 6 |
- rouge
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
# mt5-large_V8901_V89881_V17542
|
| 16 |
-
|
| 17 |
-
This model is a fine-tuned version of [emilstabil/mt5-large_V8901_V89881](https://huggingface.co/emilstabil/mt5-large_V8901_V89881) on the None dataset.
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.7588
|
| 20 |
-
- Rouge1: 27.8059
|
| 21 |
-
- Rouge2: 10.1962
|
| 22 |
-
- Rougel: 15.3479
|
| 23 |
-
- Rougelsum: 26.1829
|
| 24 |
-
- Gen Len: 540.9451
|
| 25 |
-
|
| 26 |
## Model description
|
| 27 |
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
## Intended uses & limitations
|
| 31 |
-
|
| 32 |
-
More information needed
|
| 33 |
-
|
| 34 |
-
## Training and evaluation data
|
| 35 |
-
|
| 36 |
-
More information needed
|
| 37 |
-
|
| 38 |
-
## Training procedure
|
| 39 |
-
|
| 40 |
-
### Training hyperparameters
|
| 41 |
-
|
| 42 |
-
The following hyperparameters were used during training:
|
| 43 |
-
- learning_rate: 1e-05
|
| 44 |
-
- train_batch_size: 2
|
| 45 |
-
- eval_batch_size: 2
|
| 46 |
-
- seed: 42
|
| 47 |
-
- gradient_accumulation_steps: 4
|
| 48 |
-
- total_train_batch_size: 8
|
| 49 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
-
- lr_scheduler_type: linear
|
| 51 |
-
- num_epochs: 11
|
| 52 |
-
|
| 53 |
-
### Training results
|
| 54 |
|
| 55 |
-
|
| 56 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
|
| 57 |
-
| 1.871 | 2.11 | 500 | 1.7570 | 27.3094 | 9.9205 | 15.0662 | 25.6006 | 544.1983 |
|
| 58 |
-
| 1.7982 | 4.21 | 1000 | 1.7661 | 27.6824 | 9.8242 | 15.2022 | 25.9032 | 537.4388 |
|
| 59 |
-
| 1.7311 | 6.32 | 1500 | 1.7713 | 27.3113 | 9.6774 | 14.9355 | 25.6303 | 539.827 |
|
| 60 |
-
| 1.7432 | 8.42 | 2000 | 1.7636 | 27.8775 | 10.0766 | 15.1629 | 26.1014 | 537.5359 |
|
| 61 |
-
| 1.7775 | 10.53 | 2500 | 1.7588 | 27.8059 | 10.1962 | 15.3479 | 26.1829 | 540.9451 |
|
| 62 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
### Framework versions
|
| 65 |
|
|
|
|
| 5 |
metrics:
|
| 6 |
- rouge
|
| 7 |
model-index:
|
| 8 |
+
- name: DaMedSumT5-large
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Model description
|
| 16 |
|
| 17 |
+
This repository contains a model for Danish abstractive summarisation of medicaltext.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of mt5-large on a danish medical dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
+
## Authors
|
| 22 |
+
Nicolaj Larsen
|
| 23 |
+
Mikkel Kildeberg
|
| 24 |
+
Emil Schledermann
|
| 25 |
|
| 26 |
### Framework versions
|
| 27 |
|