update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt5-small-wikinewssum-test
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# mt5-small-wikinewssum-test
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.9354
|
| 21 |
+
- Rouge1: 6.8433
|
| 22 |
+
- Rouge2: 2.5498
|
| 23 |
+
- Rougel: 5.6114
|
| 24 |
+
- Rougelsum: 6.353
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 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: 5.6e-05
|
| 44 |
+
- train_batch_size: 12
|
| 45 |
+
- eval_batch_size: 12
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 8
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
| 55 |
+
| No log | 1.0 | 661 | 3.2810 | 6.4161 | 2.403 | 5.3674 | 6.0329 |
|
| 56 |
+
| No log | 2.0 | 1322 | 3.1515 | 6.9291 | 2.6826 | 5.6839 | 6.4359 |
|
| 57 |
+
| No log | 3.0 | 1983 | 3.0565 | 6.7939 | 2.6113 | 5.6133 | 6.3126 |
|
| 58 |
+
| No log | 4.0 | 2644 | 2.9815 | 6.0279 | 2.1637 | 4.9892 | 5.5962 |
|
| 59 |
+
| No log | 5.0 | 3305 | 2.9645 | 6.3926 | 2.339 | 5.2716 | 5.9443 |
|
| 60 |
+
| 3.9937 | 6.0 | 3966 | 2.9476 | 6.4739 | 2.3615 | 5.3473 | 6.0089 |
|
| 61 |
+
| 3.9937 | 7.0 | 4627 | 2.9405 | 6.615 | 2.4309 | 5.4493 | 6.1445 |
|
| 62 |
+
| 3.9937 | 8.0 | 5288 | 2.9354 | 6.8433 | 2.5498 | 5.6114 | 6.353 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.13.0
|
| 68 |
+
- Pytorch 1.10.1
|
| 69 |
+
- Datasets 1.16.1
|
| 70 |
+
- Tokenizers 0.10.3
|