update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- mlsum
|
| 8 |
+
metrics:
|
| 9 |
+
- rouge
|
| 10 |
+
model-index:
|
| 11 |
+
- name: mt5-small-mlsum_training_sample
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Sequence-to-sequence Language Modeling
|
| 15 |
+
type: text2text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: mlsum
|
| 18 |
+
type: mlsum
|
| 19 |
+
config: de
|
| 20 |
+
split: train
|
| 21 |
+
args: de
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Rouge1
|
| 24 |
+
type: rouge
|
| 25 |
+
value: 28.2078
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# mt5-small-mlsum_training_sample
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the mlsum dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.9727
|
| 36 |
+
- Rouge1: 28.2078
|
| 37 |
+
- Rouge2: 19.0712
|
| 38 |
+
- Rougel: 26.2267
|
| 39 |
+
- Rougelsum: 26.9462
|
| 40 |
+
|
| 41 |
+
## Model description
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training and evaluation data
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Training procedure
|
| 54 |
+
|
| 55 |
+
### Training hyperparameters
|
| 56 |
+
|
| 57 |
+
The following hyperparameters were used during training:
|
| 58 |
+
- learning_rate: 0.001
|
| 59 |
+
- train_batch_size: 8
|
| 60 |
+
- eval_batch_size: 8
|
| 61 |
+
- seed: 42
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- num_epochs: 8
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 70 |
+
| 1.3193 | 1.0 | 6875 | 2.1352 | 25.8941 | 17.4672 | 24.2858 | 24.924 |
|
| 71 |
+
| 1.2413 | 2.0 | 13750 | 2.0528 | 26.6221 | 18.1166 | 24.8233 | 25.5111 |
|
| 72 |
+
| 1.1844 | 3.0 | 20625 | 1.9783 | 27.0518 | 18.3457 | 25.2288 | 25.8919 |
|
| 73 |
+
| 1.0403 | 4.0 | 27500 | 1.9487 | 27.8154 | 18.9701 | 25.9435 | 26.6578 |
|
| 74 |
+
| 0.9582 | 5.0 | 34375 | 1.9374 | 27.6863 | 18.7723 | 25.7667 | 26.4694 |
|
| 75 |
+
| 0.8992 | 6.0 | 41250 | 1.9353 | 27.8959 | 18.919 | 26.0434 | 26.7262 |
|
| 76 |
+
| 0.8109 | 7.0 | 48125 | 1.9492 | 28.0644 | 18.8873 | 26.0628 | 26.757 |
|
| 77 |
+
| 0.7705 | 8.0 | 55000 | 1.9727 | 28.2078 | 19.0712 | 26.2267 | 26.9462 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.22.1
|
| 83 |
+
- Pytorch 1.12.1+cu113
|
| 84 |
+
- Datasets 2.4.0
|
| 85 |
+
- Tokenizers 0.12.1
|