update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt5-finetuned-amazon-en-es
|
| 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-finetuned-amazon-en-es
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.0285
|
| 21 |
+
- Rouge1: 16.9728
|
| 22 |
+
- Rouge2: 8.2969
|
| 23 |
+
- Rougel: 16.8366
|
| 24 |
+
- Rougelsum: 16.851
|
| 25 |
+
- Gen Len: 10.1597
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5.6e-05
|
| 45 |
+
- train_batch_size: 8
|
| 46 |
+
- eval_batch_size: 8
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 8
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| 7.1016 | 1.0 | 1209 | 3.3069 | 13.9858 | 5.8437 | 13.6053 | 13.5125 | 8.3782 |
|
| 57 |
+
| 3.898 | 2.0 | 2418 | 3.1567 | 16.6706 | 8.6393 | 16.2882 | 16.2249 | 9.7521 |
|
| 58 |
+
| 3.5915 | 3.0 | 3627 | 3.0928 | 17.111 | 8.3921 | 16.9139 | 16.7805 | 10.3445 |
|
| 59 |
+
| 3.4174 | 4.0 | 4836 | 3.0482 | 16.9728 | 8.3066 | 16.8868 | 16.8485 | 10.3151 |
|
| 60 |
+
| 3.3258 | 5.0 | 6045 | 3.0375 | 16.5972 | 8.2621 | 16.3524 | 16.3093 | 10.0672 |
|
| 61 |
+
| 3.2427 | 6.0 | 7254 | 3.0232 | 17.3009 | 8.6087 | 17.0782 | 17.0105 | 10.0756 |
|
| 62 |
+
| 3.2009 | 7.0 | 8463 | 3.0302 | 16.9284 | 8.6569 | 16.7885 | 16.7784 | 10.2143 |
|
| 63 |
+
| 3.1838 | 8.0 | 9672 | 3.0285 | 16.9728 | 8.2969 | 16.8366 | 16.851 | 10.1597 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.12.3
|
| 69 |
+
- Pytorch 1.9.1+cu111
|
| 70 |
+
- Datasets 1.15.1
|
| 71 |
+
- Tokenizers 0.10.3
|