Commit
·
e9e8adc
1
Parent(s):
a58555a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: t5-efficient-base-finetuned-1.2
|
| 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 |
+
# t5-efficient-base-finetuned-1.2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/t5-efficient-base](https://huggingface.co/google/t5-efficient-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5294
|
| 21 |
+
- Rouge1: 62.691
|
| 22 |
+
- Rouge2: 55.9731
|
| 23 |
+
- Rougel: 60.9097
|
| 24 |
+
- Rougelsum: 61.4393
|
| 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: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 4662
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 16
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 55 |
+
| 2.2424 | 1.0 | 1217 | 1.7042 | 34.2215 | 24.2754 | 31.7289 | 32.4237 |
|
| 56 |
+
| 1.7716 | 2.0 | 2434 | 1.6184 | 43.4774 | 34.0476 | 41.3691 | 41.9132 |
|
| 57 |
+
| 1.6324 | 3.0 | 3651 | 1.5811 | 49.1441 | 40.7935 | 47.0077 | 47.6388 |
|
| 58 |
+
| 1.5226 | 4.0 | 4868 | 1.5243 | 54.4769 | 46.3387 | 52.3289 | 52.9555 |
|
| 59 |
+
| 1.4121 | 5.0 | 6085 | 1.5040 | 56.8792 | 49.1963 | 54.7327 | 55.2805 |
|
| 60 |
+
| 1.331 | 6.0 | 7302 | 1.4930 | 58.6896 | 51.1683 | 56.7096 | 57.3605 |
|
| 61 |
+
| 1.2677 | 7.0 | 8519 | 1.4785 | 59.9285 | 52.4631 | 57.8575 | 58.4203 |
|
| 62 |
+
| 1.2175 | 8.0 | 9736 | 1.4839 | 60.0299 | 52.8806 | 58.0099 | 58.6348 |
|
| 63 |
+
| 1.1782 | 9.0 | 10953 | 1.4908 | 61.247 | 54.0887 | 59.2175 | 59.7658 |
|
| 64 |
+
| 1.1442 | 10.0 | 12170 | 1.4882 | 61.9895 | 54.9455 | 60.0728 | 60.5786 |
|
| 65 |
+
| 1.1118 | 11.0 | 13387 | 1.5061 | 62.1077 | 55.1276 | 60.2218 | 60.7475 |
|
| 66 |
+
| 1.081 | 12.0 | 14604 | 1.5078 | 61.6083 | 54.6805 | 59.7912 | 60.2489 |
|
| 67 |
+
| 1.0668 | 13.0 | 15821 | 1.5200 | 62.3075 | 55.5201 | 60.5192 | 60.9557 |
|
| 68 |
+
| 1.0488 | 14.0 | 17038 | 1.5344 | 62.5144 | 55.6332 | 60.6845 | 61.1715 |
|
| 69 |
+
| 1.0324 | 15.0 | 18255 | 1.5313 | 62.7697 | 56.0313 | 60.9298 | 61.4739 |
|
| 70 |
+
| 1.0302 | 16.0 | 19472 | 1.5294 | 62.691 | 55.9731 | 60.9097 | 61.4393 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0
|
| 76 |
+
- Pytorch 1.10.2+cu102
|
| 77 |
+
- Datasets 1.18.3
|
| 78 |
+
- Tokenizers 0.11.6
|