Commit
·
a59a081
1
Parent(s):
9c9a6bd
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: t5-base-devices-sum-ver1
|
| 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 |
+
# t5-base-devices-sum-ver1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0935
|
| 20 |
+
- Rouge1: 97.2294
|
| 21 |
+
- Rouge2: 80.1323
|
| 22 |
+
- Rougel: 97.245
|
| 23 |
+
- Rougelsum: 97.2763
|
| 24 |
+
- Gen Len: 4.9507
|
| 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: 2e-05
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| No log | 1.0 | 186 | 0.2461 | 91.9436 | 71.232 | 91.9417 | 91.9585 | 4.6644 |
|
| 57 |
+
| No log | 2.0 | 372 | 0.1580 | 94.5247 | 76.1321 | 94.5044 | 94.5382 | 4.8953 |
|
| 58 |
+
| 0.488 | 3.0 | 558 | 0.1239 | 95.8673 | 78.1183 | 95.8862 | 95.8919 | 4.9102 |
|
| 59 |
+
| 0.488 | 4.0 | 744 | 0.1100 | 96.5746 | 78.9878 | 96.5848 | 96.5831 | 4.9102 |
|
| 60 |
+
| 0.488 | 5.0 | 930 | 0.1008 | 96.9074 | 79.5536 | 96.9143 | 96.9317 | 4.9291 |
|
| 61 |
+
| 0.1303 | 6.0 | 1116 | 0.0974 | 96.9274 | 79.6953 | 96.933 | 96.9473 | 4.9291 |
|
| 62 |
+
| 0.1303 | 7.0 | 1302 | 0.0969 | 96.8041 | 79.5073 | 96.817 | 96.8266 | 4.9271 |
|
| 63 |
+
| 0.1303 | 8.0 | 1488 | 0.0945 | 97.1496 | 79.9757 | 97.1529 | 97.1779 | 4.9534 |
|
| 64 |
+
| 0.089 | 9.0 | 1674 | 0.0944 | 97.253 | 80.1236 | 97.2619 | 97.2899 | 4.9595 |
|
| 65 |
+
| 0.089 | 10.0 | 1860 | 0.0935 | 97.2294 | 80.1323 | 97.245 | 97.2763 | 4.9507 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.18.0
|
| 71 |
+
- Pytorch 1.10.0+cu111
|
| 72 |
+
- Datasets 2.0.0
|
| 73 |
+
- Tokenizers 0.11.6
|