Commit
·
46c09eb
1
Parent(s):
98d3ec4
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-small-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-small-devices-sum-ver1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2335
|
| 20 |
+
- Rouge1: 93.7171
|
| 21 |
+
- Rouge2: 73.3058
|
| 22 |
+
- Rougel: 93.7211
|
| 23 |
+
- Rougelsum: 93.689
|
| 24 |
+
- Gen Len: 4.7246
|
| 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 | 185 | 0.6517 | 83.2503 | 55.7516 | 83.254 | 83.2722 | 4.4729 |
|
| 57 |
+
| No log | 2.0 | 370 | 0.4239 | 89.2246 | 65.7477 | 89.2223 | 89.2288 | 4.5575 |
|
| 58 |
+
| 1.0224 | 3.0 | 555 | 0.3459 | 91.0524 | 68.4783 | 91.0222 | 91.0312 | 4.6685 |
|
| 59 |
+
| 1.0224 | 4.0 | 740 | 0.3023 | 91.9741 | 70.1066 | 91.9886 | 91.9525 | 4.6549 |
|
| 60 |
+
| 1.0224 | 5.0 | 925 | 0.2797 | 92.667 | 71.3468 | 92.6706 | 92.6611 | 4.6969 |
|
| 61 |
+
| 0.3678 | 6.0 | 1110 | 0.2616 | 93.229 | 72.2805 | 93.222 | 93.1935 | 4.7179 |
|
| 62 |
+
| 0.3678 | 7.0 | 1295 | 0.2469 | 93.362 | 72.6985 | 93.3651 | 93.3294 | 4.7111 |
|
| 63 |
+
| 0.3678 | 8.0 | 1480 | 0.2401 | 93.5689 | 73.009 | 93.582 | 93.5377 | 4.7192 |
|
| 64 |
+
| 0.2902 | 9.0 | 1665 | 0.2350 | 93.7013 | 73.2685 | 93.7256 | 93.684 | 4.724 |
|
| 65 |
+
| 0.2902 | 10.0 | 1850 | 0.2335 | 93.7171 | 73.3058 | 93.7211 | 93.689 | 4.7246 |
|
| 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
|