Commit
·
d2408c2
1
Parent(s):
543d40d
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-ver2
|
| 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-ver2
|
| 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: 0.1919
|
| 20 |
+
- Rouge1: 95.2959
|
| 21 |
+
- Rouge2: 72.5788
|
| 22 |
+
- Rougel: 95.292
|
| 23 |
+
- Rougelsum: 95.3437
|
| 24 |
+
- Gen Len: 4.5992
|
| 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 | 91 | 0.4308 | 87.5009 | 61.4165 | 87.6082 | 87.6628 | 4.3897 |
|
| 57 |
+
| No log | 2.0 | 182 | 0.2945 | 91.7111 | 66.9023 | 91.706 | 91.7348 | 4.4965 |
|
| 58 |
+
| No log | 3.0 | 273 | 0.2515 | 93.0416 | 68.8046 | 93.063 | 93.0907 | 4.516 |
|
| 59 |
+
| No log | 4.0 | 364 | 0.2259 | 94.2097 | 70.862 | 94.2438 | 94.2767 | 4.6283 |
|
| 60 |
+
| No log | 5.0 | 455 | 0.2148 | 94.7732 | 71.4693 | 94.78 | 94.8274 | 4.5936 |
|
| 61 |
+
| 0.4603 | 6.0 | 546 | 0.2030 | 95.0207 | 71.7789 | 95.0212 | 95.0887 | 4.5798 |
|
| 62 |
+
| 0.4603 | 7.0 | 637 | 0.1964 | 95.1482 | 72.3333 | 95.1651 | 95.202 | 4.6227 |
|
| 63 |
+
| 0.4603 | 8.0 | 728 | 0.1929 | 95.3279 | 72.551 | 95.3459 | 95.3972 | 4.5825 |
|
| 64 |
+
| 0.4603 | 9.0 | 819 | 0.1935 | 95.2413 | 72.5801 | 95.2372 | 95.3121 | 4.5992 |
|
| 65 |
+
| 0.4603 | 10.0 | 910 | 0.1919 | 95.2959 | 72.5788 | 95.292 | 95.3437 | 4.5992 |
|
| 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
|