Commit ·
80dfc23
1
Parent(s): 3ccf7b2
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- rouge
|
| 6 |
+
model-index:
|
| 7 |
+
- name: results3
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# results3
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1390
|
| 19 |
+
- Rouge1: 0.4949
|
| 20 |
+
- Rouge2: 0.4142
|
| 21 |
+
- Rougel: 0.4567
|
| 22 |
+
- Rougelsum: 0.4681
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 10
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
| 53 |
+
| No log | 1.0 | 221 | 0.1354 | 0.4748 | 0.3694 | 0.4220 | 0.4369 |
|
| 54 |
+
| No log | 2.0 | 442 | 0.1342 | 0.4809 | 0.3809 | 0.4309 | 0.4458 |
|
| 55 |
+
| 0.1539 | 3.0 | 663 | 0.1327 | 0.4837 | 0.3900 | 0.4410 | 0.4530 |
|
| 56 |
+
| 0.1539 | 4.0 | 884 | 0.1347 | 0.4813 | 0.3876 | 0.4374 | 0.4502 |
|
| 57 |
+
| 0.1013 | 5.0 | 1105 | 0.1344 | 0.4897 | 0.4001 | 0.4466 | 0.4579 |
|
| 58 |
+
| 0.1013 | 6.0 | 1326 | 0.1376 | 0.4901 | 0.4054 | 0.4520 | 0.4632 |
|
| 59 |
+
| 0.0691 | 7.0 | 1547 | 0.1355 | 0.4914 | 0.4068 | 0.4497 | 0.4622 |
|
| 60 |
+
| 0.0691 | 8.0 | 1768 | 0.1383 | 0.4959 | 0.4153 | 0.4562 | 0.4679 |
|
| 61 |
+
| 0.0691 | 9.0 | 1989 | 0.1389 | 0.4952 | 0.4147 | 0.4580 | 0.4690 |
|
| 62 |
+
| 0.0533 | 10.0 | 2210 | 0.1390 | 0.4949 | 0.4142 | 0.4567 | 0.4681 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.31.0
|
| 68 |
+
- Pytorch 2.0.1+cu118
|
| 69 |
+
- Datasets 2.14.4
|
| 70 |
+
- Tokenizers 0.13.3
|