update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: bart-base-finetuned-kaggglenews-batch8-epochs10
|
| 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 |
+
# bart-base-finetuned-kaggglenews-batch8-epochs10
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.5763
|
| 20 |
+
- Rouge1: 28.693
|
| 21 |
+
- Rouge2: 16.666
|
| 22 |
+
- Rougel: 24.2361
|
| 23 |
+
- Rougelsum: 26.0289
|
| 24 |
+
- Gen Len: 20.0
|
| 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: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 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 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| No log | 1.0 | 495 | 1.6043 | 27.8611 | 15.8713 | 23.8365 | 25.378 | 20.0 |
|
| 56 |
+
| 1.9054 | 2.0 | 990 | 1.5613 | 28.2715 | 16.3724 | 24.3212 | 25.8499 | 20.0 |
|
| 57 |
+
| 1.651 | 3.0 | 1485 | 1.5394 | 28.6282 | 16.2976 | 24.2336 | 25.9434 | 20.0 |
|
| 58 |
+
| 1.4955 | 4.0 | 1980 | 1.5438 | 28.9266 | 16.7257 | 24.61 | 26.443 | 20.0 |
|
| 59 |
+
| 1.4034 | 5.0 | 2475 | 1.5449 | 28.2296 | 16.1292 | 23.9698 | 25.651 | 20.0 |
|
| 60 |
+
| 1.3077 | 6.0 | 2970 | 1.5642 | 28.4486 | 16.3833 | 24.1629 | 26.0013 | 20.0 |
|
| 61 |
+
| 1.2505 | 7.0 | 3465 | 1.5566 | 28.5469 | 16.5374 | 24.2966 | 25.962 | 20.0 |
|
| 62 |
+
| 1.2027 | 8.0 | 3960 | 1.5730 | 28.7278 | 16.6442 | 24.2531 | 26.1171 | 20.0 |
|
| 63 |
+
| 1.1571 | 9.0 | 4455 | 1.5690 | 28.7736 | 16.7491 | 24.3066 | 26.1439 | 20.0 |
|
| 64 |
+
| 1.1237 | 10.0 | 4950 | 1.5763 | 28.693 | 16.666 | 24.2361 | 26.0289 | 20.0 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.12.5
|
| 70 |
+
- Pytorch 1.10.0+cu102
|
| 71 |
+
- Datasets 1.16.1
|
| 72 |
+
- Tokenizers 0.10.3
|