Commit
•
4f19c59
1
Parent(s):
e01ab28
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- rouge
|
7 |
+
model-index:
|
8 |
+
- name: bart-large-cnn-finetuned-roundup-8
|
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-large-cnn-finetuned-roundup-8
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.4519
|
20 |
+
- Rouge1: 49.5671
|
21 |
+
- Rouge2: 27.0118
|
22 |
+
- Rougel: 30.8538
|
23 |
+
- Rougelsum: 45.5503
|
24 |
+
- Gen Len: 141.75
|
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: 2
|
45 |
+
- eval_batch_size: 2
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 8
|
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 | 132 | 1.3159 | 48.5275 | 28.0817 | 30.6646 | 45.5024 | 142.0 |
|
57 |
+
| No log | 2.0 | 264 | 1.2377 | 47.0791 | 27.4386 | 28.9458 | 44.1536 | 142.0 |
|
58 |
+
| No log | 3.0 | 396 | 1.2474 | 49.3567 | 29.5904 | 30.8029 | 46.6083 | 142.0 |
|
59 |
+
| 0.9623 | 4.0 | 528 | 1.2914 | 47.8795 | 27.0611 | 29.8538 | 44.4494 | 142.0 |
|
60 |
+
| 0.9623 | 5.0 | 660 | 1.2982 | 49.9921 | 28.4839 | 31.5688 | 46.9734 | 142.0 |
|
61 |
+
| 0.9623 | 6.0 | 792 | 1.3521 | 46.7269 | 25.8672 | 29.7325 | 43.8279 | 142.0 |
|
62 |
+
| 0.9623 | 7.0 | 924 | 1.4102 | 47.4995 | 26.0066 | 29.4342 | 44.1102 | 141.8 |
|
63 |
+
| 0.3734 | 8.0 | 1056 | 1.4519 | 49.5671 | 27.0118 | 30.8538 | 45.5503 | 141.75 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.18.0
|
69 |
+
- Pytorch 1.11.0+cu113
|
70 |
+
- Datasets 2.1.0
|
71 |
+
- Tokenizers 0.12.1
|