debbiesoon
commited on
Commit
•
74d40ee
1
Parent(s):
b41c68d
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: summarise_v2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# summarise_v2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.3235
|
18 |
+
- Rouge2 Precision: 0.018
|
19 |
+
- Rouge2 Recall: 0.0916
|
20 |
+
- Rouge2 Fmeasure: 0.0292
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 2
|
41 |
+
- eval_batch_size: 2
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 1
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
52 |
+
| 3.1721 | 0.08 | 10 | 2.7742 | 0.0107 | 0.0671 | 0.0178 |
|
53 |
+
| 3.0802 | 0.16 | 20 | 2.7914 | 0.0111 | 0.0878 | 0.019 |
|
54 |
+
| 3.0795 | 0.24 | 30 | 2.6954 | 0.0094 | 0.076 | 0.0157 |
|
55 |
+
| 2.5806 | 0.32 | 40 | 2.6587 | 0.0028 | 0.0271 | 0.0046 |
|
56 |
+
| 2.6553 | 0.4 | 50 | 2.5958 | 0.0084 | 0.0566 | 0.0143 |
|
57 |
+
| 2.689 | 0.48 | 60 | 2.4857 | 0.0089 | 0.0733 | 0.015 |
|
58 |
+
| 2.6642 | 0.56 | 70 | 2.4205 | 0.0069 | 0.0478 | 0.0116 |
|
59 |
+
| 2.3768 | 0.64 | 80 | 2.3754 | 0.0127 | 0.0795 | 0.0215 |
|
60 |
+
| 2.1949 | 0.72 | 90 | 2.3752 | 0.0155 | 0.1013 | 0.0258 |
|
61 |
+
| 2.3257 | 0.8 | 100 | 2.3509 | 0.0155 | 0.1011 | 0.0261 |
|
62 |
+
| 2.4053 | 0.88 | 110 | 2.3261 | 0.015 | 0.0901 | 0.0246 |
|
63 |
+
| 2.9896 | 0.96 | 120 | 2.3235 | 0.018 | 0.0916 | 0.0292 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.21.3
|
69 |
+
- Pytorch 1.12.1+cu113
|
70 |
+
- Datasets 1.2.1
|
71 |
+
- Tokenizers 0.12.1
|