update model card README.md
Browse files
README.md
CHANGED
@@ -4,9 +4,24 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- billsum
|
|
|
|
|
7 |
model-index:
|
8 |
- name: my_awesome_billsum_model
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,6 +30,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# my_awesome_billsum_model
|
16 |
|
17 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -43,6 +65,16 @@ The following hyperparameters were used during training:
|
|
43 |
- num_epochs: 4
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
### Framework versions
|
47 |
|
48 |
- Transformers 4.29.2
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- billsum
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
model-index:
|
10 |
- name: my_awesome_billsum_model
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: billsum
|
17 |
+
type: billsum
|
18 |
+
config: default
|
19 |
+
split: ca_test
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Rouge1
|
23 |
+
type: rouge
|
24 |
+
value: 0.1451
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
# my_awesome_billsum_model
|
31 |
|
32 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 2.5383
|
35 |
+
- Rouge1: 0.1451
|
36 |
+
- Rouge2: 0.0521
|
37 |
+
- Rougel: 0.1168
|
38 |
+
- Rougelsum: 0.1168
|
39 |
+
- Gen Len: 19.0
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
65 |
- num_epochs: 4
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
72 |
+
| No log | 1.0 | 62 | 2.8314 | 0.1277 | 0.0385 | 0.1067 | 0.1068 | 19.0 |
|
73 |
+
| No log | 2.0 | 124 | 2.6230 | 0.136 | 0.0457 | 0.1112 | 0.111 | 19.0 |
|
74 |
+
| No log | 3.0 | 186 | 2.5558 | 0.1439 | 0.0522 | 0.1163 | 0.1161 | 19.0 |
|
75 |
+
| No log | 4.0 | 248 | 2.5383 | 0.1451 | 0.0521 | 0.1168 | 0.1168 | 19.0 |
|
76 |
+
|
77 |
+
|
78 |
### Framework versions
|
79 |
|
80 |
- Transformers 4.29.2
|