nguyenkhoa2407
commited on
Commit
•
d5a12f3
1
Parent(s):
f9874b3
update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Rouge1
|
23 |
type: rouge
|
24 |
-
value:
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the filter_sort dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Rouge1:
|
36 |
- Rouge2: 0.0
|
37 |
-
- Rougel:
|
38 |
-
- Rougelsum:
|
39 |
-
- Gen Len:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -61,22 +61,32 @@ The following hyperparameters were used during training:
|
|
61 |
- seed: 42
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2
|
69 |
-
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Rouge1
|
23 |
type: rouge
|
24 |
+
value: 15.7351
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the filter_sort dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 2.3327
|
35 |
+
- Rouge1: 15.7351
|
36 |
- Rouge2: 0.0
|
37 |
+
- Rougel: 13.4803
|
38 |
+
- Rougelsum: 13.5134
|
39 |
+
- Gen Len: 12.6667
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
61 |
- seed: 42
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
+
- num_epochs: 20
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
70 |
+
| No log | 1.0 | 5 | 3.8161 | 14.754 | 0.0 | 12.6197 | 12.6426 | 10.5 |
|
71 |
+
| 4.8789 | 2.0 | 10 | 3.6423 | 14.754 | 0.0 | 12.6197 | 12.6426 | 10.5 |
|
72 |
+
| 4.8789 | 3.0 | 15 | 3.4687 | 14.754 | 0.0 | 12.6197 | 12.6426 | 10.5 |
|
73 |
+
| 4.5407 | 4.0 | 20 | 3.3086 | 14.754 | 0.0 | 12.6197 | 12.6426 | 10.5 |
|
74 |
+
| 4.5407 | 5.0 | 25 | 3.1726 | 14.754 | 0.0 | 12.6197 | 12.6426 | 10.5 |
|
75 |
+
| 4.2216 | 6.0 | 30 | 3.0464 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
76 |
+
| 4.2216 | 7.0 | 35 | 2.9326 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
77 |
+
| 4.0021 | 8.0 | 40 | 2.8305 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
78 |
+
| 4.0021 | 9.0 | 45 | 2.7386 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
79 |
+
| 3.7634 | 10.0 | 50 | 2.6588 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
80 |
+
| 3.7634 | 11.0 | 55 | 2.5916 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
81 |
+
| 3.6224 | 12.0 | 60 | 2.5358 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
82 |
+
| 3.6224 | 13.0 | 65 | 2.4895 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
83 |
+
| 3.496 | 14.0 | 70 | 2.4486 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
84 |
+
| 3.496 | 15.0 | 75 | 2.4140 | 15.7792 | 0.0 | 13.5134 | 13.5411 | 12.6667 |
|
85 |
+
| 3.4157 | 16.0 | 80 | 2.3857 | 15.7351 | 0.0 | 13.4803 | 13.5134 | 12.6667 |
|
86 |
+
| 3.4157 | 17.0 | 85 | 2.3622 | 15.7351 | 0.0 | 13.4803 | 13.5134 | 12.6667 |
|
87 |
+
| 3.3964 | 18.0 | 90 | 2.3455 | 15.7351 | 0.0 | 13.4803 | 13.5134 | 12.6667 |
|
88 |
+
| 3.3964 | 19.0 | 95 | 2.3361 | 15.7351 | 0.0 | 13.4803 | 13.5134 | 12.6667 |
|
89 |
+
| 3.3502 | 20.0 | 100 | 2.3327 | 15.7351 | 0.0 | 13.4803 | 13.5134 | 12.6667 |
|
90 |
|
91 |
|
92 |
### Framework versions
|