KellyShiiii
commited on
Commit
•
8820131
1
Parent(s):
dacdd64
update model card README.md
Browse files
README.md
CHANGED
@@ -16,12 +16,12 @@ model-index:
|
|
16 |
name: crd3
|
17 |
type: crd3
|
18 |
config: default
|
19 |
-
split: train[:
|
20 |
args: default
|
21 |
metrics:
|
22 |
- name: Rouge1
|
23 |
type: rouge
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the crd3 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Rouge1: 0.
|
36 |
-
- Rouge2: 0.
|
37 |
-
- Rougel: 0.
|
38 |
-
- Rougelsum: 0.
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -55,19 +55,20 @@ More information needed
|
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
- learning_rate: 2e-05
|
58 |
-
- train_batch_size:
|
59 |
-
- eval_batch_size:
|
60 |
- seed: 42
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
-
- num_epochs:
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
69 |
-
| No log | 1.0 |
|
70 |
-
|
|
|
|
71 |
|
72 |
|
73 |
### Framework versions
|
|
|
16 |
name: crd3
|
17 |
type: crd3
|
18 |
config: default
|
19 |
+
split: train[:500]
|
20 |
args: default
|
21 |
metrics:
|
22 |
- name: Rouge1
|
23 |
type: rouge
|
24 |
+
value: 0.16466172750612934
|
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 [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the crd3 dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 3.8082
|
35 |
+
- Rouge1: 0.1647
|
36 |
+
- Rouge2: 0.0348
|
37 |
+
- Rougel: 0.1376
|
38 |
+
- Rougelsum: 0.1488
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
- learning_rate: 2e-05
|
58 |
+
- train_batch_size: 2
|
59 |
+
- eval_batch_size: 2
|
60 |
- seed: 42
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
+
- num_epochs: 3
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
69 |
+
| No log | 1.0 | 250 | 2.9780 | 0.1772 | 0.0578 | 0.1547 | 0.1617 |
|
70 |
+
| 1.8204 | 2.0 | 500 | 3.3771 | 0.1685 | 0.0331 | 0.1404 | 0.1496 |
|
71 |
+
| 1.8204 | 3.0 | 750 | 3.8082 | 0.1647 | 0.0348 | 0.1376 | 0.1488 |
|
72 |
|
73 |
|
74 |
### Framework versions
|