domenicrosati
commited on
Commit
•
3605d93
1
Parent(s):
b4eaf9e
update model card README.md
Browse files
README.md
CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
-
- Rouge1: 0.
|
21 |
-
- Rouge2: 0.
|
22 |
-
- Rougel: 0.
|
23 |
-
- Rougelsum: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -50,6 +50,15 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.2428
|
20 |
+
- Rouge1: 0.4562
|
21 |
+
- Rouge2: 0.1529
|
22 |
+
- Rougel: 0.2402
|
23 |
+
- Rougelsum: 0.2401
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
55 |
+
| 2.4777 | 0.14 | 1000 | 2.3948 | 0.4284 | 0.1431 | 0.2336 | 0.2336 |
|
56 |
+
| 2.3863 | 0.27 | 2000 | 2.3211 | 0.4455 | 0.1496 | 0.2380 | 0.2379 |
|
57 |
+
| 2.3509 | 0.41 | 3000 | 2.2809 | 0.4521 | 0.1521 | 0.2406 | 0.2406 |
|
58 |
+
| 2.3063 | 0.55 | 4000 | 2.2428 | 0.4562 | 0.1529 | 0.2402 | 0.2401 |
|
59 |
+
| 2.2754 | 0.69 | 5000 | 2.2222 | 0.4491 | 0.1506 | 0.2393 | 0.2393 |
|
60 |
+
| 2.268 | 0.82 | 6000 | 2.2113 | 0.4499 | 0.1519 | 0.2406 | 0.2405 |
|
61 |
+
| 2.2594 | 0.96 | 7000 | 2.1892 | 0.4519 | 0.1515 | 0.2390 | 0.2391 |
|
62 |
|
63 |
|
64 |
### Framework versions
|