dariuslimzh
commited on
Training completed
Browse files
README.md
CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Rouge1: 0.
|
23 |
- Rouge2: 0.0
|
24 |
-
- Rougel: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
|
57 |
-
| No log | 1.0 | 231 | 0.
|
58 |
-
| No log | 2.0 | 462 |
|
59 |
-
| 2.2704 | 3.0 | 693 | 11.
|
60 |
-
| 2.2704 | 4.0 | 924 |
|
61 |
-
| 26.3063 | 5.0 | 1155 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 14.5862
|
22 |
+
- Rouge1: 0.0825
|
23 |
- Rouge2: 0.0
|
24 |
+
- Rougel: 0.0663
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
|
57 |
+
| No log | 1.0 | 231 | 0.1431 | 0.4566 | 0.1505 | 0.4042 |
|
58 |
+
| No log | 2.0 | 462 | 7.6729 | 0.2900 | 0.0927 | 0.2736 |
|
59 |
+
| 2.2704 | 3.0 | 693 | 11.7300 | 0.0722 | 0.0 | 0.0629 |
|
60 |
+
| 2.2704 | 4.0 | 924 | 14.5258 | 0.0390 | 0.0 | 0.0314 |
|
61 |
+
| 26.3063 | 5.0 | 1155 | 14.5862 | 0.0825 | 0.0 | 0.0663 |
|
62 |
|
63 |
|
64 |
### Framework versions
|