Upload model
Browse files- README.md +33 -6
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss:
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -43,9 +43,36 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
-
|
|
48 |
-
| 9.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 4.9458
|
19 |
+
- Validation Loss: 6.8594
|
20 |
+
- Epoch: 29
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 9.6934 | 9.6704 | 0 |
|
47 |
+
| 9.4105 | 9.4160 | 1 |
|
48 |
+
| 9.1023 | 9.1460 | 2 |
|
49 |
+
| 8.7843 | 8.8812 | 3 |
|
50 |
+
| 8.4798 | 8.6399 | 4 |
|
51 |
+
| 8.2009 | 8.4204 | 5 |
|
52 |
+
| 7.9445 | 8.2215 | 6 |
|
53 |
+
| 7.7117 | 8.0412 | 7 |
|
54 |
+
| 7.4965 | 7.8807 | 8 |
|
55 |
+
| 7.2929 | 7.7610 | 9 |
|
56 |
+
| 7.1028 | 7.6524 | 10 |
|
57 |
+
| 6.9102 | 7.5430 | 11 |
|
58 |
+
| 6.7196 | 7.4545 | 12 |
|
59 |
+
| 6.5149 | 7.3501 | 13 |
|
60 |
+
| 6.3265 | 7.2721 | 14 |
|
61 |
+
| 6.1167 | 7.1747 | 15 |
|
62 |
+
| 5.9178 | 7.0857 | 16 |
|
63 |
+
| 5.7101 | 7.0159 | 17 |
|
64 |
+
| 5.5075 | 6.9416 | 18 |
|
65 |
+
| 5.2990 | 6.8977 | 19 |
|
66 |
+
| 5.0966 | 6.8594 | 20 |
|
67 |
+
| 4.9436 | 6.8594 | 21 |
|
68 |
+
| 4.9450 | 6.8594 | 22 |
|
69 |
+
| 4.9446 | 6.8594 | 23 |
|
70 |
+
| 4.9422 | 6.8594 | 24 |
|
71 |
+
| 4.9412 | 6.8594 | 25 |
|
72 |
+
| 4.9436 | 6.8594 | 26 |
|
73 |
+
| 4.9455 | 6.8594 | 27 |
|
74 |
+
| 4.9467 | 6.8594 | 28 |
|
75 |
+
| 4.9458 | 6.8594 | 29 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503289936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2680a2f795f65aca6e1b0de4e597cda5f42377ea4419a5383355190155a274a3
|
3 |
size 503289936
|