Model save
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -50,31 +50,31 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 2.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7340
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 2.9331 | 0.4 | 10 | 2.3499 |
|
54 |
+
| 1.8204 | 0.8 | 20 | 1.3074 |
|
55 |
+
| 1.0645 | 1.2 | 30 | 0.9558 |
|
56 |
+
| 0.9181 | 1.6 | 40 | 0.8424 |
|
57 |
+
| 0.8628 | 2.0 | 50 | 0.7672 |
|
58 |
+
| 0.713 | 2.4 | 60 | 0.7212 |
|
59 |
+
| 0.7126 | 2.8 | 70 | 0.6701 |
|
60 |
+
| 0.594 | 3.2 | 80 | 0.6538 |
|
61 |
+
| 0.5837 | 3.6 | 90 | 0.6244 |
|
62 |
+
| 0.5894 | 4.0 | 100 | 0.5972 |
|
63 |
+
| 0.4848 | 4.4 | 110 | 0.6270 |
|
64 |
+
| 0.4968 | 4.8 | 120 | 0.5959 |
|
65 |
+
| 0.4858 | 5.2 | 130 | 0.6219 |
|
66 |
+
| 0.4386 | 5.6 | 140 | 0.6180 |
|
67 |
+
| 0.4708 | 6.0 | 150 | 0.6219 |
|
68 |
+
| 0.4155 | 6.4 | 160 | 0.6828 |
|
69 |
+
| 0.4172 | 6.8 | 170 | 0.6184 |
|
70 |
+
| 0.3948 | 7.2 | 180 | 0.6742 |
|
71 |
+
| 0.3676 | 7.6 | 190 | 0.6573 |
|
72 |
+
| 0.3801 | 8.0 | 200 | 0.6624 |
|
73 |
+
| 0.3527 | 8.4 | 210 | 0.7313 |
|
74 |
+
| 0.3507 | 8.8 | 220 | 0.6588 |
|
75 |
+
| 0.3362 | 9.2 | 230 | 0.7390 |
|
76 |
+
| 0.3228 | 9.6 | 240 | 0.7091 |
|
77 |
+
| 0.3306 | 10.0 | 250 | 0.7340 |
|
78 |
|
79 |
|
80 |
### Framework versions
|