Update README.md
Browse files
README.md
CHANGED
@@ -21,8 +21,8 @@ We further project E-Class to have a ratio of 264, and F-Class to have a ratio o
|
|
21 |
|
22 |
| Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss |
|
23 |
| --- | --- | --- | --- | --- | --- | --- |
|
24 |
-
| GerbilLab/Gerbil-A-3.3m | 3.3m | A-Class | 20 | 60M | 65.5k | 6.
|
25 |
-
| GerbilLab/Gerbil-B-3.3m | 3.3m | B-Class | 42 | 126M | 65.5k |
|
26 |
| --- | --- | --- | --- | --- | --- | --- |
|
27 |
| GerbilLab/Gerbil-A-6.7m | 6.7m | A-Class | 20 | 134M | 131k | 6.074100 |
|
28 |
| GerbilLab/Gerbil-B-6.7m | 6.7m | B-Class | 42 | 281M | 131k | 5.513200 |
|
|
|
21 |
|
22 |
| Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss |
|
23 |
| --- | --- | --- | --- | --- | --- | --- |
|
24 |
+
| GerbilLab/Gerbil-A-3.3m | 3.3m | A-Class | 20 | 60M | 65.5k | 6.6644 |
|
25 |
+
| GerbilLab/Gerbil-B-3.3m | 3.3m | B-Class | 42 | 126M | 65.5k | 6.0822 |
|
26 |
| --- | --- | --- | --- | --- | --- | --- |
|
27 |
| GerbilLab/Gerbil-A-6.7m | 6.7m | A-Class | 20 | 134M | 131k | 6.074100 |
|
28 |
| GerbilLab/Gerbil-B-6.7m | 6.7m | B-Class | 42 | 281M | 131k | 5.513200 |
|