Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss |
---|---|---|---|---|---|---|
GerbilLab/Gerbil-B-6.7m | 6.7m | B-Class | 42 | 281M | 131k | 5.513200 |
Model Name | Parameters | Class | Ratio | Tokens | Batch Size (Tokens) | Training Loss |
---|---|---|---|---|---|---|
GerbilLab/Gerbil-B-6.7m | 6.7m | B-Class | 42 | 281M | 131k | 5.513200 |