Gemma-2-2B_auto
Collection
36 items
•
Updated
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1_auto, the GaetanMichelet/chat-120_ft_task-1_auto and the GaetanMichelet/chat-180_ft_task-1_auto datasets. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4834 | 1.0 | 17 | 1.4382 |
1.0602 | 2.0 | 34 | 1.0723 |
0.9602 | 3.0 | 51 | 0.9960 |
0.8255 | 4.0 | 68 | 0.9752 |
0.6121 | 5.0 | 85 | 1.0406 |
0.5169 | 6.0 | 102 | 1.2142 |
0.2771 | 7.0 | 119 | 1.5290 |
0.173 | 8.0 | 136 | 1.7919 |
0.1303 | 9.0 | 153 | 2.1345 |
0.0888 | 10.0 | 170 | 2.1369 |
0.0918 | 11.0 | 187 | 2.1555 |