Gemma-2-2B
Collection
36 items
•
Updated
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-2 dataset. 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 |
---|---|---|---|
1.0003 | 0.8696 | 5 | 1.0526 |
0.9778 | 1.9130 | 11 | 0.9144 |
0.8521 | 2.9565 | 17 | 0.8022 |
0.7041 | 4.0 | 23 | 0.7458 |
0.6478 | 4.8696 | 28 | 0.7177 |
0.5764 | 5.9130 | 34 | 0.7000 |
0.4782 | 6.9565 | 40 | 0.6944 |
0.4344 | 8.0 | 46 | 0.6963 |
0.3571 | 8.8696 | 51 | 0.7276 |
0.2965 | 9.9130 | 57 | 0.8026 |
0.2046 | 10.9565 | 63 | 0.9341 |
0.119 | 12.0 | 69 | 1.0343 |
0.064 | 12.8696 | 74 | 1.2800 |
0.0358 | 13.9130 | 80 | 1.4146 |