transfer_learning_phi_2
Collection
36 items
•
Updated
This model is a fine-tuned version of microsoft/phi-2 on an unknown 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 | Accuracy | F1 Micro | Auc |
---|---|---|---|---|---|---|
0.568 | 1.0 | 38 | 0.7912 | 0.6554 | 0.6554 | 0.7416 |
0.3811 | 2.0 | 76 | 0.4819 | 0.7993 | 0.7993 | 0.8744 |
0.3865 | 3.0 | 114 | 0.4640 | 0.7977 | 0.7977 | 0.8817 |
0.0544 | 4.0 | 152 | 0.7133 | 0.8043 | 0.8043 | 0.8945 |
0.0295 | 5.0 | 190 | 0.8298 | 0.8100 | 0.8100 | 0.8867 |
0.006 | 6.0 | 228 | 0.7943 | 0.7985 | 0.7985 | 0.8943 |
0.0013 | 7.0 | 266 | 0.8377 | 0.8084 | 0.8084 | 0.8939 |
Base model
microsoft/phi-2