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 |
---|---|---|---|---|---|---|
0.6646 | 1.0 | 37 | 0.5776 | 0.6985 | 0.6985 | 0.7703 |
0.3833 | 2.0 | 74 | 0.5834 | 0.7070 | 0.7070 | 0.7918 |
0.2902 | 3.0 | 111 | 0.6313 | 0.7251 | 0.7251 | 0.7991 |
0.1051 | 4.0 | 148 | 0.8300 | 0.6985 | 0.6985 | 0.7842 |
0.0836 | 5.0 | 185 | 0.9224 | 0.7122 | 0.7122 | 0.7889 |
0.01 | 6.0 | 222 | 1.0059 | 0.7165 | 0.7165 | 0.7983 |
0.006 | 7.0 | 259 | 1.0435 | 0.7182 | 0.7182 | 0.7986 |
Base model
microsoft/phi-2