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 |
---|---|---|---|---|---|---|
0.6039 | 1.0 | 38 | 0.5804 | 0.6798 | 0.6798 | 0.7669 |
0.393 | 2.0 | 76 | 0.4995 | 0.7784 | 0.7784 | 0.8421 |
0.3163 | 3.0 | 114 | 0.4793 | 0.7918 | 0.7918 | 0.8652 |
0.1588 | 4.0 | 152 | 0.5661 | 0.7860 | 0.7860 | 0.8597 |
0.0464 | 5.0 | 190 | 0.6070 | 0.7960 | 0.7960 | 0.8758 |
0.0601 | 6.0 | 228 | 0.7045 | 0.7985 | 0.7985 | 0.8761 |
0.029 | 7.0 | 266 | 0.6897 | 0.8010 | 0.8010 | 0.8783 |
Base model
microsoft/phi-2