azma-phi-2-instruct-structured

README.md

@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.8575
 
 ## Model description
 
@@ -45,16 +43,11 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - lr_scheduler_warmup_steps: 150
-- num_epochs: 0.1
+- num_epochs: 0.5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.6839        | 0.03  | 25   | 0.9049          |
-| 0.7678        | 0.06  | 50   | 0.8707          |
-| 0.8489        | 0.09  | 75   | 0.8575          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b049c687bd8b026a06d97cfc3be5cadd2ff3326f03dafbf35c83e8d5cb4d0e1
+oid sha256:d74caff28ba59f74016fd12ff2419b553e4fd124a67b719faa70d5ec25336211
 size 1115659992