yzhuang/phi-1_5_fictional

README.md

@@ -6,7 +6,7 @@ tags:
 - sft
 - generated_from_trainer
 datasets:
-- mmlu
+- mmlu_no_train
 model-index:
 - name: phi-1_5_fictional
   results: []
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-1_5_fictional
 
-This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the mmlu dataset.
+This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the mmlu_no_train dataset.
 
 ## Model description
 
@@ -36,13 +36,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 1e-05
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results