Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: microsoft/Phi-3-mini-128k-instruct
+base_model: microsoft/Phi-3.5-mini-instruct
 datasets:
 - generator
 library_name: peft
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi3-synthese
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the generator dataset.
+This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the generator dataset.
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 

runs/Sep06_07-23-03_ip-172-16-85-69.eu-west-1.compute.internal/events.out.tfevents.1725607387.ip-172-16-85-69.eu-west-1.compute.internal

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0410373e642781bf969fd4d09ff1167ab6394bfcefe7bde27eef5c91c3cba33
-size 8618
+oid sha256:176e2b194f4b6a753637f0654a8b78c8c14ff390dc5add35ca24ddf2540dfcec
+size 8966