Model save

README.md

@@ -45,7 +45,7 @@ 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: 2
+- num_epochs: 3
 
 ### Training results
 

runs/Jul24_14-42-10_merlin.doc.ic.ac.uk/events.out.tfevents.1721828537.merlin.doc.ic.ac.uk

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b132bdb0acfb2f5901f38419f72b2e32f9498445c64df81d6b895774afb2cb43
-size 15888
+oid sha256:f60f5097e42dfdda3b60d4f1de9d828ac2d1bf4f7d9db01d0c4c47d08ccc788b
+size 16732