Training in progress, step 24750

logs/copy_teacher_modules=_(_lm_head___True)_, hs_layer_mapper=last, hs_loss_fn=mse, hs_weight=1.0, learning_rate=0.0001, per_device_train_batch_size=4/events.out.tfevents.1724150485.02dbb11e2dcc

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52eb609f3652802c4c5e98366c7ca2b398d1612d0987c5525505e4f68540bb3c
+size 11775892

logs/learning_rate=0.0001, per_device_train_batch_size=4, reinitialize_weights=xavier/events.out.tfevents.1724150220.02dbb11e2dcc

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb7329b5173b222d9c393db25fc2c40bb0e0782c81dbf367ca90e89f1ad8249
-size 312
+oid sha256:42c82a469bee13fb9e37f85a78a0221848afb257b1bd21d9dbd2240591c384f9
+size 588

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54c240360aef51b6bf4376da354e211b825db282d77c24a5346fa68de97da59
+oid sha256:47475e68d3b88dc1f8aa7edaf215a3bd8de809f6eef578874604b482755a61c9
 size 248894656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd225b0a4396af5c5e2cb2d3c42d96ee3947473a80d5eaf5ce070d579063df0
-size 1017899144
+oid sha256:cfff802791021dc51f24981bf1d023396d1dd40a4c2a3d72121cd337195ecec6
+size 1017899208