Training in progress, step 61875

logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal, attn_weight=25.0/events.out.tfevents.1724500688.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335274c9ee176f2c6ef94b69bd9ca260f9611934a1495c7c8c02d95607105ba2
+size 29625373

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821aadb92e867c39f41c6bafc997deb9786e62a2dbc16f047bae476d59ba3654
+oid sha256:8b7d7727abfa160a03b1932b595fa82dea9e9a6de0d7e299192a5f99c0c2788a
 size 248894656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83290bb8a0de86b82a93f3914ae872b55b91edea2fa3f02fa716ce370657d382
-size 5496
+oid sha256:a4ff44b3871953b465130242e9a530d42be863fcb71a24931a89de23ecaa295f
+size 5560