Training in progress, epoch 1

adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
     "v_proj",
-    "o_proj",
-    "q_proj",
     "gate_proj",
-    "up_proj"
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eeebb669d4c0fef5ea0e56f4b19fb55b59ad68e1fafa3bf296e98f01462e8b2
+oid sha256:50358b5fd537eb8d8a23f6be9dde93b2314cd1c390a283945bef53c50b0f5738
 size 2772497632

runs/Aug23_00-52-56_merlin.doc.ic.ac.uk/events.out.tfevents.1724370785.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725a194224e21125115398159cb3a311622550121abddaa079557efb34d4d6e7
+size 31909

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d19dd2d8d4416557bfdb346f51f5b45f82f9e7ee00fb7b9da7fa87e0b5c5328
+oid sha256:be979ab45bc07a7e17ee7c465242dac95c1f43414dcb9f2ad21c8b25f91c4685
 size 5048