Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
-    "o_proj",
-    "gate_proj",
     "v_proj",
+    "up_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9c05dabf6d40d9c043b57e6d93599c9a42313233533f8342aaa8cf43ecc481
+oid sha256:e9d0a15437310c2245c19515ef45c6edc195ea6e4571c4db033ade3c6c61111a
 size 2772497632

runs/Jul23_22-20-35_merlin.doc.ic.ac.uk/events.out.tfevents.1721769643.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9aa6ce542779585008ab5adf8b2991a4372eb141ae1ff502febcbc1a37638a
+size 10100

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91ef3fce3586093fbfba735e0a403d7a9db4ce644c558d52edce601a97da8f2
+oid sha256:5a36d0ed04c33cf98539fdaf754ece917fa6fb996bda56a3cc011a405b62473f
 size 5048