Training in progress, epoch 0

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01407fb1b42c26dbfe92e33723bd580701127b2bbdac02061300c14c653eced8
+oid sha256:363a9fb11065de4ca859ff78edc30faea70d8936a7f596a2d575cb505adc53ed
 size 2772497632

runs/Jul25_12-22-26_merlin.doc.ic.ac.uk/events.out.tfevents.1721906558.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a87bc80d88b37cc694f0abd3f73e41593b14ea03b275b5573b8a36025535a4f7
+size 22625

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f250493a7505a9f8d7921a54e8e00cc2259ea51a4a6595131855703ceb91dc71
+oid sha256:109f61dd6b6dc339e33380da47b4c24485af7f253e712e1eacbb13a89de1330e
 size 5048