Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
     "o_proj",
     "k_proj",
-    "down_proj",
-    "q_proj",
     "gate_proj",
-    "v_proj",
-    "up_proj"
+    "down_proj",
+    "v_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:f695caae89eee61d4fa30efe1ef4387447d1fbff6b77e078f4e425cc4d35c16b
+oid sha256:721c4faa6744fa00e338179944662a5e53d68732535bda9578a611aacc2485ed
 size 2772497632

runs/Jul25_16-38-21_merlin.doc.ic.ac.uk/events.out.tfevents.1721921913.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4684ec60a086bf8899b831587fc73a17bca1c766f747beac6a8b314d2ed726e2
+size 22625

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109f61dd6b6dc339e33380da47b4c24485af7f253e712e1eacbb13a89de1330e
+oid sha256:02eeb8f0f138565fc4db9bcec31287392404b865580b0a0c192d1bcdc556dc83
 size 5048