Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj",
     "v_proj",
+    "o_proj",
+    "q_proj",
     "k_proj",
-    "o_proj"
+    "up_proj",
+    "gate_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 sha256:1ce231db4ef2b4612e9717d2e741c8a684cda4ac13a5f65927293d24c390bd66
+oid sha256:71b426352ed731cf70db5bfb8ea033921c86c12ac791f78d72226471ee4a05e2
 size 2772497632

runs/Jul23_14-40-46_merlin.doc.ic.ac.uk/events.out.tfevents.1721742058.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb160aa321f22109395450c6d2940386df39c14d3f2cd32b677ff3ea03a9954
+size 9746

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a921931fa21f72b5ecc1ead6ed43fa45d3e2f835cd0350b838c50d2f2b3e06ba
+oid sha256:46d76ef99d6dcce6b906a9a346be5606ffb8f73240f1b7f9166d1184d5608c9a
 size 5048