Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
     "v_proj",
-    "down_proj",
-    "o_proj",
+    "gate_proj",
     "q_proj",
-    "up_proj"
+    "o_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:c0ba09b09cb102027d3aefd19320455bcb095f7fcc1ae82aad3baafac9b1e89f
+oid sha256:fbf8144351ba27d0158a640a32e172acc6efac7429b94885c84ded0edb085ee9
 size 2772497632

runs/Jul24_07-11-29_merlin.doc.ic.ac.uk/events.out.tfevents.1721801497.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8928ee5f68e54338e9f67fe63fce532d05faa8277c275656fcf96f607883c0
+size 9746

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a935644290408955814ec4c48434360c70dea5f68205ddc4d981921720774844
+oid sha256:f6067029b397230f44f2ac490e1ea41f01f1acbb7265ec125c6d0b4e6ef8cf17
 size 5048