Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
     "down_proj",
     "o_proj",
-    "v_proj",
-    "up_proj",
-    "k_proj",
-    "gate_proj"
+    "q_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 sha256:14ab65c99e300e6cd9507531a4eb4e786ee539b24097015b04fccfb4d5ff16e4
+oid sha256:c0ba09b09cb102027d3aefd19320455bcb095f7fcc1ae82aad3baafac9b1e89f
 size 2772497632

runs/Jul24_06-09-35_merlin.doc.ic.ac.uk/events.out.tfevents.1721797782.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473abfaa5b2728c48ef0c8295b4ef0ed4c75273e7b3ec8a94d5a1f318e6f6335
+size 10100

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab1484c4ba62e7212cb31446ed2949d4b940928b108e7955326fabfc52275e94
+oid sha256:a935644290408955814ec4c48434360c70dea5f68205ddc4d981921720774844
 size 5048