Training in progress, step 63

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
     "o_proj",
-    "v_proj",
-    "q_proj",
+    "down_proj",
+    "gate_proj",
     "k_proj",
-    "up_proj"
+    "up_proj",
+    "q_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:dbe1f260b98c68cf732f5017318a2c4a204504a0abeb2491408c709c6fdfbea5
+oid sha256:e9447d67d20f5f9f420e29e5eac75c00d48640136fa942092996818ff8424b61
 size 1095431224

runs/Jan03_16-47-42_fcbe71c28f78/events.out.tfevents.1767458865.fcbe71c28f78.9334.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308dc661591698cc5dc7f4499f41e85c4112885677de95e231a9dcc6c36f5718
+size 9558

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefe44dd452ca2d24885b4b05c05521b6229f6bec043fe1ff2611a5c1cb5e81e
+oid sha256:07a5c0949d0e546e140d4445032f7589a9c5535e4b5d517f469dd893c876a82c
 size 5624