Training in progress, step 195

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
+    "k_proj",
     "down_proj",
+    "o_proj",
+    "q_proj",
     "gate_proj",
-    "k_proj",
     "v_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:caf73503d376a36fc62544e2c08e1d3091a2e0e8fa4a3dee66b51c1330694f4b
+oid sha256:59a6ec0f383c48909175dd33c29e52948bfe3768debccabfa6f1dbf35a6c87cf
 size 4370592096

runs/Jul14_11-49-52_ml-cluster/events.out.tfevents.1720957796.ml-cluster

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d413a3b3cd959d6f6f23863bc7d79b4581d05d84a6971da06052937f625888c6
+size 6073

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb207d5975e0fafdd284b53620bbc08a7c5bf77eac2633c95b82eae1d074b0a7
-size 5368
+oid sha256:59b89d720b7db0e673379553ec9f2ed6dec0b50b1fac01342a180a83c55a4e4e
+size 5432