Training in progress, step 150

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
+    "gate_proj",
     "up_proj",
-    "k_proj",
+    "v_proj",
     "o_proj",
-    "q_proj",
-    "gate_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899d8bd2589b48ca72578912c9e5284e3405e8096a9052be38b8886b9454a4b1
+oid sha256:24d6f63c09de24f37566260f14128f6f6e4d458b4e04b3a7e53e0827f46fbf67
 size 5368770952

runs/Sep04_17-44-35_3b69552f5110/events.out.tfevents.1725471891.3b69552f5110.1421.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc2b20d912c516d27fefbfd6fdcbe93fda2dceab004b4f9fc55a217463d0bbe
+size 8183

runs/Sep04_17-50-47_3b69552f5110/events.out.tfevents.1725472256.3b69552f5110.1421.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2d0fc3e35ed2b6f80a1ba3b7b623a0251f1532a99ea46134738593e1fc4f32
+size 11457

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 4096,
+    "max_length": 8196,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d5b5d154dc7000be7cac569458fad2c60621333fa2a173f38ee795a40acad3
+oid sha256:22e1c387f84f4ca6d5678f49780218e66e50159aa6222d09af7c2cdd073bf62c
 size 5496