Training in progress, step 500

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
-    "down_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "gate_proj"
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "k_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:f437ed8bf8e6d43b308c5949142db2cad89d49ef943171eb76492d97f0779306
+oid sha256:59d41f8e29310d3f255fc3f32f82fe768292a262297f0f8219a4fb1ff7997b16
 size 1342238560

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 2048,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562b245f8d738e5240c21fd50361cc35f298146ed8962820e393583aae5db676
+oid sha256:56c81ecefeb97b329fffb383f7e4f3049c70f64eb7b5523a471380ddb201a4db
 size 5432