Training in progress, step 1500

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k",
-    "q",
     "v",
-    "o"
+    "o",
+    "q",
+    "k"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9edf3caac01c6988bbe176392bea109e307147f846c32c0d422850760be8a901
+oid sha256:7dad052610a32d2391db76894505cc262ad66fe8317f09ad3d4793b264d7cc70
 size 9457304

runs/Apr01_08-24-56_fdc5e912607d/events.out.tfevents.1711959896.fdc5e912607d.2505.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e37775be745d2d04709320f47a4574a1ddff7c659218c89655d96df1945014
-size 7024
+oid sha256:3d4bd6781ee45aea3b1b2c4ba9a0c0eb6efb9911b917ea54760d4f0a7e3a9b0b
+size 7760

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23190c98d14958fd7d0c9050bad987a8aa8792dd8af315f2c1fabea65798727d
+oid sha256:440635b622791efa901046be5414e9b48fe8cd34e36bc9b30471cf76dedf8a21
 size 5048