Training in progress, step 6300

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "v_proj",
+    "q_proj",
     "k_proj",
+    "o_proj",
     "gate_proj",
-    "q_proj",
+    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80dcbacc23e355ae1635e91a21ece7332dae44faf7fa35ac0e4f28696141051f
+oid sha256:bc0a36e6670b08a71ac79eba6769d626d4e1233045999a8aceff25107fa9056f
 size 671150064

runs/May11_08-07-40_gpu4-119-5/events.out.tfevents.1715378938.gpu4-119-5.116325.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c316bfc7c3c4e48ae61a3259d7ad03659d2b6b29fd71948aac2c0363bd02137
-size 334265
+oid sha256:15228ad4a149c175acb6739a87dd89bf5a3a23436ad3031440ad1fecdc253a35
+size 346945

runs/May11_22-17-27_gpu4-119-5/events.out.tfevents.1715429920.gpu4-119-5.1214138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9db43bd9c37eb969f1eb91787463ed7ecea7eb4a4a94d122de0c236bdc274f
+size 17252

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1540b513f290eb56665304de3b618f451b08fb36712fb6cc43b3b96a00af5de7
+oid sha256:024f90e6b0ad81343275b7ccd40eee85582f6de5fcf0dd68b76d761cd68e0d66
 size 5816