Training in progress, step 100

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
-    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
-    "gate_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70f95fe489a3b9f4ab1843cf3175285178c7b0898ef75c1f3a76dc82aaa4d83
+oid sha256:c20ca4bb9d830f3dc5e91ae5e278e2c0340addddc73230340ee0e004eb27e927
 size 83946192

runs/Apr15_11-10-02_holygpu8a17102.rc.fas.harvard.edu/events.out.tfevents.1713193923.holygpu8a17102.rc.fas.harvard.edu.2490248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0eddbe0f37185e1db1b7e541d2d5b27994c5f462496b8645e476c68fa79d2fc
+size 9552

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fff5d8acc5f4f91c096f066dcef02f301c87fff701aaad187eb6ee46346aab
+oid sha256:44503e2c0dc060afa9c5cf5faf8c845c6f7db08264f0af7a501434ad7b283ce1
 size 5048