Training in progress, step 2500

adapter_config.json

@@ -23,19 +23,19 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "linear_1",
+    "k_proj",
     "out_proj",
+    "up_proj",
+    "q_proj",
     "v_proj",
+    "fc2",
     "fc1",
-    "q_proj",
-    "k_proj",
-    "linear_1",
+    "lm_head",
     "linear_2",
-    "o_proj",
-    "up_proj",
-    "down_proj",
-    "gate_proj",
-    "fc2",
-    "lm_head"
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1c2a44885a37959ebf271c125c86746bfb5014410bc5f3f41f5bf93dcf025d
+oid sha256:f602b6118550b23a81fc19306feb8594628c315206c52cc8c559e5c8ae390a32
 size 621143576

runs/Apr28_15-33-42_26105b58bc3b/events.out.tfevents.1714318444.26105b58bc3b.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fcef3273668f0006bed046922891a3011845bced6e83c56146e9f43f1e96ac
+size 26629

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f55234b9070080a69d89b451fcf0890639ba2c888458f9313113e09a8477f62
+oid sha256:aca5710bd33a52f9ce86458e6a86b0d05d2d0d224c57fe22fd05d27c311c5031
 size 5048