Model save

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "v_proj",
     "k_proj",
+    "o_proj",
+    "up_proj",
     "gate_proj",
+    "v_proj",
     "q_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 5.19321114598441e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0099,
+    "train_runtime": 0.0084,
     "train_samples": 9000,
-    "train_samples_per_second": 56384.306,
-    "train_steps_per_second": 3542.999
+    "train_samples_per_second": 65929.937,
+    "train_steps_per_second": 4142.815
 }

runs/Nov28_06-38-20_RLHF000/events.out.tfevents.1732775908.RLHF000.98777.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886200c4aaba4df2c1fef3b92e99579ba28502f1624c87cda93f3f6e9185cedf
+size 7260

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 5.19321114598441e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0099,
+    "train_runtime": 0.0084,
     "train_samples": 9000,
-    "train_samples_per_second": 56384.306,
-    "train_steps_per_second": 3542.999
+    "train_samples_per_second": 65929.937,
+    "train_steps_per_second": 4142.815
 }

trainer_state.json

@@ -69,9 +69,9 @@
       "step": 35,
       "total_flos": 5.19321114598441e+16,
       "train_loss": 0.0,
-      "train_runtime": 0.0099,
-      "train_samples_per_second": 56384.306,
-      "train_steps_per_second": 3542.999
+      "train_runtime": 0.0084,
+      "train_samples_per_second": 65929.937,
+      "train_steps_per_second": 4142.815
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eadd231f38a2d294c057e90b742af8791778b34b67be9e8c3e5ab298a9a3d02
+oid sha256:18426c390d87b964366f0e138bbbc6614120bf09581855527a34ed0c4b57446e
 size 6328