Model save

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "down_proj",
     "v_proj",
-    "gate_proj",
     "k_proj",
-    "up_proj",
-    "o_proj",
+    "gate_proj",
     "q_proj",
-    "down_proj"
+    "o_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": 0.0101,
+    "train_runtime": 0.0099,
     "train_samples": 9000,
-    "train_samples_per_second": 54933.863,
-    "train_steps_per_second": 3451.859
+    "train_samples_per_second": 56384.306,
+    "train_steps_per_second": 3542.999
 }

runs/Nov28_06-35-20_RLHF000/events.out.tfevents.1732775729.RLHF000.97236.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068c4dfdf11c34ca1bbba3ce3d3fc7b087935a526996c68bb0fb25aa9444d27e
+size 7260

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 5.19321114598441e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0101,
+    "train_runtime": 0.0099,
     "train_samples": 9000,
-    "train_samples_per_second": 54933.863,
-    "train_steps_per_second": 3451.859
+    "train_samples_per_second": 56384.306,
+    "train_steps_per_second": 3542.999
 }

trainer_state.json

@@ -69,9 +69,9 @@
       "step": 35,
       "total_flos": 5.19321114598441e+16,
       "train_loss": 0.0,
-      "train_runtime": 0.0101,
-      "train_samples_per_second": 54933.863,
-      "train_steps_per_second": 3451.859
+      "train_runtime": 0.0099,
+      "train_samples_per_second": 56384.306,
+      "train_steps_per_second": 3542.999
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b5a4eaa042445efe6b2a06ce6686184fbd6b4858ba94e63f557be79d5dde1e
+oid sha256:4eadd231f38a2d294c057e90b742af8791778b34b67be9e8c3e5ab298a9a3d02
 size 6328