Model save

adapter_config.json

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

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 1.1487027058043781e+19,
-    "train_loss": 0.8902242264134556,
-    "train_runtime": 34738.9702,
+    "train_loss": 0.0,
+    "train_runtime": 0.0169,
     "train_samples": 207864,
-    "train_samples_per_second": 3.992,
-    "train_steps_per_second": 0.166
+    "train_samples_per_second": 8184133.024,
+    "train_steps_per_second": 341027.672
 }

runs/Nov18_09-06-30_d28f7adca72c/events.out.tfevents.1731920841.d28f7adca72c.1609162.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8319038ea07c5da8c1ca7771696a58956a792eef296dcd151f6d4fed81baafa
+size 6998

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 1.1487027058043781e+19,
-    "train_loss": 0.8902242264134556,
-    "train_runtime": 34738.9702,
+    "train_loss": 0.0,
+    "train_runtime": 0.0169,
     "train_samples": 207864,
-    "train_samples_per_second": 3.992,
-    "train_steps_per_second": 0.166
+    "train_samples_per_second": 8184133.024,
+    "train_steps_per_second": 341027.672
 }

trainer_state.json

@@ -8100,22 +8100,14 @@
       "loss": 0.8886,
       "step": 5775
     },
-    {
-      "epoch": 1.0,
-      "eval_loss": 0.9683669805526733,
-      "eval_runtime": 1122.8206,
-      "eval_samples_per_second": 13.671,
-      "eval_steps_per_second": 0.57,
-      "step": 5779
-    },
     {
       "epoch": 1.0,
       "step": 5779,
       "total_flos": 1.1487027058043781e+19,
-      "train_loss": 0.8902242264134556,
-      "train_runtime": 34738.9702,
-      "train_samples_per_second": 3.992,
-      "train_steps_per_second": 0.166
+      "train_loss": 0.0,
+      "train_runtime": 0.0169,
+      "train_samples_per_second": 8184133.024,
+      "train_steps_per_second": 341027.672
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f37293628d10e47961ded5c449d8942fe36a719860387f0553788b63228638f
+oid sha256:82763ac4d1451da25c7cb359dd9ee2581f99c3d2b8db998d96375db407c0978e
 size 6328