End of training

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "task_type": "SEQ_2_SEQ_LM"
 }

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 0.02,
     "eval_loss": 2.021235942840576,
-    "eval_runtime": 20.8381,
-    "eval_samples_per_second": 377.05,
-    "eval_steps_per_second": 23.611,
+    "eval_runtime": 13.6322,
+    "eval_samples_per_second": 576.357,
+    "eval_steps_per_second": 36.091,
     "train_loss": 2.7679789066314697,
-    "train_runtime": 0.8665,
-    "train_samples_per_second": 0.115,
-    "train_steps_per_second": 1.154
+    "train_runtime": 0.7741,
+    "train_samples_per_second": 0.129,
+    "train_steps_per_second": 1.292
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
     "eval_loss": 2.021235942840576,
-    "eval_runtime": 20.8381,
-    "eval_samples_per_second": 377.05,
-    "eval_steps_per_second": 23.611
+    "eval_runtime": 13.6322,
+    "eval_samples_per_second": 576.357,
+    "eval_steps_per_second": 36.091
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.02,
     "train_loss": 2.7679789066314697,
-    "train_runtime": 0.8665,
-    "train_samples_per_second": 0.115,
-    "train_steps_per_second": 1.154
+    "train_runtime": 0.7741,
+    "train_samples_per_second": 0.129,
+    "train_steps_per_second": 1.292
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "step": 1,
       "total_flos": 517012193280.0,
       "train_loss": 2.7679789066314697,
-      "train_runtime": 0.8665,
-      "train_samples_per_second": 0.115,
-      "train_steps_per_second": 1.154
+      "train_runtime": 0.7741,
+      "train_samples_per_second": 0.129,
+      "train_steps_per_second": 1.292
     }
   ],
   "logging_steps": 500,