Model save

adapter_config.json

@@ -17,9 +17,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
     "q_proj",
-    "o_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55781a0314f695d8e8230b4bb6fa7c6f34fea0b06e4d3c140c535cd51b3cbba
+oid sha256:48b34a428074e5b7cc32b3fd5343936b35b0a5c869b9ecd3c09f7000dcb50b11
 size 109086672

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0.67,
-    "eval_loss": 1.0666674375534058,
-    "eval_runtime": 2391.2283,
+    "eval_loss": 1.0666700601577759,
+    "eval_runtime": 2384.3246,
     "eval_samples": 23110,
-    "eval_samples_per_second": 9.664,
-    "eval_steps_per_second": 0.151,
-    "train_loss": 1.1599184581462074,
-    "train_runtime": 72731.1653,
+    "eval_samples_per_second": 9.692,
+    "eval_steps_per_second": 0.152,
+    "train_loss": 1.1599246359923308,
+    "train_runtime": 72626.7254,
     "train_samples": 207865,
-    "train_samples_per_second": 2.858,
+    "train_samples_per_second": 2.862,
     "train_steps_per_second": 0.006
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.67,
-    "eval_loss": 1.0666674375534058,
-    "eval_runtime": 2391.2283,
+    "eval_loss": 1.0666700601577759,
+    "eval_runtime": 2384.3246,
     "eval_samples": 23110,
-    "eval_samples_per_second": 9.664,
-    "eval_steps_per_second": 0.151
+    "eval_samples_per_second": 9.692,
+    "eval_steps_per_second": 0.152
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.67,
-    "train_loss": 1.1599184581462074,
-    "train_runtime": 72731.1653,
+    "train_loss": 1.1599246359923308,
+    "train_runtime": 72626.7254,
     "train_samples": 207865,
-    "train_samples_per_second": 2.858,
+    "train_samples_per_second": 2.862,
     "train_steps_per_second": 0.006
 }

trainer_state.json

@@ -77,7 +77,7 @@
     {
       "epoch": 0.14,
       "learning_rate": 1.910797282022027e-05,
-      "loss": 1.2333,
+      "loss": 1.2334,
       "step": 55
     },
     {
@@ -149,7 +149,7 @@
     {
       "epoch": 0.28,
       "learning_rate": 1.629520819706912e-05,
-      "loss": 1.1069,
+      "loss": 1.107,
       "step": 115
     },
     {
@@ -179,7 +179,7 @@
     {
       "epoch": 0.34,
       "learning_rate": 1.4684084406997903e-05,
-      "loss": 1.0909,
+      "loss": 1.091,
       "step": 140
     },
     {
@@ -275,7 +275,7 @@
     {
       "epoch": 0.54,
       "learning_rate": 8.688345254588579e-06,
-      "loss": 1.0685,
+      "loss": 1.0686,
       "step": 220
     },
     {
@@ -340,9 +340,9 @@
     },
     {
       "epoch": 0.67,
-      "eval_loss": 1.0667219161987305,
-      "eval_runtime": 2389.1593,
-      "eval_samples_per_second": 9.673,
+      "eval_loss": 1.066724419593811,
+      "eval_runtime": 2385.329,
+      "eval_samples_per_second": 9.688,
       "eval_steps_per_second": 0.152,
       "step": 272
     },
@@ -350,9 +350,9 @@
       "epoch": 0.67,
       "step": 272,
       "total_flos": 4.932776606721638e+16,
-      "train_loss": 1.1599184581462074,
-      "train_runtime": 72731.1653,
-      "train_samples_per_second": 2.858,
+      "train_loss": 1.1599246359923308,
+      "train_runtime": 72626.7254,
+      "train_samples_per_second": 2.862,
       "train_steps_per_second": 0.006
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7bafc436c3a41a9a2a47904c2a1fb60e8d46cd8f97932f14a89887397ae60d
+oid sha256:9a116181e8e43014f8554b0cc2a81c8131193600bb4d374a77cd396fcfdc6416
 size 5624