Model save

adapter_config.json

@@ -16,9 +16,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.5,
     "eval_loss": 0.3125712275505066,
-    "eval_runtime": 13.3953,
+    "eval_runtime": 13.3998,
     "eval_samples": 120,
-    "eval_samples_per_second": 8.958,
-    "eval_steps_per_second": 2.24,
+    "eval_samples_per_second": 8.955,
+    "eval_steps_per_second": 2.239,
     "train_loss": 0.4085692544042328,
-    "train_runtime": 1490.0921,
+    "train_runtime": 1490.1076,
     "train_samples": 1076,
     "train_samples_per_second": 2.166,
     "train_steps_per_second": 0.542

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.5,
     "eval_loss": 0.3125712275505066,
-    "eval_runtime": 13.3953,
+    "eval_runtime": 13.3998,
     "eval_samples": 120,
-    "eval_samples_per_second": 8.958,
-    "eval_steps_per_second": 2.24
+    "eval_samples_per_second": 8.955,
+    "eval_steps_per_second": 2.239
 }

runs/Nov17_19-26-11_7a59b30c842e/events.out.tfevents.1700249177.7a59b30c842e.5618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d523fd6593c2045ac62fede13556623b7ffac702fc4664a3942fb4d9a4e455
+size 13242

runs/Nov17_19-26-11_7a59b30c842e/events.out.tfevents.1700250680.7a59b30c842e.5618.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afcbcc6d2b8fe5842707556ab62faa8b66ce093b4383fd4950e31f0ac2c9258
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.5,
     "train_loss": 0.4085692544042328,
-    "train_runtime": 1490.0921,
+    "train_runtime": 1490.1076,
     "train_samples": 1076,
     "train_samples_per_second": 2.166,
     "train_steps_per_second": 0.542

trainer_state.json

@@ -47,9 +47,9 @@
     {
       "epoch": 0.19,
       "eval_loss": 0.5209892392158508,
-      "eval_runtime": 13.386,
-      "eval_samples_per_second": 8.965,
-      "eval_steps_per_second": 2.241,
+      "eval_runtime": 13.3799,
+      "eval_samples_per_second": 8.969,
+      "eval_steps_per_second": 2.242,
       "step": 50
     },
     {
@@ -85,8 +85,8 @@
     {
       "epoch": 0.37,
       "eval_loss": 0.3655029237270355,
-      "eval_runtime": 13.3923,
-      "eval_samples_per_second": 8.96,
+      "eval_runtime": 13.394,
+      "eval_samples_per_second": 8.959,
       "eval_steps_per_second": 2.24,
       "step": 100
     },
@@ -123,8 +123,8 @@
     {
       "epoch": 1.06,
       "eval_loss": 0.33579277992248535,
-      "eval_runtime": 13.3932,
-      "eval_samples_per_second": 8.96,
+      "eval_runtime": 13.3918,
+      "eval_samples_per_second": 8.961,
       "eval_steps_per_second": 2.24,
       "step": 150
     },
@@ -161,9 +161,9 @@
     {
       "epoch": 1.24,
       "eval_loss": 0.32932165265083313,
-      "eval_runtime": 13.3968,
-      "eval_samples_per_second": 8.957,
-      "eval_steps_per_second": 2.239,
+      "eval_runtime": 13.3944,
+      "eval_samples_per_second": 8.959,
+      "eval_steps_per_second": 2.24,
       "step": 200
     },
     {
@@ -199,9 +199,9 @@
     {
       "epoch": 1.43,
       "eval_loss": 0.3206278085708618,
-      "eval_runtime": 13.3982,
-      "eval_samples_per_second": 8.956,
-      "eval_steps_per_second": 2.239,
+      "eval_runtime": 13.393,
+      "eval_samples_per_second": 8.96,
+      "eval_steps_per_second": 2.24,
       "step": 250
     },
     {
@@ -237,9 +237,9 @@
     {
       "epoch": 2.11,
       "eval_loss": 0.3176751732826233,
-      "eval_runtime": 13.3874,
-      "eval_samples_per_second": 8.964,
-      "eval_steps_per_second": 2.241,
+      "eval_runtime": 13.3957,
+      "eval_samples_per_second": 8.958,
+      "eval_steps_per_second": 2.24,
       "step": 300
     },
     {
@@ -275,8 +275,8 @@
     {
       "epoch": 2.3,
       "eval_loss": 0.31533822417259216,
-      "eval_runtime": 13.3997,
-      "eval_samples_per_second": 8.955,
+      "eval_runtime": 13.396,
+      "eval_samples_per_second": 8.958,
       "eval_steps_per_second": 2.239,
       "step": 350
     },
@@ -313,7 +313,7 @@
     {
       "epoch": 2.48,
       "eval_loss": 0.31296682357788086,
-      "eval_runtime": 13.3926,
+      "eval_runtime": 13.3929,
       "eval_samples_per_second": 8.96,
       "eval_steps_per_second": 2.24,
       "step": 400
@@ -323,7 +323,7 @@
       "step": 405,
       "total_flos": 7.077875641902694e+16,
       "train_loss": 0.4085692544042328,
-      "train_runtime": 1490.0921,
+      "train_runtime": 1490.1076,
       "train_samples_per_second": 2.166,
       "train_steps_per_second": 0.542
     }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66793634e8d7f0f1ba7604b0abaf49c95b94b5297f3a1a786e7ecf55c6231a4d
+oid sha256:c8afa4b1ac7680ace81555ad3d37c75491f2ba1a85f21347a2fcd7fb4e08d8f6
 size 4664