End of training

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.7885141326077298,
-    "eval_loss": 1.2729982137680054,
-    "eval_runtime": 50.6249,
-    "eval_samples": 2251,
-    "eval_samples_per_second": 44.464,
-    "eval_steps_per_second": 1.402,
-    "perplexity": 3.571544780301725,
-    "train_loss": 1.5675515473778567,
-    "train_runtime": 1123.1663,
-    "train_samples": 42861,
-    "train_samples_per_second": 38.161,
-    "train_steps_per_second": 1.193
+    "eval_accuracy": 0.7884666754551509,
+    "eval_loss": 1.2736778259277344,
+    "eval_runtime": 50.2183,
+    "eval_samples": 2252,
+    "eval_samples_per_second": 44.844,
+    "eval_steps_per_second": 1.414,
+    "perplexity": 3.5739728705498077,
+    "train_loss": 1.5686970041758979,
+    "train_runtime": 1113.7917,
+    "train_samples": 42863,
+    "train_samples_per_second": 38.484,
+    "train_steps_per_second": 1.203
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.7885141326077298,
-    "eval_loss": 1.2729982137680054,
-    "eval_runtime": 50.6249,
-    "eval_samples": 2251,
-    "eval_samples_per_second": 44.464,
-    "eval_steps_per_second": 1.402,
-    "perplexity": 3.571544780301725
+    "eval_accuracy": 0.7884666754551509,
+    "eval_loss": 1.2736778259277344,
+    "eval_runtime": 50.2183,
+    "eval_samples": 2252,
+    "eval_samples_per_second": 44.844,
+    "eval_steps_per_second": 1.414,
+    "perplexity": 3.5739728705498077
 }

runs/Nov06_12-17-24_hkmustamd-Super-Server/events.out.tfevents.1730868016.hkmustamd-Super-Server.3550109.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73f18c19472a5413709a3450fdf1b0e931b6f4f6442056374682c8ce9a8b58f
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 1.5675515473778567,
-    "train_runtime": 1123.1663,
-    "train_samples": 42861,
-    "train_samples_per_second": 38.161,
-    "train_steps_per_second": 1.193
+    "train_loss": 1.5686970041758979,
+    "train_runtime": 1113.7917,
+    "train_samples": 42863,
+    "train_samples_per_second": 38.484,
+    "train_steps_per_second": 1.203
 }

trainer_state.json

@@ -10,28 +10,28 @@
     {
       "epoch": 0.37,
       "learning_rate": 6.965174129353234e-07,
-      "loss": 1.8368,
+      "loss": 1.8401,
       "step": 500
     },
     {
       "epoch": 0.75,
       "learning_rate": 2.8192371475953566e-07,
-      "loss": 1.4194,
+      "loss": 1.4199,
       "step": 1000
     },
     {
       "epoch": 1.0,
       "step": 1340,
-      "total_flos": 1.306695716831232e+16,
-      "train_loss": 1.5675515473778567,
-      "train_runtime": 1123.1663,
-      "train_samples_per_second": 38.161,
-      "train_steps_per_second": 1.193
+      "total_flos": 1.306756690477056e+16,
+      "train_loss": 1.5686970041758979,
+      "train_runtime": 1113.7917,
+      "train_samples_per_second": 38.484,
+      "train_steps_per_second": 1.203
     }
   ],
   "max_steps": 1340,
   "num_train_epochs": 1,
-  "total_flos": 1.306695716831232e+16,
+  "total_flos": 1.306756690477056e+16,
   "trial_name": null,
   "trial_params": null
 }