End of training

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 1.0,
     "eval_accuracy": 0.7884666754551509,
     "eval_loss": 1.2736778259277344,
-    "eval_runtime": 50.2183,
+    "eval_runtime": 49.5638,
     "eval_samples": 2252,
-    "eval_samples_per_second": 44.844,
-    "eval_steps_per_second": 1.414,
+    "eval_samples_per_second": 45.436,
+    "eval_steps_per_second": 1.432,
     "perplexity": 3.5739728705498077,
     "train_loss": 1.5686970041758979,
-    "train_runtime": 1113.7917,
+    "train_runtime": 1110.7658,
     "train_samples": 42863,
-    "train_samples_per_second": 38.484,
-    "train_steps_per_second": 1.203
+    "train_samples_per_second": 38.589,
+    "train_steps_per_second": 1.206
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 1.0,
     "eval_accuracy": 0.7884666754551509,
     "eval_loss": 1.2736778259277344,
-    "eval_runtime": 50.2183,
+    "eval_runtime": 49.5638,
     "eval_samples": 2252,
-    "eval_samples_per_second": 44.844,
-    "eval_steps_per_second": 1.414,
+    "eval_samples_per_second": 45.436,
+    "eval_steps_per_second": 1.432,
     "perplexity": 3.5739728705498077
 }

runs/Nov06_17-40-38_hkmustamd-Super-Server/events.out.tfevents.1730887369.hkmustamd-Super-Server.3609935.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7f6e0bb839131ce076417b7a575619c3d2222dc6e61405f6aa5c0ddd043ec0
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 1.5686970041758979,
-    "train_runtime": 1113.7917,
+    "train_runtime": 1110.7658,
     "train_samples": 42863,
-    "train_samples_per_second": 38.484,
-    "train_steps_per_second": 1.203
+    "train_samples_per_second": 38.589,
+    "train_steps_per_second": 1.206
 }

trainer_state.json

@@ -24,9 +24,9 @@
       "step": 1340,
       "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
+      "train_runtime": 1110.7658,
+      "train_samples_per_second": 38.589,
+      "train_steps_per_second": 1.206
     }
   ],
   "max_steps": 1340,