End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.8,
-    "eval_loss": 0.6858694553375244,
-    "eval_runtime": 0.1243,
-    "eval_samples_per_second": 40.237,
-    "eval_steps_per_second": 8.047,
-    "train_loss": 0.6942512125208757,
-    "train_runtime": 21.1635,
-    "train_samples_per_second": 3.26,
-    "train_steps_per_second": 3.26
+    "eval_accuracy": 0.6,
+    "eval_loss": 0.6853448748588562,
+    "eval_runtime": 0.1365,
+    "eval_samples_per_second": 36.618,
+    "eval_steps_per_second": 7.324,
+    "train_loss": 0.6992312652477319,
+    "train_runtime": 27.1417,
+    "train_samples_per_second": 2.542,
+    "train_steps_per_second": 2.542
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.8,
-    "eval_loss": 0.6858694553375244,
-    "eval_runtime": 0.1243,
-    "eval_samples_per_second": 40.237,
-    "eval_steps_per_second": 8.047
+    "eval_accuracy": 0.6,
+    "eval_loss": 0.6853448748588562,
+    "eval_runtime": 0.1365,
+    "eval_samples_per_second": 36.618,
+    "eval_steps_per_second": 7.324
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6942512125208757,
-    "train_runtime": 21.1635,
-    "train_samples_per_second": 3.26,
-    "train_steps_per_second": 3.26
+    "train_loss": 0.6992312652477319,
+    "train_runtime": 27.1417,
+    "train_samples_per_second": 2.542,
+    "train_steps_per_second": 2.542
 }

trainer_state.json

@@ -10,74 +10,74 @@
     {
       "epoch": 0.43,
       "learning_rate": 4.27536231884058e-05,
-      "loss": 0.6875,
+      "loss": 0.7204,
       "step": 10
     },
     {
       "epoch": 0.87,
       "learning_rate": 3.5507246376811596e-05,
-      "loss": 0.7142,
+      "loss": 0.6918,
       "step": 20
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 0.689231276512146,
-      "eval_runtime": 0.1389,
-      "eval_samples_per_second": 35.988,
-      "eval_steps_per_second": 7.198,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6894806623458862,
+      "eval_runtime": 0.1526,
+      "eval_samples_per_second": 32.764,
+      "eval_steps_per_second": 6.553,
       "step": 23
     },
     {
       "epoch": 1.3,
       "learning_rate": 2.826086956521739e-05,
-      "loss": 0.6874,
+      "loss": 0.6986,
       "step": 30
     },
     {
       "epoch": 1.74,
       "learning_rate": 2.101449275362319e-05,
-      "loss": 0.6938,
+      "loss": 0.7019,
       "step": 40
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4,
-      "eval_loss": 0.7027438879013062,
-      "eval_runtime": 0.1438,
-      "eval_samples_per_second": 34.781,
-      "eval_steps_per_second": 6.956,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6858540177345276,
+      "eval_runtime": 0.1355,
+      "eval_samples_per_second": 36.891,
+      "eval_steps_per_second": 7.378,
       "step": 46
     },
     {
       "epoch": 2.17,
       "learning_rate": 1.3768115942028985e-05,
-      "loss": 0.6999,
+      "loss": 0.6927,
       "step": 50
     },
     {
       "epoch": 2.61,
       "learning_rate": 6.521739130434783e-06,
-      "loss": 0.6823,
+      "loss": 0.69,
       "step": 60
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8,
-      "eval_loss": 0.6858694553375244,
-      "eval_runtime": 0.1346,
-      "eval_samples_per_second": 37.154,
-      "eval_steps_per_second": 7.431,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6853448748588562,
+      "eval_runtime": 0.1356,
+      "eval_samples_per_second": 36.871,
+      "eval_steps_per_second": 7.374,
       "step": 69
     },
     {
       "epoch": 3.0,
       "step": 69,
       "total_flos": 1465242836520960.0,
-      "train_loss": 0.6942512125208757,
-      "train_runtime": 21.1635,
-      "train_samples_per_second": 3.26,
-      "train_steps_per_second": 3.26
+      "train_loss": 0.6992312652477319,
+      "train_runtime": 27.1417,
+      "train_samples_per_second": 2.542,
+      "train_steps_per_second": 2.542
     }
   ],
   "max_steps": 69,