End of training

all_results.json

@@ -1,7 +1,12 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6886791284533514,
-    "train_runtime": 13.5776,
-    "train_samples_per_second": 5.082,
-    "train_steps_per_second": 5.082
+    "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_results.json

@@ -0,0 +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
+}

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6886791284533514,
-    "train_runtime": 13.5776,
-    "train_samples_per_second": 5.082,
-    "train_steps_per_second": 5.082
+    "train_loss": 0.6942512125208757,
+    "train_runtime": 21.1635,
+    "train_samples_per_second": 3.26,
+    "train_steps_per_second": 3.26
 }

trainer_state.json

@@ -7,14 +7,77 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.27536231884058e-05,
+      "loss": 0.6875,
+      "step": 10
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.5507246376811596e-05,
+      "loss": 0.7142,
+      "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,
+      "step": 23
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.826086956521739e-05,
+      "loss": 0.6874,
+      "step": 30
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.101449275362319e-05,
+      "loss": 0.6938,
+      "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,
+      "step": 46
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.6999,
+      "step": 50
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.6823,
+      "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,
+      "step": 69
+    },
     {
       "epoch": 3.0,
       "step": 69,
       "total_flos": 1465242836520960.0,
-      "train_loss": 0.6886791284533514,
-      "train_runtime": 13.5776,
-      "train_samples_per_second": 5.082,
-      "train_steps_per_second": 5.082
+      "train_loss": 0.6942512125208757,
+      "train_runtime": 21.1635,
+      "train_samples_per_second": 3.26,
+      "train_steps_per_second": 3.26
     }
   ],
   "max_steps": 69,