End of training

all_results.json

@@ -16,8 +16,8 @@
     "predict_steps_per_second": 4.179,
     "total_flos": 2512343535714304.0,
     "train_loss": 0.3421715199947357,
-    "train_runtime": 21.295,
+    "train_runtime": 21.559,
     "train_samples": 100,
-    "train_samples_per_second": 93.919,
-    "train_steps_per_second": 3.757
+    "train_samples_per_second": 92.769,
+    "train_steps_per_second": 3.711
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 4.0,
     "total_flos": 2512343535714304.0,
     "train_loss": 0.3421715199947357,
-    "train_runtime": 21.295,
+    "train_runtime": 21.559,
     "train_samples": 100,
-    "train_samples_per_second": 93.919,
-    "train_steps_per_second": 3.757
+    "train_samples_per_second": 92.769,
+    "train_steps_per_second": 3.711
 }

trainer_state.json

@@ -13,9 +13,9 @@
       "eval_loss": 0.41245660185813904,
       "eval_macro-f1": 0.029029793735676088,
       "eval_micro-f1": 0.16521739130434782,
-      "eval_runtime": 1.0746,
-      "eval_samples_per_second": 93.059,
-      "eval_steps_per_second": 3.722,
+      "eval_runtime": 1.0722,
+      "eval_samples_per_second": 93.268,
+      "eval_steps_per_second": 3.731,
       "step": 4
     },
     {
@@ -23,9 +23,9 @@
       "eval_loss": 0.3445906341075897,
       "eval_macro-f1": 0.029029793735676088,
       "eval_micro-f1": 0.16521739130434782,
-      "eval_runtime": 1.4551,
-      "eval_samples_per_second": 68.726,
-      "eval_steps_per_second": 2.749,
+      "eval_runtime": 1.4747,
+      "eval_samples_per_second": 67.809,
+      "eval_steps_per_second": 2.712,
       "step": 8
     },
     {
@@ -33,9 +33,9 @@
       "eval_loss": 0.3343995213508606,
       "eval_macro-f1": 0.029029793735676088,
       "eval_micro-f1": 0.16521739130434782,
-      "eval_runtime": 1.1868,
-      "eval_samples_per_second": 84.263,
-      "eval_steps_per_second": 3.371,
+      "eval_runtime": 1.6766,
+      "eval_samples_per_second": 59.646,
+      "eval_steps_per_second": 2.386,
       "step": 12
     },
     {
@@ -43,9 +43,9 @@
       "eval_loss": 0.333324134349823,
       "eval_macro-f1": 0.029029793735676088,
       "eval_micro-f1": 0.16521739130434782,
-      "eval_runtime": 1.0777,
-      "eval_samples_per_second": 92.789,
-      "eval_steps_per_second": 3.712,
+      "eval_runtime": 1.0723,
+      "eval_samples_per_second": 93.253,
+      "eval_steps_per_second": 3.73,
       "step": 16
     },
     {
@@ -53,9 +53,9 @@
       "step": 16,
       "total_flos": 2512343535714304.0,
       "train_loss": 0.3421715199947357,
-      "train_runtime": 21.295,
-      "train_samples_per_second": 93.919,
-      "train_steps_per_second": 3.757
+      "train_runtime": 21.559,
+      "train_samples_per_second": 92.769,
+      "train_steps_per_second": 3.711
     }
   ],
   "logging_steps": 500,