Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -48,9 +48,9 @@
       "epoch": 1.0416666666666667,
       "eval_accuracy": 0.4625,
       "eval_loss": 1.135870099067688,
-      "eval_runtime": 1.3858,
-      "eval_samples_per_second": 57.728,
-      "eval_steps_per_second": 7.216,
+      "eval_runtime": 1.2659,
+      "eval_samples_per_second": 63.197,
+      "eval_steps_per_second": 7.9,
       "step": 50
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 2.0833333333333335,
       "eval_accuracy": 0.725,
       "eval_loss": 1.0034687519073486,
-      "eval_runtime": 1.3401,
-      "eval_samples_per_second": 59.698,
-      "eval_steps_per_second": 7.462,
+      "eval_runtime": 1.2636,
+      "eval_samples_per_second": 63.309,
+      "eval_steps_per_second": 7.914,
       "step": 100
     },
     {
@@ -136,9 +136,9 @@
       "epoch": 3.125,
       "eval_accuracy": 0.7625,
       "eval_loss": 0.8992247581481934,
-      "eval_runtime": 1.3171,
-      "eval_samples_per_second": 60.738,
-      "eval_steps_per_second": 7.592,
+      "eval_runtime": 1.2311,
+      "eval_samples_per_second": 64.981,
+      "eval_steps_per_second": 8.123,
       "step": 150
     },
     {
@@ -180,9 +180,9 @@
       "epoch": 4.166666666666667,
       "eval_accuracy": 0.8,
       "eval_loss": 0.7827270030975342,
-      "eval_runtime": 1.3172,
-      "eval_samples_per_second": 60.737,
-      "eval_steps_per_second": 7.592,
+      "eval_runtime": 1.2396,
+      "eval_samples_per_second": 64.536,
+      "eval_steps_per_second": 8.067,
       "step": 200
     },
     {
@@ -224,9 +224,9 @@
       "epoch": 5.208333333333333,
       "eval_accuracy": 0.8125,
       "eval_loss": 0.6670618653297424,
-      "eval_runtime": 1.3129,
-      "eval_samples_per_second": 60.935,
-      "eval_steps_per_second": 7.617,
+      "eval_runtime": 1.2584,
+      "eval_samples_per_second": 63.572,
+      "eval_steps_per_second": 7.946,
       "step": 250
     },
     {
@@ -268,9 +268,9 @@
       "epoch": 6.25,
       "eval_accuracy": 0.725,
       "eval_loss": 0.6925244927406311,
-      "eval_runtime": 1.3148,
-      "eval_samples_per_second": 60.847,
-      "eval_steps_per_second": 7.606,
+      "eval_runtime": 1.3296,
+      "eval_samples_per_second": 60.169,
+      "eval_steps_per_second": 7.521,
       "step": 300
     },
     {
@@ -312,9 +312,9 @@
       "epoch": 7.291666666666667,
       "eval_accuracy": 0.8125,
       "eval_loss": 0.5735878348350525,
-      "eval_runtime": 1.3277,
-      "eval_samples_per_second": 60.256,
-      "eval_steps_per_second": 7.532,
+      "eval_runtime": 1.2591,
+      "eval_samples_per_second": 63.536,
+      "eval_steps_per_second": 7.942,
       "step": 350
     },
     {
@@ -356,9 +356,9 @@
       "epoch": 8.333333333333334,
       "eval_accuracy": 0.8125,
       "eval_loss": 0.5838413238525391,
-      "eval_runtime": 1.2821,
-      "eval_samples_per_second": 62.397,
-      "eval_steps_per_second": 7.8,
+      "eval_runtime": 1.3799,
+      "eval_samples_per_second": 57.977,
+      "eval_steps_per_second": 7.247,
       "step": 400
     },
     {
@@ -400,9 +400,9 @@
       "epoch": 9.375,
       "eval_accuracy": 0.8125,
       "eval_loss": 0.570094108581543,
-      "eval_runtime": 1.273,
-      "eval_samples_per_second": 62.845,
-      "eval_steps_per_second": 7.856,
+      "eval_runtime": 1.4058,
+      "eval_samples_per_second": 56.905,
+      "eval_steps_per_second": 7.113,
       "step": 450
     },
     {
@@ -431,9 +431,9 @@
       "step": 480,
       "total_flos": 5.866248766604083e+17,
       "train_loss": 0.5593519407014053,
-      "train_runtime": 337.9667,
-      "train_samples_per_second": 22.399,
-      "train_steps_per_second": 1.42
+      "train_runtime": 335.8262,
+      "train_samples_per_second": 22.541,
+      "train_steps_per_second": 1.429
     }
   ],
   "logging_steps": 10,