End of training

all_results.json

@@ -9,10 +9,10 @@
     "eval_overall_f1": 0.751588502269289,
     "eval_overall_precision": 0.7280187573270809,
     "eval_overall_recall": 0.776735459662289,
-    "eval_runtime": 14.4883,
+    "eval_runtime": 12.6089,
     "eval_samples": 391,
-    "eval_samples_per_second": 26.987,
-    "eval_steps_per_second": 3.382,
+    "eval_samples_per_second": 31.01,
+    "eval_steps_per_second": 3.886,
     "predict_NG_f1": 0.757035509061441,
     "predict_NG_number": 3337,
     "predict_NG_precision": 0.7446376811594203,
@@ -22,12 +22,12 @@
     "predict_overall_f1": 0.757035509061441,
     "predict_overall_precision": 0.7446376811594203,
     "predict_overall_recall": 0.7698531615223254,
-    "predict_runtime": 15.2653,
-    "predict_samples_per_second": 25.614,
-    "predict_steps_per_second": 3.21,
+    "predict_runtime": 12.9044,
+    "predict_samples_per_second": 30.3,
+    "predict_steps_per_second": 3.797,
     "train_loss": 0.19723336571141292,
-    "train_runtime": 986.049,
+    "train_runtime": 917.7763,
     "train_samples": 1824,
-    "train_samples_per_second": 9.249,
-    "train_steps_per_second": 1.156
+    "train_samples_per_second": 9.937,
+    "train_steps_per_second": 1.242
 }

eval_results.json

@@ -9,8 +9,8 @@
     "eval_overall_f1": 0.751588502269289,
     "eval_overall_precision": 0.7280187573270809,
     "eval_overall_recall": 0.776735459662289,
-    "eval_runtime": 14.4883,
+    "eval_runtime": 12.6089,
     "eval_samples": 391,
-    "eval_samples_per_second": 26.987,
-    "eval_steps_per_second": 3.382
+    "eval_samples_per_second": 31.01,
+    "eval_steps_per_second": 3.886
 }

predict_results.json

@@ -8,7 +8,7 @@
     "predict_overall_f1": 0.757035509061441,
     "predict_overall_precision": 0.7446376811594203,
     "predict_overall_recall": 0.7698531615223254,
-    "predict_runtime": 15.2653,
-    "predict_samples_per_second": 25.614,
-    "predict_steps_per_second": 3.21
+    "predict_runtime": 12.9044,
+    "predict_samples_per_second": 30.3,
+    "predict_steps_per_second": 3.797
 }

runs/Jul05_17-25-35_e2ece3d5b0b5/events.out.tfevents.1688579015.e2ece3d5b0b5.4966.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ce4cd8f8d479c74df8ac4bafc4bb766176a29b2fd004150b311842ee6cc0a3
+size 803

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "train_loss": 0.19723336571141292,
-    "train_runtime": 986.049,
+    "train_runtime": 917.7763,
     "train_samples": 1824,
-    "train_samples_per_second": 9.249,
-    "train_steps_per_second": 1.156
+    "train_samples_per_second": 9.937,
+    "train_steps_per_second": 1.242
 }

trainer_state.json

@@ -24,9 +24,9 @@
       "eval_overall_f1": 0.7305991767037658,
       "eval_overall_precision": 0.7128830705147278,
       "eval_overall_recall": 0.7492182614133833,
-      "eval_runtime": 14.3745,
-      "eval_samples_per_second": 27.201,
-      "eval_steps_per_second": 3.409,
+      "eval_runtime": 13.4558,
+      "eval_samples_per_second": 29.058,
+      "eval_steps_per_second": 3.642,
       "step": 228
     },
     {
@@ -46,9 +46,9 @@
       "eval_overall_f1": 0.7509135200974422,
       "eval_overall_precision": 0.7317507418397626,
       "eval_overall_recall": 0.7711069418386491,
-      "eval_runtime": 14.3096,
-      "eval_samples_per_second": 27.324,
-      "eval_steps_per_second": 3.424,
+      "eval_runtime": 13.7791,
+      "eval_samples_per_second": 28.376,
+      "eval_steps_per_second": 3.556,
       "step": 456
     },
     {
@@ -68,9 +68,9 @@
       "eval_overall_f1": 0.7496210973022128,
       "eval_overall_precision": 0.7273529411764705,
       "eval_overall_recall": 0.7732958098811757,
-      "eval_runtime": 14.2735,
-      "eval_samples_per_second": 27.393,
-      "eval_steps_per_second": 3.433,
+      "eval_runtime": 13.0377,
+      "eval_samples_per_second": 29.99,
+      "eval_steps_per_second": 3.758,
       "step": 684
     },
     {
@@ -90,9 +90,9 @@
       "eval_overall_f1": 0.7498103474434835,
       "eval_overall_precision": 0.7282640730916593,
       "eval_overall_recall": 0.7726704190118824,
-      "eval_runtime": 14.344,
-      "eval_samples_per_second": 27.259,
-      "eval_steps_per_second": 3.416,
+      "eval_runtime": 12.649,
+      "eval_samples_per_second": 30.912,
+      "eval_steps_per_second": 3.874,
       "step": 912
     },
     {
@@ -112,9 +112,9 @@
       "eval_overall_f1": 0.751588502269289,
       "eval_overall_precision": 0.7280187573270809,
       "eval_overall_recall": 0.776735459662289,
-      "eval_runtime": 14.3162,
-      "eval_samples_per_second": 27.312,
-      "eval_steps_per_second": 3.423,
+      "eval_runtime": 12.6742,
+      "eval_samples_per_second": 30.85,
+      "eval_steps_per_second": 3.866,
       "step": 1140
     },
     {
@@ -122,9 +122,9 @@
       "step": 1140,
       "total_flos": 2383047966228480.0,
       "train_loss": 0.19723336571141292,
-      "train_runtime": 986.049,
-      "train_samples_per_second": 9.249,
-      "train_steps_per_second": 1.156
+      "train_runtime": 917.7763,
+      "train_samples_per_second": 9.937,
+      "train_steps_per_second": 1.242
     }
   ],
   "max_steps": 1140,