End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- id
 license: mit
 base_model: indolem/indobert-base-uncased
 tags:

all_results.json

@@ -17,10 +17,10 @@
     "eval_overall_f1": 0.9622166246851386,
     "eval_overall_precision": 0.9646464646464646,
     "eval_overall_recall": 0.9597989949748744,
-    "eval_runtime": 1.1963,
+    "eval_runtime": 0.675,
     "eval_samples": 170,
-    "eval_samples_per_second": 142.108,
-    "eval_steps_per_second": 2.508,
+    "eval_samples_per_second": 251.849,
+    "eval_steps_per_second": 4.444,
     "predict_LOCATION_f1": 0.9771309771309771,
     "predict_LOCATION_number": 237,
     "predict_LOCATION_precision": 0.9631147540983607,
@@ -38,12 +38,12 @@
     "predict_overall_f1": 0.987012987012987,
     "predict_overall_precision": 0.9865384615384616,
     "predict_overall_recall": 0.987487969201155,
-    "predict_runtime": 3.6213,
-    "predict_samples_per_second": 117.362,
-    "predict_steps_per_second": 1.933,
+    "predict_runtime": 1.7615,
+    "predict_samples_per_second": 241.266,
+    "predict_steps_per_second": 3.974,
     "train_loss": 0.07880291553835074,
-    "train_runtime": 223.1323,
+    "train_runtime": 118.8792,
     "train_samples": 1531,
-    "train_samples_per_second": 34.307,
-    "train_steps_per_second": 2.151
+    "train_samples_per_second": 64.393,
+    "train_steps_per_second": 4.038
 }

eval_results.json

@@ -17,8 +17,8 @@
     "eval_overall_f1": 0.9622166246851386,
     "eval_overall_precision": 0.9646464646464646,
     "eval_overall_recall": 0.9597989949748744,
-    "eval_runtime": 1.1963,
+    "eval_runtime": 0.675,
     "eval_samples": 170,
-    "eval_samples_per_second": 142.108,
-    "eval_steps_per_second": 2.508
+    "eval_samples_per_second": 251.849,
+    "eval_steps_per_second": 4.444
 }

predict_results.json

@@ -16,7 +16,7 @@
     "predict_overall_f1": 0.987012987012987,
     "predict_overall_precision": 0.9865384615384616,
     "predict_overall_recall": 0.987487969201155,
-    "predict_runtime": 3.6213,
-    "predict_samples_per_second": 117.362,
-    "predict_steps_per_second": 1.933
+    "predict_runtime": 1.7615,
+    "predict_samples_per_second": 241.266,
+    "predict_steps_per_second": 3.974
 }

runs/May28_20-19-04_indolem-petl-vm/events.out.tfevents.1716927686.indolem-petl-vm.225100.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191415ea2b42fdeba14d354d3e8da3e998554a4b9ffa10c4e7489a5f05d1def1
+size 1305

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "train_loss": 0.07880291553835074,
-    "train_runtime": 223.1323,
+    "train_runtime": 118.8792,
     "train_samples": 1531,
-    "train_samples_per_second": 34.307,
-    "train_steps_per_second": 2.151
+    "train_samples_per_second": 64.393,
+    "train_steps_per_second": 4.038
 }

trainer_state.json

@@ -34,9 +34,9 @@
       "eval_overall_f1": 0.9354838709677419,
       "eval_overall_precision": 0.9240196078431373,
       "eval_overall_recall": 0.9472361809045227,
-      "eval_runtime": 1.2222,
-      "eval_samples_per_second": 139.096,
-      "eval_steps_per_second": 2.455,
+      "eval_runtime": 0.5823,
+      "eval_samples_per_second": 291.947,
+      "eval_steps_per_second": 5.152,
       "step": 96
     },
     {
@@ -65,9 +65,9 @@
       "eval_overall_f1": 0.9584905660377357,
       "eval_overall_precision": 0.9596977329974811,
       "eval_overall_recall": 0.957286432160804,
-      "eval_runtime": 1.2555,
-      "eval_samples_per_second": 135.404,
-      "eval_steps_per_second": 2.389,
+      "eval_runtime": 0.5986,
+      "eval_samples_per_second": 283.986,
+      "eval_steps_per_second": 5.012,
       "step": 192
     },
     {
@@ -96,9 +96,9 @@
       "eval_overall_f1": 0.9525,
       "eval_overall_precision": 0.9477611940298507,
       "eval_overall_recall": 0.957286432160804,
-      "eval_runtime": 1.1959,
-      "eval_samples_per_second": 142.158,
-      "eval_steps_per_second": 2.509,
+      "eval_runtime": 0.6639,
+      "eval_samples_per_second": 256.046,
+      "eval_steps_per_second": 4.518,
       "step": 288
     },
     {
@@ -127,9 +127,9 @@
       "eval_overall_f1": 0.957286432160804,
       "eval_overall_precision": 0.957286432160804,
       "eval_overall_recall": 0.957286432160804,
-      "eval_runtime": 1.2864,
-      "eval_samples_per_second": 132.147,
-      "eval_steps_per_second": 2.332,
+      "eval_runtime": 0.6313,
+      "eval_samples_per_second": 269.277,
+      "eval_steps_per_second": 4.752,
       "step": 384
     },
     {
@@ -158,9 +158,9 @@
       "eval_overall_f1": 0.9622166246851386,
       "eval_overall_precision": 0.9646464646464646,
       "eval_overall_recall": 0.9597989949748744,
-      "eval_runtime": 1.2628,
-      "eval_samples_per_second": 134.623,
-      "eval_steps_per_second": 2.376,
+      "eval_runtime": 0.6158,
+      "eval_samples_per_second": 276.053,
+      "eval_steps_per_second": 4.872,
       "step": 480
     },
     {
@@ -168,9 +168,9 @@
       "step": 480,
       "total_flos": 192923809958682.0,
       "train_loss": 0.07880291553835074,
-      "train_runtime": 223.1323,
-      "train_samples_per_second": 34.307,
-      "train_steps_per_second": 2.151
+      "train_runtime": 118.8792,
+      "train_samples_per_second": 64.393,
+      "train_steps_per_second": 4.038
     }
   ],
   "logging_steps": 500,