End of training

README.md

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

all_results.json

@@ -5,21 +5,21 @@
     "eval_loss": 0.15753257274627686,
     "eval_precision": 0.776536312849162,
     "eval_recall": 0.8884369552585706,
-    "eval_runtime": 5.2653,
+    "eval_runtime": 5.4104,
     "eval_samples": 935,
-    "eval_samples_per_second": 177.577,
-    "eval_steps_per_second": 2.849,
+    "eval_samples_per_second": 172.815,
+    "eval_steps_per_second": 2.772,
     "predict_accuracy": 0.9876279863481229,
     "predict_f1": 0.9276586033774533,
     "predict_loss": 0.04439631476998329,
     "predict_precision": 0.9009308510638298,
     "predict_recall": 0.9560206961429916,
-    "predict_runtime": 12.1307,
-    "predict_samples_per_second": 193.146,
-    "predict_steps_per_second": 3.05,
+    "predict_runtime": 12.6513,
+    "predict_samples_per_second": 185.198,
+    "predict_steps_per_second": 2.925,
     "train_loss": 0.2260448426911325,
-    "train_runtime": 121.6263,
+    "train_runtime": 127.3009,
     "train_samples": 8437,
-    "train_samples_per_second": 69.368,
-    "train_steps_per_second": 4.341
+    "train_samples_per_second": 66.276,
+    "train_steps_per_second": 4.148
 }

eval_results.json

@@ -5,8 +5,8 @@
     "eval_loss": 0.15753257274627686,
     "eval_precision": 0.776536312849162,
     "eval_recall": 0.8884369552585706,
-    "eval_runtime": 5.2653,
+    "eval_runtime": 5.4104,
     "eval_samples": 935,
-    "eval_samples_per_second": 177.577,
-    "eval_steps_per_second": 2.849
+    "eval_samples_per_second": 172.815,
+    "eval_steps_per_second": 2.772
 }

predict_results.json

@@ -4,7 +4,7 @@
     "predict_loss": 0.04439631476998329,
     "predict_precision": 0.9009308510638298,
     "predict_recall": 0.9560206961429916,
-    "predict_runtime": 12.1307,
-    "predict_samples_per_second": 193.146,
-    "predict_steps_per_second": 3.05
+    "predict_runtime": 12.6513,
+    "predict_samples_per_second": 185.198,
+    "predict_steps_per_second": 2.925
 }

runs/May24_14-26-31_indolem-petl-vm/events.out.tfevents.1716560944.indolem-petl-vm.1460180.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b146104fd6e8fc200a7e6a04dc72c1161a88d0aa134ff7e60d38145b10c8e91
+size 560

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.2260448426911325,
-    "train_runtime": 121.6263,
+    "train_runtime": 127.3009,
     "train_samples": 8437,
-    "train_samples_per_second": 69.368,
-    "train_steps_per_second": 4.341
+    "train_samples_per_second": 66.276,
+    "train_steps_per_second": 4.148
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_loss": 0.15753257274627686,
       "eval_precision": 0.776536312849162,
       "eval_recall": 0.8884369552585706,
-      "eval_runtime": 5.3398,
-      "eval_samples_per_second": 175.101,
-      "eval_steps_per_second": 2.809,
+      "eval_runtime": 5.4112,
+      "eval_samples_per_second": 172.791,
+      "eval_steps_per_second": 2.772,
       "step": 528
     },
     {
@@ -32,9 +32,9 @@
       "step": 528,
       "total_flos": 230610745968444.0,
       "train_loss": 0.2260448426911325,
-      "train_runtime": 121.6263,
-      "train_samples_per_second": 69.368,
-      "train_steps_per_second": 4.341
+      "train_runtime": 127.3009,
+      "train_samples_per_second": 66.276,
+      "train_steps_per_second": 4.148
     }
   ],
   "logging_steps": 500,