End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-bert/bert-base-uncased
 tags:
 - generated_from_trainer
+metrics:
+- f1
 model-index:
 - name: bert-sdg-classification
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-sdg-classification
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7344
+- F1: 0.7900
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.0,
-    "eval_f1": 0.9421819286392854,
-    "eval_loss": 0.3017396032810211,
-    "eval_runtime": 2280.6832,
+    "eval_f1": 0.789972706564468,
+    "eval_loss": 0.7343637943267822,
+    "eval_runtime": 2232.9309,
     "eval_samples": 12908,
-    "eval_samples_per_second": 5.66,
-    "eval_steps_per_second": 0.708,
+    "eval_samples_per_second": 5.781,
+    "eval_steps_per_second": 0.723,
     "total_flos": 2.377533515518771e+16,
-    "train_loss": 0.15210941878937695,
-    "train_runtime": 47350.7748,
+    "train_loss": 1.0759811563350086,
+    "train_runtime": 46811.0436,
     "train_samples": 30117,
-    "train_samples_per_second": 1.908,
+    "train_samples_per_second": 1.93,
     "train_steps_per_second": 0.06
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_f1": 0.9421819286392854,
-    "eval_loss": 0.3017396032810211,
-    "eval_runtime": 2280.6832,
+    "eval_f1": 0.789972706564468,
+    "eval_loss": 0.7343637943267822,
+    "eval_runtime": 2232.9309,
     "eval_samples": 12908,
-    "eval_samples_per_second": 5.66,
-    "eval_steps_per_second": 0.708
+    "eval_samples_per_second": 5.781,
+    "eval_steps_per_second": 0.723
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 2.377533515518771e+16,
-    "train_loss": 0.15210941878937695,
-    "train_runtime": 47350.7748,
+    "train_loss": 1.0759811563350086,
+    "train_runtime": 46811.0436,
     "train_samples": 30117,
-    "train_samples_per_second": 1.908,
+    "train_samples_per_second": 1.93,
     "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -10,46 +10,46 @@
   "log_history": [
     {
       "epoch": 0.5307855626326964,
-      "grad_norm": 3.384657382965088,
+      "grad_norm": 5.489389896392822,
       "learning_rate": 8.333333333333334e-06,
-      "loss": 0.2368,
+      "loss": 2.354,
       "step": 500
     },
     {
       "epoch": 1.0615711252653928,
-      "grad_norm": 10.156657218933105,
+      "grad_norm": 5.129901885986328,
       "learning_rate": 8.203054806828391e-06,
-      "loss": 0.1146,
+      "loss": 1.0543,
       "step": 1000
     },
     {
       "epoch": 1.5923566878980893,
-      "grad_norm": 0.6068603992462158,
+      "grad_norm": 9.780948638916016,
       "learning_rate": 5.9568733153638815e-06,
-      "loss": 0.1799,
+      "loss": 0.8205,
       "step": 1500
     },
     {
       "epoch": 2.1231422505307855,
-      "grad_norm": 6.402149677276611,
+      "grad_norm": 8.44005012512207,
       "learning_rate": 3.710691823899371e-06,
-      "loss": 0.1593,
+      "loss": 0.7534,
       "step": 2000
     },
     {
       "epoch": 2.653927813163482,
-      "grad_norm": 3.010026693344116,
+      "grad_norm": 4.482905387878418,
       "learning_rate": 1.464510332434861e-06,
-      "loss": 0.1031,
+      "loss": 0.6727,
       "step": 2500
     },
     {
       "epoch": 3.0,
       "step": 2826,
       "total_flos": 2.377533515518771e+16,
-      "train_loss": 0.15210941878937695,
-      "train_runtime": 47350.7748,
-      "train_samples_per_second": 1.908,
+      "train_loss": 1.0759811563350086,
+      "train_runtime": 46811.0436,
+      "train_samples_per_second": 1.93,
       "train_steps_per_second": 0.06
     }
   ],