End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_km_20_v2_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7034313725490197
+    - name: F1
+      type: f1
+      value: 0.815267175572519
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_20_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2587
-- Accuracy: 0.6863
-- F1: 0.7793
-- Combined Score: 0.7328
+- Loss: 0.6078
+- Accuracy: 0.7034
+- F1: 0.8153
+- Combined Score: 0.7593
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_combined_score": 0.7593492740607694,
     "eval_f1": 0.815267175572519,
     "eval_loss": 0.6078192591667175,
-    "eval_runtime": 0.2942,
+    "eval_runtime": 0.2924,
     "eval_samples": 408,
-    "eval_samples_per_second": 1386.713,
-    "eval_steps_per_second": 6.798,
+    "eval_samples_per_second": 1395.509,
+    "eval_steps_per_second": 6.841,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.36015133233297436,
-    "train_runtime": 57.7393,
+    "train_runtime": 59.2376,
     "train_samples": 3668,
-    "train_samples_per_second": 3176.344,
-    "train_steps_per_second": 12.989
+    "train_samples_per_second": 3096.005,
+    "train_steps_per_second": 12.661
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7593492740607694,
     "eval_f1": 0.815267175572519,
     "eval_loss": 0.6078192591667175,
-    "eval_runtime": 0.2942,
+    "eval_runtime": 0.2924,
     "eval_samples": 408,
-    "eval_samples_per_second": 1386.713,
-    "eval_steps_per_second": 6.798
+    "eval_samples_per_second": 1395.509,
+    "eval_steps_per_second": 6.841
 }

logs/events.out.tfevents.1745398577.s_005_m.2876923.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391e2bee57ddcbf934a1e30b4f280958f37c077f9a2695c4d5c67d70a26d7452
+size 459

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.36015133233297436,
-    "train_runtime": 57.7393,
+    "train_runtime": 59.2376,
     "train_samples": 3668,
-    "train_samples_per_second": 3176.344,
-    "train_steps_per_second": 12.989
+    "train_samples_per_second": 3096.005,
+    "train_steps_per_second": 12.661
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_combined_score": 0.740016030108726,
       "eval_f1": 0.7962085308056872,
       "eval_loss": 0.616814136505127,
-      "eval_runtime": 0.2757,
-      "eval_samples_per_second": 1480.037,
-      "eval_steps_per_second": 7.255,
+      "eval_runtime": 0.2744,
+      "eval_samples_per_second": 1486.649,
+      "eval_steps_per_second": 7.287,
       "step": 15
     },
     {
@@ -40,9 +40,9 @@
       "eval_combined_score": 0.7593492740607694,
       "eval_f1": 0.815267175572519,
       "eval_loss": 0.6078192591667175,
-      "eval_runtime": 0.2689,
-      "eval_samples_per_second": 1517.136,
-      "eval_steps_per_second": 7.437,
+      "eval_runtime": 0.2706,
+      "eval_samples_per_second": 1507.857,
+      "eval_steps_per_second": 7.391,
       "step": 30
     },
     {
@@ -58,9 +58,9 @@
       "eval_combined_score": 0.7530461066215624,
       "eval_f1": 0.805111821086262,
       "eval_loss": 0.6499011516571045,
-      "eval_runtime": 0.2843,
-      "eval_samples_per_second": 1435.076,
-      "eval_steps_per_second": 7.035,
+      "eval_runtime": 0.2726,
+      "eval_samples_per_second": 1496.591,
+      "eval_steps_per_second": 7.336,
       "step": 45
     },
     {
@@ -76,9 +76,9 @@
       "eval_combined_score": 0.7396096088521171,
       "eval_f1": 0.7855917667238422,
       "eval_loss": 0.6939632892608643,
-      "eval_runtime": 0.2783,
-      "eval_samples_per_second": 1466.162,
-      "eval_steps_per_second": 7.187,
+      "eval_runtime": 0.2946,
+      "eval_samples_per_second": 1384.696,
+      "eval_steps_per_second": 6.788,
       "step": 60
     },
     {
@@ -94,9 +94,9 @@
       "eval_combined_score": 0.6798529411764705,
       "eval_f1": 0.72,
       "eval_loss": 0.876370906829834,
-      "eval_runtime": 0.2728,
-      "eval_samples_per_second": 1495.769,
-      "eval_steps_per_second": 7.332,
+      "eval_runtime": 0.2767,
+      "eval_samples_per_second": 1474.695,
+      "eval_steps_per_second": 7.229,
       "step": 75
     },
     {
@@ -112,9 +112,9 @@
       "eval_combined_score": 0.7140350877192982,
       "eval_f1": 0.7614035087719299,
       "eval_loss": 1.1046664714813232,
-      "eval_runtime": 0.2749,
-      "eval_samples_per_second": 1483.97,
-      "eval_steps_per_second": 7.274,
+      "eval_runtime": 0.2943,
+      "eval_samples_per_second": 1386.409,
+      "eval_steps_per_second": 6.796,
       "step": 90
     },
     {
@@ -130,9 +130,9 @@
       "eval_combined_score": 0.7327924273157539,
       "eval_f1": 0.7793103448275862,
       "eval_loss": 1.2587286233901978,
-      "eval_runtime": 0.2835,
-      "eval_samples_per_second": 1439.35,
-      "eval_steps_per_second": 7.056,
+      "eval_runtime": 0.2836,
+      "eval_samples_per_second": 1438.785,
+      "eval_steps_per_second": 7.053,
       "step": 105
     },
     {
@@ -140,9 +140,9 @@
       "step": 105,
       "total_flos": 3377819728711680.0,
       "train_loss": 0.36015133233297436,
-      "train_runtime": 57.7393,
-      "train_samples_per_second": 3176.344,
-      "train_steps_per_second": 12.989
+      "train_runtime": 59.2376,
+      "train_samples_per_second": 3096.005,
+      "train_steps_per_second": 12.661
     }
   ],
   "logging_steps": 1,