End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_km_50_v1_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: 0.8141321044546851
 ---
 
 <!-- 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_50_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1340
-- Accuracy: 0.6593
-- F1: 0.7531
-- Combined Score: 0.7062
+- Loss: 0.5894
+- Accuracy: 0.7034
+- F1: 0.8141
+- Combined Score: 0.7588
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_combined_score": 0.7587817385018524,
     "eval_f1": 0.8141321044546851,
     "eval_loss": 0.5893518924713135,
-    "eval_runtime": 0.3351,
+    "eval_runtime": 0.2812,
     "eval_samples": 408,
-    "eval_samples_per_second": 1217.397,
-    "eval_steps_per_second": 5.968,
+    "eval_samples_per_second": 1450.71,
+    "eval_steps_per_second": 7.111,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.37630167575109574,
-    "train_runtime": 57.9107,
+    "train_runtime": 59.1897,
     "train_samples": 3668,
-    "train_samples_per_second": 3166.945,
-    "train_steps_per_second": 12.951
+    "train_samples_per_second": 3098.514,
+    "train_steps_per_second": 12.671
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7587817385018524,
     "eval_f1": 0.8141321044546851,
     "eval_loss": 0.5893518924713135,
-    "eval_runtime": 0.3351,
+    "eval_runtime": 0.2812,
     "eval_samples": 408,
-    "eval_samples_per_second": 1217.397,
-    "eval_steps_per_second": 5.968
+    "eval_samples_per_second": 1450.71,
+    "eval_steps_per_second": 7.111
 }

logs/events.out.tfevents.1745080139.s_005_m.2793776.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44220412ad73cbe3e83ab521deda94ba749ef4b328479a63f55ce4e777284268
+size 459

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.37630167575109574,
-    "train_runtime": 57.9107,
+    "train_runtime": 59.1897,
     "train_samples": 3668,
-    "train_samples_per_second": 3166.945,
-    "train_steps_per_second": 12.951
+    "train_samples_per_second": 3098.514,
+    "train_steps_per_second": 12.671
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_combined_score": 0.7452987825395369,
       "eval_f1": 0.8018720748829953,
       "eval_loss": 0.5977591872215271,
-      "eval_runtime": 0.2702,
-      "eval_samples_per_second": 1509.746,
-      "eval_steps_per_second": 7.401,
+      "eval_runtime": 0.2815,
+      "eval_samples_per_second": 1449.507,
+      "eval_steps_per_second": 7.105,
       "step": 15
     },
     {
@@ -40,9 +40,9 @@
       "eval_combined_score": 0.7587817385018524,
       "eval_f1": 0.8141321044546851,
       "eval_loss": 0.5893518924713135,
-      "eval_runtime": 0.2724,
-      "eval_samples_per_second": 1497.989,
-      "eval_steps_per_second": 7.343,
+      "eval_runtime": 0.2759,
+      "eval_samples_per_second": 1478.916,
+      "eval_steps_per_second": 7.25,
       "step": 30
     },
     {
@@ -58,9 +58,9 @@
       "eval_combined_score": 0.7552244582043344,
       "eval_f1": 0.8070175438596491,
       "eval_loss": 0.6016624569892883,
-      "eval_runtime": 0.2763,
-      "eval_samples_per_second": 1476.67,
-      "eval_steps_per_second": 7.239,
+      "eval_runtime": 0.2708,
+      "eval_samples_per_second": 1506.861,
+      "eval_steps_per_second": 7.387,
       "step": 45
     },
     {
@@ -76,9 +76,9 @@
       "eval_combined_score": 0.737373677185623,
       "eval_f1": 0.7909238249594813,
       "eval_loss": 0.6796642541885376,
-      "eval_runtime": 0.2698,
-      "eval_samples_per_second": 1512.03,
-      "eval_steps_per_second": 7.412,
+      "eval_runtime": 0.2782,
+      "eval_samples_per_second": 1466.576,
+      "eval_steps_per_second": 7.189,
       "step": 60
     },
     {
@@ -94,9 +94,9 @@
       "eval_combined_score": 0.6872946105816629,
       "eval_f1": 0.7299813780260708,
       "eval_loss": 0.8248001337051392,
-      "eval_runtime": 0.3065,
-      "eval_samples_per_second": 1331.354,
-      "eval_steps_per_second": 6.526,
+      "eval_runtime": 0.2776,
+      "eval_samples_per_second": 1469.566,
+      "eval_steps_per_second": 7.204,
       "step": 75
     },
     {
@@ -112,9 +112,9 @@
       "eval_combined_score": 0.6659663865546219,
       "eval_f1": 0.7142857142857143,
       "eval_loss": 1.088710904121399,
-      "eval_runtime": 0.2777,
-      "eval_samples_per_second": 1469.065,
-      "eval_steps_per_second": 7.201,
+      "eval_runtime": 0.2704,
+      "eval_samples_per_second": 1509.018,
+      "eval_steps_per_second": 7.397,
       "step": 90
     },
     {
@@ -130,9 +130,9 @@
       "eval_combined_score": 0.7062110368125936,
       "eval_f1": 0.7531083481349912,
       "eval_loss": 1.1340426206588745,
-      "eval_runtime": 0.2695,
-      "eval_samples_per_second": 1514.054,
-      "eval_steps_per_second": 7.422,
+      "eval_runtime": 0.2846,
+      "eval_samples_per_second": 1433.362,
+      "eval_steps_per_second": 7.026,
       "step": 105
     },
     {
@@ -140,9 +140,9 @@
       "step": 105,
       "total_flos": 3377819728711680.0,
       "train_loss": 0.37630167575109574,
-      "train_runtime": 57.9107,
-      "train_samples_per_second": 3166.945,
-      "train_steps_per_second": 12.951
+      "train_runtime": 59.1897,
+      "train_samples_per_second": 3098.514,
+      "train_steps_per_second": 12.671
     }
   ],
   "logging_steps": 1,