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:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_km_50_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_50_v1_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8469
-- Matthews Correlation: 0.0852
-- Accuracy: 0.6424
+- Loss: 0.6189
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6189477443695068,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.7085,
+    "eval_runtime": 0.682,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1472.162,
-    "eval_steps_per_second": 7.057,
+    "eval_samples_per_second": 1529.234,
+    "eval_steps_per_second": 7.331,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.5067869074204389,
-    "train_runtime": 98.7528,
+    "train_runtime": 102.5188,
     "train_samples": 8551,
-    "train_samples_per_second": 4329.496,
-    "train_steps_per_second": 17.215
+    "train_samples_per_second": 4170.455,
+    "train_steps_per_second": 16.582
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6189477443695068,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.7085,
+    "eval_runtime": 0.682,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1472.162,
-    "eval_steps_per_second": 7.057
+    "eval_samples_per_second": 1529.234,
+    "eval_steps_per_second": 7.331
 }

logs/events.out.tfevents.1745080054.s_005_m.2793776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73825a8ae916933c150b77be680b330a576c2a7ffeb041f34e8dcc65b7e0c38c
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.5067869074204389,
-    "train_runtime": 98.7528,
+    "train_runtime": 102.5188,
     "train_samples": 8551,
-    "train_samples_per_second": 4329.496,
-    "train_steps_per_second": 17.215
+    "train_samples_per_second": 4170.455,
+    "train_steps_per_second": 16.582
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6189477443695068,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6591,
-      "eval_samples_per_second": 1582.419,
-      "eval_steps_per_second": 7.586,
+      "eval_runtime": 0.6736,
+      "eval_samples_per_second": 1548.296,
+      "eval_steps_per_second": 7.422,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.693192720413208,
       "eval_loss": 0.6232299208641052,
       "eval_matthews_correlation": 0.0592680243795702,
-      "eval_runtime": 0.6914,
-      "eval_samples_per_second": 1508.436,
-      "eval_steps_per_second": 7.231,
+      "eval_runtime": 0.6773,
+      "eval_samples_per_second": 1540.051,
+      "eval_steps_per_second": 7.383,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6605944633483887,
       "eval_loss": 0.6374881267547607,
       "eval_matthews_correlation": -0.0024323816012785963,
-      "eval_runtime": 0.7006,
-      "eval_samples_per_second": 1488.738,
-      "eval_steps_per_second": 7.137,
+      "eval_runtime": 0.7278,
+      "eval_samples_per_second": 1433.044,
+      "eval_steps_per_second": 6.87,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.6711409687995911,
       "eval_loss": 0.6979495882987976,
       "eval_matthews_correlation": 0.05755092158161861,
-      "eval_runtime": 0.6955,
-      "eval_samples_per_second": 1499.697,
-      "eval_steps_per_second": 7.189,
+      "eval_runtime": 0.6758,
+      "eval_samples_per_second": 1543.421,
+      "eval_steps_per_second": 7.399,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6558005809783936,
       "eval_loss": 0.7205694913864136,
       "eval_matthews_correlation": 0.11450544212711358,
-      "eval_runtime": 0.673,
-      "eval_samples_per_second": 1549.858,
-      "eval_steps_per_second": 7.43,
+      "eval_runtime": 0.6773,
+      "eval_samples_per_second": 1539.872,
+      "eval_steps_per_second": 7.382,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6423777341842651,
       "eval_loss": 0.8469471335411072,
       "eval_matthews_correlation": 0.08517981300248055,
-      "eval_runtime": 0.7073,
-      "eval_samples_per_second": 1474.532,
-      "eval_steps_per_second": 7.069,
+      "eval_runtime": 0.6819,
+      "eval_samples_per_second": 1529.601,
+      "eval_steps_per_second": 7.333,
       "step": 204
     },
     {
@@ -116,9 +116,9 @@
       "step": 204,
       "total_flos": 6749587903150080.0,
       "train_loss": 0.5067869074204389,
-      "train_runtime": 98.7528,
-      "train_samples_per_second": 4329.496,
-      "train_steps_per_second": 17.215
+      "train_runtime": 102.5188,
+      "train_samples_per_second": 4170.455,
+      "train_steps_per_second": 16.582
     }
   ],
   "logging_steps": 1,