End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_10_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_km_10_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_10_v1_cola
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_10_v1](https://huggingface.co/Hartunka/bert_base_km_10_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_10_v1](https://huggingface.co/Hartunka/bert_base_km_10_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8679
-- Matthews Correlation: 0.0665
-- Accuracy: 0.6500
+- Loss: 0.6211
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6210572123527527,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.704,
+    "eval_runtime": 0.6904,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1481.629,
-    "eval_steps_per_second": 7.103,
+    "eval_samples_per_second": 1510.621,
+    "eval_steps_per_second": 7.242,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.4883236604578355,
-    "train_runtime": 100.2774,
+    "train_runtime": 100.3492,
     "train_samples": 8551,
-    "train_samples_per_second": 4263.674,
-    "train_steps_per_second": 16.953
+    "train_samples_per_second": 4260.621,
+    "train_steps_per_second": 16.941
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6210572123527527,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.704,
+    "eval_runtime": 0.6904,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1481.629,
-    "eval_steps_per_second": 7.103
+    "eval_samples_per_second": 1510.621,
+    "eval_steps_per_second": 7.242
 }

logs/events.out.tfevents.1745015797.s_005_m.2780655.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625e8401de6e8ec78cc72af50e4f82080764dec1277966a17be64663ad93d557
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.4883236604578355,
-    "train_runtime": 100.2774,
+    "train_runtime": 100.3492,
     "train_samples": 8551,
-    "train_samples_per_second": 4263.674,
-    "train_steps_per_second": 16.953
+    "train_samples_per_second": 4260.621,
+    "train_steps_per_second": 16.941
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6210572123527527,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6731,
-      "eval_samples_per_second": 1549.445,
-      "eval_steps_per_second": 7.428,
+      "eval_runtime": 0.6785,
+      "eval_samples_per_second": 1537.293,
+      "eval_steps_per_second": 7.37,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6874400973320007,
       "eval_loss": 0.6245772838592529,
       "eval_matthews_correlation": 0.08020927197111564,
-      "eval_runtime": 0.7164,
-      "eval_samples_per_second": 1455.858,
-      "eval_steps_per_second": 6.979,
+      "eval_runtime": 0.667,
+      "eval_samples_per_second": 1563.696,
+      "eval_steps_per_second": 7.496,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6845637559890747,
       "eval_loss": 0.6238712668418884,
       "eval_matthews_correlation": 0.08097785992490644,
-      "eval_runtime": 0.6793,
-      "eval_samples_per_second": 1535.443,
-      "eval_steps_per_second": 7.361,
+      "eval_runtime": 0.6925,
+      "eval_samples_per_second": 1506.101,
+      "eval_steps_per_second": 7.22,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.6596356630325317,
       "eval_loss": 0.7118160724639893,
       "eval_matthews_correlation": 0.09763740948697848,
-      "eval_runtime": 0.7261,
-      "eval_samples_per_second": 1436.398,
-      "eval_steps_per_second": 6.886,
+      "eval_runtime": 0.6731,
+      "eval_samples_per_second": 1549.438,
+      "eval_steps_per_second": 7.428,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6356663703918457,
       "eval_loss": 0.7543103098869324,
       "eval_matthews_correlation": 0.07673140340421428,
-      "eval_runtime": 0.6902,
-      "eval_samples_per_second": 1511.249,
-      "eval_steps_per_second": 7.245,
+      "eval_runtime": 0.6703,
+      "eval_samples_per_second": 1556.031,
+      "eval_steps_per_second": 7.459,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6500479578971863,
       "eval_loss": 0.867901086807251,
       "eval_matthews_correlation": 0.06649950842111448,
-      "eval_runtime": 0.6833,
-      "eval_samples_per_second": 1526.422,
-      "eval_steps_per_second": 7.317,
+      "eval_runtime": 0.6864,
+      "eval_samples_per_second": 1519.507,
+      "eval_steps_per_second": 7.284,
       "step": 204
     },
     {
@@ -116,9 +116,9 @@
       "step": 204,
       "total_flos": 6749587903150080.0,
       "train_loss": 0.4883236604578355,
-      "train_runtime": 100.2774,
-      "train_samples_per_second": 4263.674,
-      "train_steps_per_second": 16.953
+      "train_runtime": 100.3492,
+      "train_samples_per_second": 4260.621,
+      "train_steps_per_second": 16.941
     }
   ],
   "logging_steps": 1,