End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_km_20_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_20_v1_cola
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8696
-- Matthews Correlation: 0.0963
-- Accuracy: 0.6366
+- Loss: 0.6226
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6225768327713013,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6888,
+    "eval_runtime": 0.6754,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1514.181,
-    "eval_steps_per_second": 7.259,
+    "eval_samples_per_second": 1544.329,
+    "eval_steps_per_second": 7.403,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.484881274840411,
-    "train_runtime": 99.6839,
+    "train_runtime": 101.9729,
     "train_samples": 8551,
-    "train_samples_per_second": 4289.056,
-    "train_steps_per_second": 17.054
+    "train_samples_per_second": 4192.78,
+    "train_steps_per_second": 16.671
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6225768327713013,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6888,
+    "eval_runtime": 0.6754,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1514.181,
-    "eval_steps_per_second": 7.259
+    "eval_samples_per_second": 1544.329,
+    "eval_steps_per_second": 7.403
 }

logs/events.out.tfevents.1745044145.s_005_m.2788007.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d068924ea3c00b2e583ccc949e632706f205f304ed22e20bfb28aca9d38824
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 6749587903150080.0,
     "train_loss": 0.484881274840411,
-    "train_runtime": 99.6839,
+    "train_runtime": 101.9729,
     "train_samples": 8551,
-    "train_samples_per_second": 4289.056,
-    "train_steps_per_second": 17.054
+    "train_samples_per_second": 4192.78,
+    "train_steps_per_second": 16.671
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6225768327713013,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7082,
-      "eval_samples_per_second": 1472.699,
-      "eval_steps_per_second": 7.06,
+      "eval_runtime": 0.6878,
+      "eval_samples_per_second": 1516.325,
+      "eval_steps_per_second": 7.269,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6893576383590698,
       "eval_loss": 0.6297030448913574,
       "eval_matthews_correlation": 0.07656947466775693,
-      "eval_runtime": 0.6837,
-      "eval_samples_per_second": 1525.417,
-      "eval_steps_per_second": 7.313,
+      "eval_runtime": 0.675,
+      "eval_samples_per_second": 1545.239,
+      "eval_steps_per_second": 7.408,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6797698736190796,
       "eval_loss": 0.6300162076950073,
       "eval_matthews_correlation": 0.08088406701239864,
-      "eval_runtime": 0.6712,
-      "eval_samples_per_second": 1553.855,
-      "eval_steps_per_second": 7.449,
+      "eval_runtime": 0.6962,
+      "eval_samples_per_second": 1498.188,
+      "eval_steps_per_second": 7.182,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.6519654989242554,
       "eval_loss": 0.6926795244216919,
       "eval_matthews_correlation": 0.14975092131840292,
-      "eval_runtime": 0.6975,
-      "eval_samples_per_second": 1495.386,
-      "eval_steps_per_second": 7.169,
+      "eval_runtime": 0.6643,
+      "eval_samples_per_second": 1570.163,
+      "eval_steps_per_second": 7.527,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.6567593216896057,
       "eval_loss": 0.7553606033325195,
       "eval_matthews_correlation": 0.09193331749307261,
-      "eval_runtime": 0.6706,
-      "eval_samples_per_second": 1555.292,
-      "eval_steps_per_second": 7.456,
+      "eval_runtime": 0.6983,
+      "eval_samples_per_second": 1493.613,
+      "eval_steps_per_second": 7.16,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6366251111030579,
       "eval_loss": 0.8696136474609375,
       "eval_matthews_correlation": 0.09631786888423775,
-      "eval_runtime": 0.6847,
-      "eval_samples_per_second": 1523.185,
-      "eval_steps_per_second": 7.302,
+      "eval_runtime": 0.6804,
+      "eval_samples_per_second": 1532.842,
+      "eval_steps_per_second": 7.348,
       "step": 204
     },
     {
@@ -116,9 +116,9 @@
       "step": 204,
       "total_flos": 6749587903150080.0,
       "train_loss": 0.484881274840411,
-      "train_runtime": 99.6839,
-      "train_samples_per_second": 4289.056,
-      "train_steps_per_second": 17.054
+      "train_runtime": 101.9729,
+      "train_samples_per_second": 4192.78,
+      "train_steps_per_second": 16.671
     }
   ],
   "logging_steps": 1,