End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_km_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_km_5_v2_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. -->
 
 # tiny_bert_km_5_v2_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v2](https://huggingface.co/Hartunka/tiny_bert_km_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v2](https://huggingface.co/Hartunka/tiny_bert_km_5_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7225
-- Matthews Correlation: 0.0664
-- Accuracy: 0.6433
+- Loss: 0.6132
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -3,14 +3,14 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6132072806358337,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3395,
+    "eval_runtime": 0.35,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3072.424,
-    "eval_steps_per_second": 14.729,
+    "eval_samples_per_second": 2979.605,
+    "eval_steps_per_second": 14.284,
     "total_flos": 1793902531485696.0,
     "train_loss": 0.5503367466085097,
-    "train_runtime": 45.4021,
+    "train_runtime": 46.3757,
     "train_samples": 8551,
-    "train_samples_per_second": 9416.971,
-    "train_steps_per_second": 37.443
+    "train_samples_per_second": 9219.277,
+    "train_steps_per_second": 36.657
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_accuracy": 0.6912751793861389,
     "eval_loss": 0.6132072806358337,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3395,
+    "eval_runtime": 0.35,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3072.424,
-    "eval_steps_per_second": 14.729
+    "eval_samples_per_second": 2979.605,
+    "eval_steps_per_second": 14.284
 }

logs/events.out.tfevents.1745268024.s_005_m.2836625.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806f8964113ce247bcb412364e918fc6c0a8118353cfb0194c4f502ea8078f25
+size 427

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "total_flos": 1793902531485696.0,
     "train_loss": 0.5503367466085097,
-    "train_runtime": 45.4021,
+    "train_runtime": 46.3757,
     "train_samples": 8551,
-    "train_samples_per_second": 9416.971,
-    "train_steps_per_second": 37.443
+    "train_samples_per_second": 9219.277,
+    "train_steps_per_second": 36.657
 }

trainer_state.json

@@ -21,9 +21,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6185938119888306,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.325,
-      "eval_samples_per_second": 3208.865,
-      "eval_steps_per_second": 15.383,
+      "eval_runtime": 0.3261,
+      "eval_samples_per_second": 3198.315,
+      "eval_steps_per_second": 15.332,
       "step": 34
     },
     {
@@ -38,9 +38,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6137447357177734,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3406,
-      "eval_samples_per_second": 3062.365,
-      "eval_steps_per_second": 14.681,
+      "eval_runtime": 0.3136,
+      "eval_samples_per_second": 3326.092,
+      "eval_steps_per_second": 15.945,
       "step": 68
     },
     {
@@ -55,9 +55,9 @@
       "eval_accuracy": 0.6912751793861389,
       "eval_loss": 0.6132072806358337,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3117,
-      "eval_samples_per_second": 3346.424,
-      "eval_steps_per_second": 16.042,
+      "eval_runtime": 0.3328,
+      "eval_samples_per_second": 3134.163,
+      "eval_steps_per_second": 15.025,
       "step": 102
     },
     {
@@ -72,9 +72,9 @@
       "eval_accuracy": 0.6922339200973511,
       "eval_loss": 0.6316416263580322,
       "eval_matthews_correlation": 0.0463559874942472,
-      "eval_runtime": 0.3269,
-      "eval_samples_per_second": 3190.096,
-      "eval_steps_per_second": 15.293,
+      "eval_runtime": 0.3268,
+      "eval_samples_per_second": 3191.404,
+      "eval_steps_per_second": 15.299,
       "step": 136
     },
     {
@@ -89,9 +89,9 @@
       "eval_accuracy": 0.7027804255485535,
       "eval_loss": 0.6342248916625977,
       "eval_matthews_correlation": 0.17712606131822545,
-      "eval_runtime": 0.3079,
-      "eval_samples_per_second": 3387.574,
-      "eval_steps_per_second": 16.24,
+      "eval_runtime": 0.3211,
+      "eval_samples_per_second": 3248.185,
+      "eval_steps_per_second": 15.571,
       "step": 170
     },
     {
@@ -106,9 +106,9 @@
       "eval_accuracy": 0.6318312287330627,
       "eval_loss": 0.6609932780265808,
       "eval_matthews_correlation": 0.08825845093702572,
-      "eval_runtime": 0.3339,
-      "eval_samples_per_second": 3123.819,
-      "eval_steps_per_second": 14.975,
+      "eval_runtime": 0.3814,
+      "eval_samples_per_second": 2734.581,
+      "eval_steps_per_second": 13.109,
       "step": 204
     },
     {
@@ -123,9 +123,9 @@
       "eval_accuracy": 0.6778523325920105,
       "eval_loss": 0.7212586998939514,
       "eval_matthews_correlation": 0.07130170780284954,
-      "eval_runtime": 0.3491,
-      "eval_samples_per_second": 2987.563,
-      "eval_steps_per_second": 14.322,
+      "eval_runtime": 0.3419,
+      "eval_samples_per_second": 3050.928,
+      "eval_steps_per_second": 14.626,
       "step": 238
     },
     {
@@ -140,9 +140,9 @@
       "eval_accuracy": 0.6433365345001221,
       "eval_loss": 0.7225203514099121,
       "eval_matthews_correlation": 0.06635583278930876,
-      "eval_runtime": 0.3177,
-      "eval_samples_per_second": 3283.145,
-      "eval_steps_per_second": 15.739,
+      "eval_runtime": 0.339,
+      "eval_samples_per_second": 3076.588,
+      "eval_steps_per_second": 14.749,
       "step": 272
     },
     {
@@ -150,9 +150,9 @@
       "step": 272,
       "total_flos": 1793902531485696.0,
       "train_loss": 0.5503367466085097,
-      "train_runtime": 45.4021,
-      "train_samples_per_second": 9416.971,
-      "train_steps_per_second": 37.443
+      "train_runtime": 46.3757,
+      "train_samples_per_second": 9219.277,
+      "train_steps_per_second": 36.657
     }
   ],
   "logging_steps": 1,