End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_km_20_v1_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.39436619718309857
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_20_v1_wnli
 
-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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8994
-- Accuracy: 0.1690
+- Loss: 0.7542
+- Accuracy: 0.3944
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 6.0,
     "eval_accuracy": 0.39436619718309857,
     "eval_loss": 0.7541812658309937,
-    "eval_runtime": 0.0745,
+    "eval_runtime": 0.0757,
     "eval_samples": 71,
-    "eval_samples_per_second": 953.089,
-    "eval_steps_per_second": 13.424,
+    "eval_samples_per_second": 938.137,
+    "eval_steps_per_second": 13.213,
     "total_flos": 501226560460800.0,
     "train_loss": 0.6963877810372247,
-    "train_runtime": 18.5769,
+    "train_runtime": 19.3347,
     "train_samples": 635,
-    "train_samples_per_second": 1709.111,
-    "train_steps_per_second": 8.075
+    "train_samples_per_second": 1642.129,
+    "train_steps_per_second": 7.758
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "eval_accuracy": 0.39436619718309857,
     "eval_loss": 0.7541812658309937,
-    "eval_runtime": 0.0745,
+    "eval_runtime": 0.0757,
     "eval_samples": 71,
-    "eval_samples_per_second": 953.089,
-    "eval_steps_per_second": 13.424
+    "eval_samples_per_second": 938.137,
+    "eval_steps_per_second": 13.213
 }

logs/events.out.tfevents.1745050805.s_005_m.2788007.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6aa7cd78e589c0e2a2b7d8bd2b2c4e4e0143bf9fb8ddc83757ce0da5f0cf40
+size 357

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 501226560460800.0,
     "train_loss": 0.6963877810372247,
-    "train_runtime": 18.5769,
+    "train_runtime": 19.3347,
     "train_samples": 635,
-    "train_samples_per_second": 1709.111,
-    "train_steps_per_second": 8.075
+    "train_samples_per_second": 1642.129,
+    "train_steps_per_second": 7.758
 }

trainer_state.json

@@ -20,9 +20,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.39436619718309857,
       "eval_loss": 0.7541812658309937,
-      "eval_runtime": 0.0584,
-      "eval_samples_per_second": 1215.398,
-      "eval_steps_per_second": 17.118,
+      "eval_runtime": 0.0818,
+      "eval_samples_per_second": 868.221,
+      "eval_steps_per_second": 12.228,
       "step": 3
     },
     {
@@ -36,9 +36,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.2112676056338028,
       "eval_loss": 0.7640296220779419,
-      "eval_runtime": 0.0644,
-      "eval_samples_per_second": 1101.727,
-      "eval_steps_per_second": 15.517,
+      "eval_runtime": 0.0608,
+      "eval_samples_per_second": 1166.879,
+      "eval_steps_per_second": 16.435,
       "step": 6
     },
     {
@@ -52,9 +52,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.22535211267605634,
       "eval_loss": 0.7914281487464905,
-      "eval_runtime": 0.0545,
-      "eval_samples_per_second": 1303.617,
-      "eval_steps_per_second": 18.361,
+      "eval_runtime": 0.0568,
+      "eval_samples_per_second": 1250.685,
+      "eval_steps_per_second": 17.615,
       "step": 9
     },
     {
@@ -68,9 +68,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.2676056338028169,
       "eval_loss": 0.814260721206665,
-      "eval_runtime": 0.0691,
-      "eval_samples_per_second": 1028.222,
-      "eval_steps_per_second": 14.482,
+      "eval_runtime": 0.0573,
+      "eval_samples_per_second": 1238.364,
+      "eval_steps_per_second": 17.442,
       "step": 12
     },
     {
@@ -84,9 +84,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.2112676056338028,
       "eval_loss": 0.8581647872924805,
-      "eval_runtime": 0.0555,
-      "eval_samples_per_second": 1279.597,
-      "eval_steps_per_second": 18.022,
+      "eval_runtime": 0.0598,
+      "eval_samples_per_second": 1187.52,
+      "eval_steps_per_second": 16.726,
       "step": 15
     },
     {
@@ -100,9 +100,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.16901408450704225,
       "eval_loss": 0.8994279503822327,
-      "eval_runtime": 0.0558,
-      "eval_samples_per_second": 1272.37,
-      "eval_steps_per_second": 17.921,
+      "eval_runtime": 0.0623,
+      "eval_samples_per_second": 1138.876,
+      "eval_steps_per_second": 16.041,
       "step": 18
     },
     {
@@ -110,9 +110,9 @@
       "step": 18,
       "total_flos": 501226560460800.0,
       "train_loss": 0.6963877810372247,
-      "train_runtime": 18.5769,
-      "train_samples_per_second": 1709.111,
-      "train_steps_per_second": 8.075
+      "train_runtime": 19.3347,
+      "train_samples_per_second": 1642.129,
+      "train_steps_per_second": 7.758
     }
   ],
   "logging_steps": 1,