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_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8084862385321101
 ---
 
 <!-- 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_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9019
-- Accuracy: 0.7798
+- Loss: 0.4363
+- Accuracy: 0.8085
 
 ## Model description
 

all_results.json

@@ -2,14 +2,14 @@
     "epoch": 6.0,
     "eval_accuracy": 0.8084862385321101,
     "eval_loss": 0.4363076388835907,
-    "eval_runtime": 0.5773,
+    "eval_runtime": 0.5981,
     "eval_samples": 872,
-    "eval_samples_per_second": 1510.453,
-    "eval_steps_per_second": 6.929,
+    "eval_samples_per_second": 1457.961,
+    "eval_steps_per_second": 6.688,
     "total_flos": 5.316079940232192e+16,
     "train_loss": 0.17508280758905892,
-    "train_runtime": 660.7862,
+    "train_runtime": 659.8178,
     "train_samples": 67349,
-    "train_samples_per_second": 5096.126,
-    "train_steps_per_second": 19.976
+    "train_samples_per_second": 5103.606,
+    "train_steps_per_second": 20.006
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "eval_accuracy": 0.8084862385321101,
     "eval_loss": 0.4363076388835907,
-    "eval_runtime": 0.5773,
+    "eval_runtime": 0.5981,
     "eval_samples": 872,
-    "eval_samples_per_second": 1510.453,
-    "eval_steps_per_second": 6.929
+    "eval_samples_per_second": 1457.961,
+    "eval_steps_per_second": 6.688
 }

logs/events.out.tfevents.1745050623.s_005_m.2788007.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406fea1d8ee866e1ca0fa78daf3f1592b9aff0a532a243eeb6b8c4518fffd66b
+size 363

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "total_flos": 5.316079940232192e+16,
     "train_loss": 0.17508280758905892,
-    "train_runtime": 660.7862,
+    "train_runtime": 659.8178,
     "train_samples": 67349,
-    "train_samples_per_second": 5096.126,
-    "train_steps_per_second": 19.976
+    "train_samples_per_second": 5103.606,
+    "train_steps_per_second": 20.006
 }

trainer_state.json

@@ -20,9 +20,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.8084862385321101,
       "eval_loss": 0.4363076388835907,
-      "eval_runtime": 0.5636,
-      "eval_samples_per_second": 1547.325,
-      "eval_steps_per_second": 7.098,
+      "eval_runtime": 0.5669,
+      "eval_samples_per_second": 1538.269,
+      "eval_steps_per_second": 7.056,
       "step": 264
     },
     {
@@ -36,9 +36,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.8027522935779816,
       "eval_loss": 0.5351740121841431,
-      "eval_runtime": 0.5563,
-      "eval_samples_per_second": 1567.611,
-      "eval_steps_per_second": 7.191,
+      "eval_runtime": 0.5619,
+      "eval_samples_per_second": 1551.884,
+      "eval_steps_per_second": 7.119,
       "step": 528
     },
     {
@@ -52,9 +52,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.7981651376146789,
       "eval_loss": 0.7095787525177002,
-      "eval_runtime": 0.5568,
-      "eval_samples_per_second": 1566.163,
-      "eval_steps_per_second": 7.184,
+      "eval_runtime": 0.5629,
+      "eval_samples_per_second": 1549.196,
+      "eval_steps_per_second": 7.106,
       "step": 792
     },
     {
@@ -68,9 +68,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.7981651376146789,
       "eval_loss": 0.5919294953346252,
-      "eval_runtime": 0.5813,
-      "eval_samples_per_second": 1500.171,
-      "eval_steps_per_second": 6.882,
+      "eval_runtime": 0.5621,
+      "eval_samples_per_second": 1551.216,
+      "eval_steps_per_second": 7.116,
       "step": 1056
     },
     {
@@ -84,9 +84,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.783256880733945,
       "eval_loss": 0.7547828555107117,
-      "eval_runtime": 0.557,
-      "eval_samples_per_second": 1565.462,
-      "eval_steps_per_second": 7.181,
+      "eval_runtime": 0.5846,
+      "eval_samples_per_second": 1491.658,
+      "eval_steps_per_second": 6.842,
       "step": 1320
     },
     {
@@ -100,9 +100,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.7798165137614679,
       "eval_loss": 0.901915967464447,
-      "eval_runtime": 0.574,
-      "eval_samples_per_second": 1519.183,
-      "eval_steps_per_second": 6.969,
+      "eval_runtime": 0.5612,
+      "eval_samples_per_second": 1553.681,
+      "eval_steps_per_second": 7.127,
       "step": 1584
     },
     {
@@ -110,9 +110,9 @@
       "step": 1584,
       "total_flos": 5.316079940232192e+16,
       "train_loss": 0.17508280758905892,
-      "train_runtime": 660.7862,
-      "train_samples_per_second": 5096.126,
-      "train_steps_per_second": 19.976
+      "train_runtime": 659.8178,
+      "train_samples_per_second": 5103.606,
+      "train_steps_per_second": 20.006
     }
   ],
   "logging_steps": 1,