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_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.48736462093862815
 ---
 
 <!-- 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_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4270
-- Accuracy: 0.4946
+- Loss: 0.7144
+- Accuracy: 0.4874
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.49458483754512633,
-    "eval_loss": 0.7144136428833008,
-    "eval_runtime": 0.2138,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 0.7143642902374268,
+    "eval_runtime": 0.2188,
     "eval_samples": 277,
-    "eval_samples_per_second": 1295.412,
-    "eval_steps_per_second": 9.353,
+    "eval_samples_per_second": 1265.975,
+    "eval_steps_per_second": 9.141,
     "total_flos": 2293012847462400.0,
-    "train_loss": 0.47900971174240115,
-    "train_runtime": 45.1124,
+    "train_loss": 0.47949272564479284,
+    "train_runtime": 44.6997,
     "train_samples": 2490,
-    "train_samples_per_second": 2759.772,
-    "train_steps_per_second": 11.083
+    "train_samples_per_second": 2785.254,
+    "train_steps_per_second": 11.186
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
-    "eval_accuracy": 0.49458483754512633,
-    "eval_loss": 0.7144136428833008,
-    "eval_runtime": 0.2138,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 0.7143642902374268,
+    "eval_runtime": 0.2188,
     "eval_samples": 277,
-    "eval_samples_per_second": 1295.412,
-    "eval_steps_per_second": 9.353
+    "eval_samples_per_second": 1265.975,
+    "eval_steps_per_second": 9.141
 }

logs/events.out.tfevents.1745049936.s_005_m.2788007.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15df30b4fa7702da063dfb491ce8d1b7f187b42a5cb4249e9d8e3c29fa4217ed
+size 357

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 7.0,
     "total_flos": 2293012847462400.0,
-    "train_loss": 0.47900971174240115,
-    "train_runtime": 45.1124,
+    "train_loss": 0.47949272564479284,
+    "train_runtime": 44.6997,
     "train_samples": 2490,
-    "train_samples_per_second": 2759.772,
-    "train_steps_per_second": 11.083
+    "train_samples_per_second": 2785.254,
+    "train_steps_per_second": 11.186
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 20,
-  "best_metric": 0.7144136428833008,
+  "best_metric": 0.7143642902374268,
   "best_model_checkpoint": "bert_base_km_20_v1_rte/checkpoint-20",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -11,124 +11,124 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.612154245376587,
+      "grad_norm": 1.6082864999771118,
       "learning_rate": 4.9e-05,
       "loss": 0.7172,
       "step": 10
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4548736462093863,
-      "eval_loss": 0.7189333438873291,
-      "eval_runtime": 0.1891,
-      "eval_samples_per_second": 1465.169,
-      "eval_steps_per_second": 10.579,
+      "eval_accuracy": 0.45126353790613716,
+      "eval_loss": 0.7190461158752441,
+      "eval_runtime": 0.2048,
+      "eval_samples_per_second": 1352.543,
+      "eval_steps_per_second": 9.766,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.070043683052063,
+      "grad_norm": 1.069560170173645,
       "learning_rate": 4.8e-05,
-      "loss": 0.6657,
+      "loss": 0.6658,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.49458483754512633,
-      "eval_loss": 0.7144136428833008,
-      "eval_runtime": 0.1939,
-      "eval_samples_per_second": 1428.509,
-      "eval_steps_per_second": 10.314,
+      "eval_accuracy": 0.48736462093862815,
+      "eval_loss": 0.7143642902374268,
+      "eval_runtime": 0.1966,
+      "eval_samples_per_second": 1408.66,
+      "eval_steps_per_second": 10.171,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.0873299837112427,
+      "grad_norm": 1.088363766670227,
       "learning_rate": 4.7e-05,
-      "loss": 0.6167,
+      "loss": 0.6169,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.48014440433212996,
-      "eval_loss": 0.7387924194335938,
-      "eval_runtime": 0.1956,
-      "eval_samples_per_second": 1415.945,
-      "eval_steps_per_second": 10.223,
+      "eval_accuracy": 0.48375451263537905,
+      "eval_loss": 0.7388594150543213,
+      "eval_runtime": 0.2029,
+      "eval_samples_per_second": 1365.048,
+      "eval_steps_per_second": 9.856,
       "step": 30
     },
     {
       "epoch": 4.0,
-      "grad_norm": 1.5245287418365479,
+      "grad_norm": 1.4970088005065918,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 0.5298,
+      "loss": 0.5307,
       "step": 40
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4981949458483754,
-      "eval_loss": 0.7878444194793701,
-      "eval_runtime": 0.1917,
-      "eval_samples_per_second": 1445.232,
-      "eval_steps_per_second": 10.435,
+      "eval_accuracy": 0.49458483754512633,
+      "eval_loss": 0.7875006794929504,
+      "eval_runtime": 0.1976,
+      "eval_samples_per_second": 1401.985,
+      "eval_steps_per_second": 10.123,
       "step": 40
     },
     {
       "epoch": 5.0,
-      "grad_norm": 2.408193588256836,
+      "grad_norm": 2.31677508354187,
       "learning_rate": 4.5e-05,
-      "loss": 0.4001,
+      "loss": 0.4009,
       "step": 50
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.9474132657051086,
-      "eval_runtime": 0.1934,
-      "eval_samples_per_second": 1432.46,
-      "eval_steps_per_second": 10.343,
+      "eval_loss": 0.947138249874115,
+      "eval_runtime": 0.2288,
+      "eval_samples_per_second": 1210.554,
+      "eval_steps_per_second": 8.74,
       "step": 50
     },
     {
       "epoch": 6.0,
-      "grad_norm": 5.390678405761719,
+      "grad_norm": 5.374250411987305,
       "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.2708,
+      "loss": 0.2719,
       "step": 60
     },
     {
       "epoch": 6.0,
       "eval_accuracy": 0.48736462093862815,
-      "eval_loss": 1.1789220571517944,
-      "eval_runtime": 0.1869,
-      "eval_samples_per_second": 1482.292,
-      "eval_steps_per_second": 10.702,
+      "eval_loss": 1.1685609817504883,
+      "eval_runtime": 0.1915,
+      "eval_samples_per_second": 1446.654,
+      "eval_steps_per_second": 10.445,
       "step": 60
     },
     {
       "epoch": 7.0,
-      "grad_norm": 3.910654306411743,
+      "grad_norm": 3.844560384750366,
       "learning_rate": 4.3e-05,
-      "loss": 0.1527,
+      "loss": 0.153,
       "step": 70
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.48375451263537905,
-      "eval_loss": 1.4288209676742554,
-      "eval_runtime": 0.2156,
-      "eval_samples_per_second": 1284.848,
-      "eval_steps_per_second": 9.277,
+      "eval_accuracy": 0.49458483754512633,
+      "eval_loss": 1.4269626140594482,
+      "eval_runtime": 0.1935,
+      "eval_samples_per_second": 1431.625,
+      "eval_steps_per_second": 10.337,
       "step": 70
     },
     {
       "epoch": 7.0,
       "step": 70,
       "total_flos": 2293012847462400.0,
-      "train_loss": 0.47900971174240115,
-      "train_runtime": 45.1124,
-      "train_samples_per_second": 2759.772,
-      "train_steps_per_second": 11.083
+      "train_loss": 0.47949272564479284,
+      "train_runtime": 44.6997,
+      "train_samples_per_second": 2785.254,
+      "train_steps_per_second": 11.186
     }
   ],
   "logging_steps": 1,