End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_rand_100_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7107843137254902
+    - name: F1
+      type: f1
+      value: 0.8033333333333333
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_rand_100_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v1](https://huggingface.co/Hartunka/bert_base_rand_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4011
-- Accuracy: 0.6495
-- F1: 0.7357
-- Combined Score: 0.6926
+- Loss: 0.5808
+- Accuracy: 0.7108
+- F1: 0.8033
+- Combined Score: 0.7571
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_combined_score": 0.7570588235294118,
     "eval_f1": 0.8033333333333333,
     "eval_loss": 0.5807782411575317,
-    "eval_runtime": 0.3002,
+    "eval_runtime": 0.3042,
     "eval_samples": 408,
-    "eval_samples_per_second": 1359.097,
-    "eval_steps_per_second": 6.662,
+    "eval_samples_per_second": 1341.2,
+    "eval_steps_per_second": 6.575,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.3727283318837484,
-    "train_runtime": 58.1176,
+    "train_runtime": 60.2116,
     "train_samples": 3668,
-    "train_samples_per_second": 3155.67,
-    "train_steps_per_second": 12.905
+    "train_samples_per_second": 3045.927,
+    "train_steps_per_second": 12.456
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7570588235294118,
     "eval_f1": 0.8033333333333333,
     "eval_loss": 0.5807782411575317,
-    "eval_runtime": 0.3002,
+    "eval_runtime": 0.3042,
     "eval_samples": 408,
-    "eval_samples_per_second": 1359.097,
-    "eval_steps_per_second": 6.662
+    "eval_samples_per_second": 1341.2,
+    "eval_steps_per_second": 6.575
 }

logs/events.out.tfevents.1745183177.s_005_m.2815556.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fddd66f86acf8c7487dbc3b185d7b2c9dcb0a384e77f2717ea0c297d612014bb
+size 459

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "total_flos": 3377819728711680.0,
     "train_loss": 0.3727283318837484,
-    "train_runtime": 58.1176,
+    "train_runtime": 60.2116,
     "train_samples": 3668,
-    "train_samples_per_second": 3155.67,
-    "train_steps_per_second": 12.905
+    "train_samples_per_second": 3045.927,
+    "train_steps_per_second": 12.456
 }

trainer_state.json

@@ -22,9 +22,9 @@
       "eval_combined_score": 0.7513938781619518,
       "eval_f1": 0.8091603053435115,
       "eval_loss": 0.5958898067474365,
-      "eval_runtime": 0.2694,
-      "eval_samples_per_second": 1514.258,
-      "eval_steps_per_second": 7.423,
+      "eval_runtime": 0.2695,
+      "eval_samples_per_second": 1513.971,
+      "eval_steps_per_second": 7.421,
       "step": 15
     },
     {
@@ -40,9 +40,9 @@
       "eval_combined_score": 0.7570588235294118,
       "eval_f1": 0.8033333333333333,
       "eval_loss": 0.5807782411575317,
-      "eval_runtime": 0.2724,
-      "eval_samples_per_second": 1497.92,
-      "eval_steps_per_second": 7.343,
+      "eval_runtime": 0.2883,
+      "eval_samples_per_second": 1415.329,
+      "eval_steps_per_second": 6.938,
       "step": 30
     },
     {
@@ -58,9 +58,9 @@
       "eval_combined_score": 0.7586610486891385,
       "eval_f1": 0.8089887640449438,
       "eval_loss": 0.5847347974777222,
-      "eval_runtime": 0.3261,
-      "eval_samples_per_second": 1251.324,
-      "eval_steps_per_second": 6.134,
+      "eval_runtime": 0.2696,
+      "eval_samples_per_second": 1513.304,
+      "eval_steps_per_second": 7.418,
       "step": 45
     },
     {
@@ -76,9 +76,9 @@
       "eval_combined_score": 0.7443602859203882,
       "eval_f1": 0.7926421404682275,
       "eval_loss": 0.7103803753852844,
-      "eval_runtime": 0.2922,
-      "eval_samples_per_second": 1396.208,
-      "eval_steps_per_second": 6.844,
+      "eval_runtime": 0.285,
+      "eval_samples_per_second": 1431.679,
+      "eval_steps_per_second": 7.018,
       "step": 60
     },
     {
@@ -94,9 +94,9 @@
       "eval_combined_score": 0.7373566326705814,
       "eval_f1": 0.7810858143607706,
       "eval_loss": 0.9412671327590942,
-      "eval_runtime": 0.2711,
-      "eval_samples_per_second": 1505.075,
-      "eval_steps_per_second": 7.378,
+      "eval_runtime": 0.2734,
+      "eval_samples_per_second": 1492.486,
+      "eval_steps_per_second": 7.316,
       "step": 75
     },
     {
@@ -112,9 +112,9 @@
       "eval_combined_score": 0.7117102396514161,
       "eval_f1": 0.7518518518518519,
       "eval_loss": 1.1874147653579712,
-      "eval_runtime": 0.2829,
-      "eval_samples_per_second": 1441.989,
-      "eval_steps_per_second": 7.069,
+      "eval_runtime": 0.2693,
+      "eval_samples_per_second": 1515.172,
+      "eval_steps_per_second": 7.427,
       "step": 90
     },
     {
@@ -130,9 +130,9 @@
       "eval_combined_score": 0.6925922402232612,
       "eval_f1": 0.7356746765249538,
       "eval_loss": 1.4011175632476807,
-      "eval_runtime": 0.2802,
-      "eval_samples_per_second": 1456.129,
-      "eval_steps_per_second": 7.138,
+      "eval_runtime": 0.2886,
+      "eval_samples_per_second": 1413.947,
+      "eval_steps_per_second": 6.931,
       "step": 105
     },
     {
@@ -140,9 +140,9 @@
       "step": 105,
       "total_flos": 3377819728711680.0,
       "train_loss": 0.3727283318837484,
-      "train_runtime": 58.1176,
-      "train_samples_per_second": 3155.67,
-      "train_steps_per_second": 12.905
+      "train_runtime": 60.2116,
+      "train_samples_per_second": 3045.927,
+      "train_steps_per_second": 12.456
     }
   ],
   "logging_steps": 1,