End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert-base-cased-finetuned-qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9108830076675736
+    - name: F1
+      type: f1
+      value: 0.8798719701263629
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-cased-finetuned-qqp
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3636
 - Accuracy: 0.9109
-- Combined Score: 0.8957
-- F1: 0.8805
-- Loss: 0.3568
+- F1: 0.8799
+- Combined Score: 0.8954
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9102646549591887,
-    "eval_combined_score": 0.8956452152607972,
-    "eval_f1": 0.8810257755624057,
-    "eval_loss": 0.34155702590942383,
-    "eval_runtime": 1896.9354,
+    "eval_accuracy": 0.9108830076675736,
+    "eval_combined_score": 0.8953774888969682,
+    "eval_f1": 0.8798719701263629,
+    "eval_loss": 0.363625168800354,
+    "eval_runtime": 6006.0944,
     "eval_samples": 40430,
-    "eval_samples_per_second": 21.313,
-    "eval_steps_per_second": 2.664,
+    "eval_samples_per_second": 6.731,
+    "eval_steps_per_second": 0.841,
     "total_flos": 2.8719571514554368e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0116,
+    "train_runtime": 0.0017,
     "train_samples": 363846,
-    "train_samples_per_second": 93935783.158,
-    "train_steps_per_second": 5871147.806
+    "train_samples_per_second": 658929504.829,
+    "train_steps_per_second": 41184225.934
 }

config.json

@@ -23,6 +23,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.45.0.dev0",
   "type_vocab_size": 2,

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9102646549591887,
-    "eval_combined_score": 0.8956452152607972,
-    "eval_f1": 0.8810257755624057,
-    "eval_loss": 0.34155702590942383,
-    "eval_runtime": 1896.9354,
+    "eval_accuracy": 0.9108830076675736,
+    "eval_combined_score": 0.8953774888969682,
+    "eval_f1": 0.8798719701263629,
+    "eval_loss": 0.363625168800354,
+    "eval_runtime": 6006.0944,
     "eval_samples": 40430,
-    "eval_samples_per_second": 21.313,
-    "eval_steps_per_second": 2.664
+    "eval_samples_per_second": 6.731,
+    "eval_steps_per_second": 0.841
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 2.8719571514554368e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0116,
+    "train_runtime": 0.0017,
     "train_samples": 363846,
-    "train_samples_per_second": 93935783.158,
-    "train_steps_per_second": 5871147.806
+    "train_samples_per_second": 658929504.829,
+    "train_steps_per_second": 41184225.934
 }

trainer_state.json

@@ -67,9 +67,9 @@
       "step": 68223,
       "total_flos": 2.8719571514554368e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.0116,
-      "train_samples_per_second": 93935783.158,
-      "train_steps_per_second": 5871147.806
+      "train_runtime": 0.0017,
+      "train_samples_per_second": 658929504.829,
+      "train_steps_per_second": 41184225.934
     }
   ],
   "logging_steps": 500,