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-uncased-finetuned-mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8529411764705882
+    - name: F1
+      type: f1
+      value: 0.8958333333333334
 ---
 
 <!-- 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-uncased-finetuned-mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4322
 - Accuracy: 0.8529
-- Combined Score: 0.8744
 - F1: 0.8958
-- Loss: 0.4322
+- Combined Score: 0.8744
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6342515349388123,
+    "eval_accuracy": 0.8529411764705882,
+    "eval_combined_score": 0.8743872549019608,
+    "eval_f1": 0.8958333333333334,
+    "eval_loss": 0.43215397000312805,
     "eval_model_preparation_time": 0.0025,
-    "eval_runtime": 2.8487,
+    "eval_runtime": 2.0353,
     "eval_samples": 408,
-    "eval_samples_per_second": 143.222,
-    "eval_steps_per_second": 17.903,
+    "eval_samples_per_second": 200.46,
+    "eval_steps_per_second": 25.058,
     "total_flos": 2895274053181440.0,
-    "train_loss": 0.3542040064714957,
-    "train_runtime": 140.1555,
+    "train_loss": 0.0,
+    "train_runtime": 0.0023,
     "train_samples": 3668,
-    "train_samples_per_second": 78.513,
-    "train_steps_per_second": 4.923
+    "train_samples_per_second": 4799222.337,
+    "train_steps_per_second": 300932.698
 }

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": "4.44.2",
   "type_vocab_size": 2,

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6342515349388123,
-    "eval_model_preparation_time": 0.0025,
-    "eval_runtime": 2.8487,
+    "epoch": 3.0,
+    "eval_accuracy": 0.8529411764705882,
+    "eval_combined_score": 0.8743872549019608,
+    "eval_f1": 0.8958333333333334,
+    "eval_loss": 0.43215397000312805,
+    "eval_runtime": 2.0353,
     "eval_samples": 408,
-    "eval_samples_per_second": 143.222,
-    "eval_steps_per_second": 17.903
+    "eval_samples_per_second": 200.46,
+    "eval_steps_per_second": 25.058
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 2895274053181440.0,
-    "train_loss": 0.3542040064714957,
-    "train_runtime": 140.1555,
+    "train_loss": 0.0,
+    "train_runtime": 0.0023,
     "train_samples": 3668,
-    "train_samples_per_second": 78.513,
-    "train_steps_per_second": 4.923
+    "train_samples_per_second": 4799222.337,
+    "train_steps_per_second": 300932.698
 }

trainer_state.json

@@ -66,10 +66,10 @@
       "epoch": 3.0,
       "step": 690,
       "total_flos": 2895274053181440.0,
-      "train_loss": 0.3542040064714957,
-      "train_runtime": 140.1555,
-      "train_samples_per_second": 78.513,
-      "train_steps_per_second": 4.923
+      "train_loss": 0.0,
+      "train_runtime": 0.0023,
+      "train_samples_per_second": 4799222.337,
+      "train_steps_per_second": 300932.698
     }
   ],
   "logging_steps": 500,