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: 0.8480392156862745
+    - name: F1
+      type: f1
+      value: 0.8923611111111112
 ---
 
 <!-- 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:
-- Accuracy: 0.8529
-- Combined Score: 0.8744
-- F1: 0.8958
-- Loss: 0.4322
+- Loss: 0.4198
+- Accuracy: 0.8480
+- F1: 0.8924
+- Combined Score: 0.8702
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.8529411764705882,
-    "eval_combined_score": 0.8743872549019608,
-    "eval_f1": 0.8958333333333334,
-    "eval_loss": 0.4279242157936096,
+    "eval_accuracy": 0.8480392156862745,
+    "eval_combined_score": 0.8702001633986929,
+    "eval_f1": 0.8923611111111112,
+    "eval_loss": 0.4198153018951416,
     "eval_model_preparation_time": 0.0025,
-    "eval_runtime": 60.4806,
+    "eval_runtime": 60.8121,
     "eval_samples": 408,
-    "eval_samples_per_second": 6.746,
-    "eval_steps_per_second": 0.843,
+    "eval_samples_per_second": 6.709,
+    "eval_steps_per_second": 0.839,
     "total_flos": 2895274053181440.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0014,
+    "train_runtime": 0.0013,
     "train_samples": 3668,
-    "train_samples_per_second": 7792355.431,
-    "train_steps_per_second": 488615.526
+    "train_samples_per_second": 8422284.893,
+    "train_steps_per_second": 528114.92
 }

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": 0.8529411764705882,
-    "eval_combined_score": 0.8743872549019608,
-    "eval_f1": 0.8958333333333334,
-    "eval_loss": 0.4279242157936096,
-    "eval_runtime": 60.4806,
+    "eval_accuracy": 0.8480392156862745,
+    "eval_combined_score": 0.8702001633986929,
+    "eval_f1": 0.8923611111111112,
+    "eval_loss": 0.4198153018951416,
+    "eval_runtime": 60.8121,
     "eval_samples": 408,
-    "eval_samples_per_second": 6.746,
-    "eval_steps_per_second": 0.843
+    "eval_samples_per_second": 6.709,
+    "eval_steps_per_second": 0.839
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 2895274053181440.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0014,
+    "train_runtime": 0.0013,
     "train_samples": 3668,
-    "train_samples_per_second": 7792355.431,
-    "train_steps_per_second": 488615.526
+    "train_samples_per_second": 8422284.893,
+    "train_steps_per_second": 528114.92
 }

trainer_state.json

@@ -67,9 +67,9 @@
       "step": 690,
       "total_flos": 2895274053181440.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0014,
-      "train_samples_per_second": 7792355.431,
-      "train_steps_per_second": 488615.526
+      "train_runtime": 0.0013,
+      "train_samples_per_second": 8422284.893,
+      "train_steps_per_second": 528114.92
     }
   ],
   "logging_steps": 500,