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-sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.910784071234232
+    - name: F1
+      type: f1
+      value: 0.8782365054180873
 ---
 
 <!-- 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-sst2
 
-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:
-- Accuracy: 0.9109
-- Combined Score: 0.8954
-- F1: 0.8799
-- Loss: 0.3585
+- Loss: 0.3776
+- Accuracy: 0.9108
+- F1: 0.8782
+- Combined Score: 0.8945
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9109077417759089,
-    "eval_combined_score": 0.8953925089190357,
-    "eval_f1": 0.8798772760621624,
-    "eval_loss": 0.35853680968284607,
-    "eval_runtime": 173.7873,
+    "eval_accuracy": 0.910784071234232,
+    "eval_combined_score": 0.8945102883261596,
+    "eval_f1": 0.8782365054180873,
+    "eval_loss": 0.3775930106639862,
+    "eval_runtime": 1120.9866,
     "eval_samples": 40430,
-    "eval_samples_per_second": 232.641,
-    "eval_steps_per_second": 29.082,
+    "eval_samples_per_second": 36.066,
+    "eval_steps_per_second": 4.509,
     "total_flos": 2.8719571514554368e+17,
-    "train_loss": 0.20698899069389173,
-    "train_runtime": 14606.6124,
+    "train_loss": 0.0,
+    "train_runtime": 0.002,
     "train_samples": 363846,
-    "train_samples_per_second": 74.729,
-    "train_steps_per_second": 4.671
+    "train_samples_per_second": 559413758.499,
+    "train_steps_per_second": 34964320.845
 }

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": 0.9109077417759089,
-    "eval_combined_score": 0.8953925089190357,
-    "eval_f1": 0.8798772760621624,
-    "eval_loss": 0.35853680968284607,
-    "eval_runtime": 173.7873,
+    "eval_accuracy": 0.910784071234232,
+    "eval_combined_score": 0.8945102883261596,
+    "eval_f1": 0.8782365054180873,
+    "eval_loss": 0.3775930106639862,
+    "eval_runtime": 1120.9866,
     "eval_samples": 40430,
-    "eval_samples_per_second": 232.641,
-    "eval_steps_per_second": 29.082
+    "eval_samples_per_second": 36.066,
+    "eval_steps_per_second": 4.509
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 2.8719571514554368e+17,
-    "train_loss": 0.20698899069389173,
-    "train_runtime": 14606.6124,
+    "train_loss": 0.0,
+    "train_runtime": 0.002,
     "train_samples": 363846,
-    "train_samples_per_second": 74.729,
-    "train_steps_per_second": 4.671
+    "train_samples_per_second": 559413758.499,
+    "train_steps_per_second": 34964320.845
 }

trainer_state.json

@@ -66,10 +66,10 @@
       "epoch": 3.0,
       "step": 68223,
       "total_flos": 2.8719571514554368e+17,
-      "train_loss": 0.20698899069389173,
-      "train_runtime": 14606.6124,
-      "train_samples_per_second": 74.729,
-      "train_steps_per_second": 4.671
+      "train_loss": 0.0,
+      "train_runtime": 0.002,
+      "train_samples_per_second": 559413758.499,
+      "train_steps_per_second": 34964320.845
     }
   ],
   "logging_steps": 500,