End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-base-uncased-finetuned-qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9114039904814205
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.9132
-- Loss: 0.3919
+- Loss: 0.4043
+- Accuracy: 0.9114
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9062786015010068,
-    "eval_loss": 0.3877147138118744,
-    "eval_runtime": 168.0069,
+    "eval_accuracy": 0.9114039904814205,
+    "eval_loss": 0.40430235862731934,
+    "eval_runtime": 438.058,
     "eval_samples": 5463,
-    "eval_samples_per_second": 32.517,
-    "eval_steps_per_second": 4.065,
+    "eval_samples_per_second": 12.471,
+    "eval_steps_per_second": 1.559,
     "total_flos": 8.267712381471744e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 104743,
-    "train_samples_per_second": 246211834.787,
-    "train_steps_per_second": 15389561.902
+    "train_samples_per_second": 253407412.347,
+    "train_steps_per_second": 15839324.142
 }

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

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9062786015010068,
-    "eval_loss": 0.3877147138118744,
-    "eval_runtime": 168.0069,
+    "eval_accuracy": 0.9114039904814205,
+    "eval_loss": 0.40430235862731934,
+    "eval_runtime": 438.058,
     "eval_samples": 5463,
-    "eval_samples_per_second": 32.517,
-    "eval_steps_per_second": 4.065
+    "eval_samples_per_second": 12.471,
+    "eval_steps_per_second": 1.559
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 8.267712381471744e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 104743,
-    "train_samples_per_second": 246211834.787,
-    "train_steps_per_second": 15389561.902
+    "train_samples_per_second": 253407412.347,
+    "train_steps_per_second": 15839324.142
 }

trainer_state.json

@@ -61,9 +61,9 @@
       "step": 19641,
       "total_flos": 8.267712381471744e+16,
       "train_loss": 0.0,
-      "train_runtime": 0.0013,
-      "train_samples_per_second": 246211834.787,
-      "train_steps_per_second": 15389561.902
+      "train_runtime": 0.0012,
+      "train_samples_per_second": 253407412.347,
+      "train_steps_per_second": 15839324.142
     }
   ],
   "logging_steps": 500,