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-mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8361472742066721
 ---
 
 <!-- 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-mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.8469
-- Loss: 0.5565
+- Loss: 0.6428
+- Accuracy: 0.8361
 
 ## Model description
 

all_results.json

@@ -1,22 +1,22 @@
 {
     "epoch": 3.0,
     "epoch_mm": 3.0,
-    "eval_accuracy": 0.845236882322975,
-    "eval_accuracy_mm": 0.8463181448331977,
-    "eval_loss": 0.5687322616577148,
-    "eval_loss_mm": 0.5642727613449097,
-    "eval_runtime": 610.678,
-    "eval_runtime_mm": 611.7861,
+    "eval_accuracy": 0.834538970962812,
+    "eval_accuracy_mm": 0.8361472742066721,
+    "eval_loss": 0.6543402671813965,
+    "eval_loss_mm": 0.6428265571594238,
+    "eval_runtime": 142.9111,
+    "eval_runtime_mm": 143.0775,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 16.072,
-    "eval_samples_per_second_mm": 16.071,
-    "eval_steps_per_second": 2.009,
-    "eval_steps_per_second_mm": 2.009,
+    "eval_samples_per_second": 68.679,
+    "eval_samples_per_second_mm": 68.718,
+    "eval_steps_per_second": 8.586,
+    "eval_steps_per_second_mm": 8.59,
     "total_flos": 3.099754961058632e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 392702,
-    "train_samples_per_second": 910006391.938,
-    "train_steps_per_second": 56875689.158
+    "train_samples_per_second": 996839763.612,
+    "train_steps_per_second": 62302802.527
 }

config.json

@@ -29,6 +29,7 @@
   "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

@@ -1,16 +1,16 @@
 {
     "epoch": 3.0,
     "epoch_mm": 3.0,
-    "eval_accuracy": 0.845236882322975,
-    "eval_accuracy_mm": 0.8463181448331977,
-    "eval_loss": 0.5687322616577148,
-    "eval_loss_mm": 0.5642727613449097,
-    "eval_runtime": 610.678,
-    "eval_runtime_mm": 611.7861,
+    "eval_accuracy": 0.834538970962812,
+    "eval_accuracy_mm": 0.8361472742066721,
+    "eval_loss": 0.6543402671813965,
+    "eval_loss_mm": 0.6428265571594238,
+    "eval_runtime": 142.9111,
+    "eval_runtime_mm": 143.0775,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 16.072,
-    "eval_samples_per_second_mm": 16.071,
-    "eval_steps_per_second": 2.009,
-    "eval_steps_per_second_mm": 2.009
+    "eval_samples_per_second": 68.679,
+    "eval_samples_per_second_mm": 68.718,
+    "eval_steps_per_second": 8.586,
+    "eval_steps_per_second_mm": 8.59
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 3.099754961058632e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 392702,
-    "train_samples_per_second": 910006391.938,
-    "train_steps_per_second": 56875689.158
+    "train_samples_per_second": 996839763.612,
+    "train_steps_per_second": 62302802.527
 }

trainer_state.json

@@ -61,9 +61,9 @@
       "step": 73632,
       "total_flos": 3.099754961058632e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.0013,
-      "train_samples_per_second": 910006391.938,
-      "train_steps_per_second": 56875689.158
+      "train_runtime": 0.0012,
+      "train_samples_per_second": 996839763.612,
+      "train_steps_per_second": 62302802.527
     }
   ],
   "logging_steps": 500,