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-sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9288990825688074
 ---
 
 <!-- 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-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.9266
-- Loss: 0.3198
+- Loss: 0.3197
+- Accuracy: 0.9289
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.930045871559633,
-    "eval_loss": 0.34476935863494873,
-    "eval_runtime": 12.9657,
+    "eval_accuracy": 0.9288990825688074,
+    "eval_loss": 0.3197207450866699,
+    "eval_runtime": 23.8916,
     "eval_samples": 872,
-    "eval_samples_per_second": 67.254,
-    "eval_steps_per_second": 8.407,
+    "eval_samples_per_second": 36.498,
+    "eval_steps_per_second": 4.562,
     "total_flos": 5.316079940232192e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 67349,
-    "train_samples_per_second": 151981086.852,
-    "train_steps_per_second": 9500369.354
+    "train_samples_per_second": 162751400.094,
+    "train_steps_per_second": 10173623.876
 }

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": 0.930045871559633,
-    "eval_loss": 0.34476935863494873,
-    "eval_runtime": 12.9657,
+    "eval_accuracy": 0.9288990825688074,
+    "eval_loss": 0.3197207450866699,
+    "eval_runtime": 23.8916,
     "eval_samples": 872,
-    "eval_samples_per_second": 67.254,
-    "eval_steps_per_second": 8.407
+    "eval_samples_per_second": 36.498,
+    "eval_steps_per_second": 4.562
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "total_flos": 5.316079940232192e+16,
     "train_loss": 0.0,
-    "train_runtime": 0.0013,
+    "train_runtime": 0.0012,
     "train_samples": 67349,
-    "train_samples_per_second": 151981086.852,
-    "train_steps_per_second": 9500369.354
+    "train_samples_per_second": 162751400.094,
+    "train_steps_per_second": 10173623.876
 }

trainer_state.json

@@ -61,9 +61,9 @@
       "step": 12630,
       "total_flos": 5.316079940232192e+16,
       "train_loss": 0.0,
-      "train_runtime": 0.0013,
-      "train_samples_per_second": 151981086.852,
-      "train_steps_per_second": 9500369.354
+      "train_runtime": 0.0012,
+      "train_samples_per_second": 162751400.094,
+      "train_steps_per_second": 10173623.876
     }
   ],
   "logging_steps": 500,