End of training

README.md

@@ -1,13 +1,30 @@
 ---
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
 - glue
+metrics:
+- spearmanr
 model-index:
 - name: out-glue-stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      config: stsb
+      split: validation
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.8807931789519186
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out-glue-stsb
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE STSB dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5330
+- Pearson: 0.8855
+- Spearmanr: 0.8808
+- Combined Score: 0.8831
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 20.0,
-    "eval_combined_score": 0.8830287553865886,
-    "eval_loss": 0.533576250076294,
-    "eval_pearson": 0.8853386403755572,
-    "eval_runtime": 1.1414,
+    "eval_combined_score": 0.8831457963278682,
+    "eval_loss": 0.5330392122268677,
+    "eval_pearson": 0.8854984137038179,
+    "eval_runtime": 1.1378,
     "eval_samples": 1500,
-    "eval_samples_per_second": 1314.172,
-    "eval_spearmanr": 0.8807188703976201,
-    "eval_steps_per_second": 5.257,
-    "train_loss": 0.4903079410394033,
-    "train_runtime": 237.6265,
+    "eval_samples_per_second": 1318.312,
+    "eval_spearmanr": 0.8807931789519186,
+    "eval_steps_per_second": 5.273,
+    "train_loss": 0.017963338692982993,
+    "train_runtime": 43.8472,
     "train_samples": 5749,
-    "train_samples_per_second": 483.869,
-    "train_steps_per_second": 2.525
+    "train_samples_per_second": 2622.287,
+    "train_steps_per_second": 13.684
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 20.0,
-    "eval_combined_score": 0.8830287553865886,
-    "eval_loss": 0.533576250076294,
-    "eval_pearson": 0.8853386403755572,
-    "eval_runtime": 1.1414,
+    "eval_combined_score": 0.8831457963278682,
+    "eval_loss": 0.5330392122268677,
+    "eval_pearson": 0.8854984137038179,
+    "eval_runtime": 1.1378,
     "eval_samples": 1500,
-    "eval_samples_per_second": 1314.172,
-    "eval_spearmanr": 0.8807188703976201,
-    "eval_steps_per_second": 5.257
+    "eval_samples_per_second": 1318.312,
+    "eval_spearmanr": 0.8807931789519186,
+    "eval_steps_per_second": 5.273
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.4903079410394033,
-    "train_runtime": 237.6265,
+    "train_loss": 0.017963338692982993,
+    "train_runtime": 43.8472,
     "train_samples": 5749,
-    "train_samples_per_second": 483.869,
-    "train_steps_per_second": 2.525
+    "train_samples_per_second": 2622.287,
+    "train_steps_per_second": 13.684
 }

trainer_state.json

@@ -131,13 +131,13 @@
     {
       "epoch": 17.5,
       "learning_rate": 2.6e-06,
-      "loss": 0.1095,
+      "loss": 0.1094,
       "step": 525
     },
     {
       "epoch": 18.33,
       "learning_rate": 1.7666666666666668e-06,
-      "loss": 0.1088,
+      "loss": 0.1093,
       "step": 550
     },
     {
@@ -149,17 +149,17 @@
     {
       "epoch": 20.0,
       "learning_rate": 1.0000000000000001e-07,
-      "loss": 0.1063,
+      "loss": 0.1064,
       "step": 600
     },
     {
       "epoch": 20.0,
       "step": 600,
       "total_flos": 7563059380055040.0,
-      "train_loss": 0.4903079410394033,
-      "train_runtime": 237.6265,
-      "train_samples_per_second": 483.869,
-      "train_steps_per_second": 2.525
+      "train_loss": 0.017963338692982993,
+      "train_runtime": 43.8472,
+      "train_samples_per_second": 2622.287,
+      "train_steps_per_second": 13.684
     }
   ],
   "logging_steps": 25,