End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MRPC
       type: glue
       config: mrpc
       split: validation
@@ -21,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6838235294117647
+      value: 0.6862745098039216
     - name: F1
       type: f1
-      value: 0.7809847198641766
+      value: 0.7999999999999999
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_mrpc
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9708
-- Accuracy: 0.6838
-- F1: 0.7810
-- Combined Score: 0.7324
+- Loss: 0.6051
+- Accuracy: 0.6863
+- F1: 0.8000
+- Combined Score: 0.7431
 
 ## Model description
 

all_results.json

@@ -4,13 +4,13 @@
     "eval_combined_score": 0.7431372549019608,
     "eval_f1": 0.7999999999999999,
     "eval_loss": 0.6050820350646973,
-    "eval_runtime": 0.5403,
+    "eval_runtime": 0.5155,
     "eval_samples": 408,
-    "eval_samples_per_second": 755.096,
-    "eval_steps_per_second": 3.701,
-    "train_loss": 0.4964691546228197,
-    "train_runtime": 203.7797,
+    "eval_samples_per_second": 791.396,
+    "eval_steps_per_second": 3.879,
+    "train_loss": 0.14563740226957533,
+    "train_runtime": 96.9183,
     "train_samples": 3668,
-    "train_samples_per_second": 899.991,
-    "train_steps_per_second": 3.68
+    "train_samples_per_second": 1892.315,
+    "train_steps_per_second": 7.738
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7431372549019608,
     "eval_f1": 0.7999999999999999,
     "eval_loss": 0.6050820350646973,
-    "eval_runtime": 0.5403,
+    "eval_runtime": 0.5155,
     "eval_samples": 408,
-    "eval_samples_per_second": 755.096,
-    "eval_steps_per_second": 3.701
+    "eval_samples_per_second": 791.396,
+    "eval_steps_per_second": 3.879
 }

logs/events.out.tfevents.1677709281.serv-9225.3038038.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16037de5fbcf6993efcf9449fc4b6614f4c60d4752d2bc547e3b9fa9fbbabad6
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 12.0,
-    "train_loss": 0.4964691546228197,
-    "train_runtime": 203.7797,
+    "train_loss": 0.14563740226957533,
+    "train_runtime": 96.9183,
     "train_samples": 3668,
-    "train_samples_per_second": 899.991,
-    "train_steps_per_second": 3.68
+    "train_samples_per_second": 1892.315,
+    "train_steps_per_second": 7.738
 }

trainer_state.json

@@ -138,9 +138,9 @@
       "eval_combined_score": 0.7477645971225257,
       "eval_f1": 0.8019017432646594,
       "eval_loss": 0.6560007929801941,
-      "eval_runtime": 0.515,
-      "eval_samples_per_second": 792.192,
-      "eval_steps_per_second": 3.883,
+      "eval_runtime": 0.5165,
+      "eval_samples_per_second": 789.95,
+      "eval_steps_per_second": 3.872,
       "step": 120
     },
     {
@@ -156,7 +156,7 @@
       "eval_f1": 0.7678244972577698,
       "eval_loss": 0.6672889590263367,
       "eval_runtime": 0.5142,
-      "eval_samples_per_second": 793.515,
+      "eval_samples_per_second": 793.531,
       "eval_steps_per_second": 3.89,
       "step": 135
     },
@@ -172,9 +172,9 @@
       "eval_combined_score": 0.7382192221150756,
       "eval_f1": 0.7901639344262296,
       "eval_loss": 0.8091686367988586,
-      "eval_runtime": 0.5155,
-      "eval_samples_per_second": 791.402,
-      "eval_steps_per_second": 3.879,
+      "eval_runtime": 0.5146,
+      "eval_samples_per_second": 792.772,
+      "eval_steps_per_second": 3.886,
       "step": 150
     },
     {
@@ -190,7 +190,7 @@
       "eval_f1": 0.7934959349593496,
       "eval_loss": 0.9342193603515625,
       "eval_runtime": 0.5139,
-      "eval_samples_per_second": 793.922,
+      "eval_samples_per_second": 793.879,
       "eval_steps_per_second": 3.892,
       "step": 165
     },
@@ -206,19 +206,19 @@
       "eval_combined_score": 0.7324041246379707,
       "eval_f1": 0.7809847198641766,
       "eval_loss": 0.9707943201065063,
-      "eval_runtime": 0.5142,
-      "eval_samples_per_second": 793.529,
-      "eval_steps_per_second": 3.89,
+      "eval_runtime": 0.5166,
+      "eval_samples_per_second": 789.753,
+      "eval_steps_per_second": 3.871,
       "step": 180
     },
     {
       "epoch": 12.0,
       "step": 180,
       "total_flos": 5559706315653120.0,
-      "train_loss": 0.4964691546228197,
-      "train_runtime": 203.7797,
-      "train_samples_per_second": 899.991,
-      "train_steps_per_second": 3.68
+      "train_loss": 0.14563740226957533,
+      "train_runtime": 96.9183,
+      "train_samples_per_second": 1892.315,
+      "train_steps_per_second": 7.738
     }
   ],
   "max_steps": 750,