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": 0.5155,
+    "eval_runtime": 0.5364,
     "eval_samples": 408,
-    "eval_samples_per_second": 791.396,
-    "eval_steps_per_second": 3.879,
-    "train_loss": 0.14563740226957533,
-    "train_runtime": 96.9183,
+    "eval_samples_per_second": 760.588,
+    "eval_steps_per_second": 3.728,
+    "train_loss": 0.4964691546228197,
+    "train_runtime": 282.764,
     "train_samples": 3668,
-    "train_samples_per_second": 1892.315,
-    "train_steps_per_second": 7.738
+    "train_samples_per_second": 648.597,
+    "train_steps_per_second": 2.652
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7431372549019608,
     "eval_f1": 0.7999999999999999,
     "eval_loss": 0.6050820350646973,
-    "eval_runtime": 0.5155,
+    "eval_runtime": 0.5364,
     "eval_samples": 408,
-    "eval_samples_per_second": 791.396,
-    "eval_steps_per_second": 3.879
+    "eval_samples_per_second": 760.588,
+    "eval_steps_per_second": 3.728
 }

logs/events.out.tfevents.1677737995.serv-9223.249682.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f50ea8f611c8ea2600b186a8a0f9dace58aea64fa20b2be9baacf4404f4d569
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 12.0,
-    "train_loss": 0.14563740226957533,
-    "train_runtime": 96.9183,
+    "train_loss": 0.4964691546228197,
+    "train_runtime": 282.764,
     "train_samples": 3668,
-    "train_samples_per_second": 1892.315,
-    "train_steps_per_second": 7.738
+    "train_samples_per_second": 648.597,
+    "train_steps_per_second": 2.652
 }

trainer_state.json

@@ -19,9 +19,9 @@
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
       "eval_loss": 0.6242610216140747,
-      "eval_runtime": 0.5132,
-      "eval_samples_per_second": 794.982,
-      "eval_steps_per_second": 3.897,
+      "eval_runtime": 0.5234,
+      "eval_samples_per_second": 779.55,
+      "eval_steps_per_second": 3.821,
       "step": 15
     },
     {
@@ -36,9 +36,9 @@
       "eval_combined_score": 0.7563543936092956,
       "eval_f1": 0.8117283950617284,
       "eval_loss": 0.6174396872520447,
-      "eval_runtime": 0.511,
-      "eval_samples_per_second": 798.461,
-      "eval_steps_per_second": 3.914,
+      "eval_runtime": 0.5245,
+      "eval_samples_per_second": 777.948,
+      "eval_steps_per_second": 3.813,
       "step": 30
     },
     {
@@ -53,9 +53,9 @@
       "eval_combined_score": 0.7571301247771836,
       "eval_f1": 0.8181818181818181,
       "eval_loss": 0.6089469194412231,
-      "eval_runtime": 0.5125,
-      "eval_samples_per_second": 796.115,
-      "eval_steps_per_second": 3.903,
+      "eval_runtime": 0.5219,
+      "eval_samples_per_second": 781.803,
+      "eval_steps_per_second": 3.832,
       "step": 45
     },
     {
@@ -70,9 +70,9 @@
       "eval_combined_score": 0.7508428629183632,
       "eval_f1": 0.8129602356406479,
       "eval_loss": 0.606163740158081,
-      "eval_runtime": 0.5136,
-      "eval_samples_per_second": 794.368,
-      "eval_steps_per_second": 3.894,
+      "eval_runtime": 0.5254,
+      "eval_samples_per_second": 776.564,
+      "eval_steps_per_second": 3.807,
       "step": 60
     },
     {
@@ -87,9 +87,9 @@
       "eval_combined_score": 0.739911448450348,
       "eval_f1": 0.7935483870967743,
       "eval_loss": 0.6104128956794739,
-      "eval_runtime": 0.5141,
-      "eval_samples_per_second": 793.575,
-      "eval_steps_per_second": 3.89,
+      "eval_runtime": 0.5226,
+      "eval_samples_per_second": 780.687,
+      "eval_steps_per_second": 3.827,
       "step": 75
     },
     {
@@ -104,9 +104,9 @@
       "eval_combined_score": 0.7633269720101782,
       "eval_f1": 0.818320610687023,
       "eval_loss": 0.6184039115905762,
-      "eval_runtime": 0.5141,
-      "eval_samples_per_second": 793.682,
-      "eval_steps_per_second": 3.891,
+      "eval_runtime": 0.5242,
+      "eval_samples_per_second": 778.365,
+      "eval_steps_per_second": 3.816,
       "step": 90
     },
     {
@@ -121,9 +121,9 @@
       "eval_combined_score": 0.7431372549019608,
       "eval_f1": 0.7999999999999999,
       "eval_loss": 0.6050820350646973,
-      "eval_runtime": 0.5141,
-      "eval_samples_per_second": 793.592,
-      "eval_steps_per_second": 3.89,
+      "eval_runtime": 0.5657,
+      "eval_samples_per_second": 721.186,
+      "eval_steps_per_second": 3.535,
       "step": 105
     },
     {
@@ -138,9 +138,9 @@
       "eval_combined_score": 0.7477645971225257,
       "eval_f1": 0.8019017432646594,
       "eval_loss": 0.6560007929801941,
-      "eval_runtime": 0.5165,
-      "eval_samples_per_second": 789.95,
-      "eval_steps_per_second": 3.872,
+      "eval_runtime": 0.5247,
+      "eval_samples_per_second": 777.645,
+      "eval_steps_per_second": 3.812,
       "step": 120
     },
     {
@@ -155,9 +155,9 @@
       "eval_combined_score": 0.7282749937269242,
       "eval_f1": 0.7678244972577698,
       "eval_loss": 0.6672889590263367,
-      "eval_runtime": 0.5142,
-      "eval_samples_per_second": 793.531,
-      "eval_steps_per_second": 3.89,
+      "eval_runtime": 0.5245,
+      "eval_samples_per_second": 777.879,
+      "eval_steps_per_second": 3.813,
       "step": 135
     },
     {
@@ -172,9 +172,9 @@
       "eval_combined_score": 0.7382192221150756,
       "eval_f1": 0.7901639344262296,
       "eval_loss": 0.8091686367988586,
-      "eval_runtime": 0.5146,
-      "eval_samples_per_second": 792.772,
-      "eval_steps_per_second": 3.886,
+      "eval_runtime": 0.5259,
+      "eval_samples_per_second": 775.813,
+      "eval_steps_per_second": 3.803,
       "step": 150
     },
     {
@@ -189,9 +189,9 @@
       "eval_combined_score": 0.741110712577714,
       "eval_f1": 0.7934959349593496,
       "eval_loss": 0.9342193603515625,
-      "eval_runtime": 0.5139,
-      "eval_samples_per_second": 793.879,
-      "eval_steps_per_second": 3.892,
+      "eval_runtime": 0.5247,
+      "eval_samples_per_second": 777.527,
+      "eval_steps_per_second": 3.811,
       "step": 165
     },
     {
@@ -206,19 +206,19 @@
       "eval_combined_score": 0.7324041246379707,
       "eval_f1": 0.7809847198641766,
       "eval_loss": 0.9707943201065063,
-      "eval_runtime": 0.5166,
-      "eval_samples_per_second": 789.753,
-      "eval_steps_per_second": 3.871,
+      "eval_runtime": 0.5231,
+      "eval_samples_per_second": 779.911,
+      "eval_steps_per_second": 3.823,
       "step": 180
     },
     {
       "epoch": 12.0,
       "step": 180,
       "total_flos": 5559706315653120.0,
-      "train_loss": 0.14563740226957533,
-      "train_runtime": 96.9183,
-      "train_samples_per_second": 1892.315,
-      "train_steps_per_second": 7.738
+      "train_loss": 0.4964691546228197,
+      "train_runtime": 282.764,
+      "train_samples_per_second": 648.597,
+      "train_steps_per_second": 2.652
     }
   ],
   "max_steps": 750,