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 QQP
       type: glue
       config: qqp
       split: validation
@@ -21,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8781103141231759
+      value: 0.8679940638139995
     - name: F1
       type: f1
-      value: 0.8354371201496026
+      value: 0.8221652060910999
 ---
 
 <!-- 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_qqp
 
-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 QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4176
-- Accuracy: 0.8781
-- F1: 0.8354
-- Combined Score: 0.8568
+- Loss: 0.3039
+- Accuracy: 0.8680
+- F1: 0.8222
+- Combined Score: 0.8451
 
 ## Model description
 

all_results.json

@@ -4,13 +4,13 @@
     "eval_combined_score": 0.8450796349525497,
     "eval_f1": 0.8221652060910999,
     "eval_loss": 0.3039037883281708,
-    "eval_runtime": 49.9948,
+    "eval_runtime": 51.5942,
     "eval_samples": 40430,
-    "eval_samples_per_second": 808.685,
-    "eval_steps_per_second": 3.16,
+    "eval_samples_per_second": 783.616,
+    "eval_steps_per_second": 3.062,
     "train_loss": 0.20186867962071328,
-    "train_runtime": 10978.3186,
+    "train_runtime": 11093.9393,
     "train_samples": 363846,
-    "train_samples_per_second": 1657.112,
-    "train_steps_per_second": 6.476
+    "train_samples_per_second": 1639.841,
+    "train_steps_per_second": 6.409
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.8450796349525497,
     "eval_f1": 0.8221652060910999,
     "eval_loss": 0.3039037883281708,
-    "eval_runtime": 49.9948,
+    "eval_runtime": 51.5942,
     "eval_samples": 40430,
-    "eval_samples_per_second": 808.685,
-    "eval_steps_per_second": 3.16
+    "eval_samples_per_second": 783.616,
+    "eval_steps_per_second": 3.062
 }

logs/events.out.tfevents.1677752824.serv-9223.249682.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a7dc67c7e914784fbdf13812bf95520195b2353a0df158f90cd8b2228ed409
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.0,
     "train_loss": 0.20186867962071328,
-    "train_runtime": 10978.3186,
+    "train_runtime": 11093.9393,
     "train_samples": 363846,
-    "train_samples_per_second": 1657.112,
-    "train_steps_per_second": 6.476
+    "train_samples_per_second": 1639.841,
+    "train_steps_per_second": 6.409
 }

trainer_state.json

@@ -19,9 +19,9 @@
       "eval_combined_score": 0.8116115925137688,
       "eval_f1": 0.794655289900157,
       "eval_loss": 0.3665443956851959,
-      "eval_runtime": 50.6077,
-      "eval_samples_per_second": 798.89,
-      "eval_steps_per_second": 3.122,
+      "eval_runtime": 51.3292,
+      "eval_samples_per_second": 787.661,
+      "eval_steps_per_second": 3.078,
       "step": 1422
     },
     {
@@ -36,9 +36,9 @@
       "eval_combined_score": 0.8398193588062908,
       "eval_f1": 0.8171108917407043,
       "eval_loss": 0.3111252784729004,
-      "eval_runtime": 50.4355,
-      "eval_samples_per_second": 801.618,
-      "eval_steps_per_second": 3.133,
+      "eval_runtime": 51.3204,
+      "eval_samples_per_second": 787.796,
+      "eval_steps_per_second": 3.079,
       "step": 2844
     },
     {
@@ -53,9 +53,9 @@
       "eval_combined_score": 0.8450796349525497,
       "eval_f1": 0.8221652060910999,
       "eval_loss": 0.3039037883281708,
-      "eval_runtime": 50.4592,
-      "eval_samples_per_second": 801.241,
-      "eval_steps_per_second": 3.131,
+      "eval_runtime": 51.3838,
+      "eval_samples_per_second": 786.824,
+      "eval_steps_per_second": 3.075,
       "step": 4266
     },
     {
@@ -70,9 +70,9 @@
       "eval_combined_score": 0.8531681858438971,
       "eval_f1": 0.8326781970649895,
       "eval_loss": 0.32322049140930176,
-      "eval_runtime": 50.5899,
-      "eval_samples_per_second": 799.171,
-      "eval_steps_per_second": 3.123,
+      "eval_runtime": 51.2318,
+      "eval_samples_per_second": 789.158,
+      "eval_steps_per_second": 3.084,
       "step": 5688
     },
     {
@@ -87,9 +87,9 @@
       "eval_combined_score": 0.8455726540359703,
       "eval_f1": 0.8194163938992965,
       "eval_loss": 0.3742031753063202,
-      "eval_runtime": 50.4756,
-      "eval_samples_per_second": 800.98,
-      "eval_steps_per_second": 3.13,
+      "eval_runtime": 51.195,
+      "eval_samples_per_second": 789.725,
+      "eval_steps_per_second": 3.086,
       "step": 7110
     },
     {
@@ -104,9 +104,9 @@
       "eval_combined_score": 0.8431165534906415,
       "eval_f1": 0.8146031292419805,
       "eval_loss": 0.40085598826408386,
-      "eval_runtime": 50.493,
-      "eval_samples_per_second": 800.705,
-      "eval_steps_per_second": 3.129,
+      "eval_runtime": 51.3501,
+      "eval_samples_per_second": 787.341,
+      "eval_steps_per_second": 3.077,
       "step": 8532
     },
     {
@@ -121,9 +121,9 @@
       "eval_combined_score": 0.8499536553423827,
       "eval_f1": 0.8299592523122696,
       "eval_loss": 0.4470857083797455,
-      "eval_runtime": 50.5119,
-      "eval_samples_per_second": 800.405,
-      "eval_steps_per_second": 3.128,
+      "eval_runtime": 51.3929,
+      "eval_samples_per_second": 786.684,
+      "eval_steps_per_second": 3.074,
       "step": 9954
     },
     {
@@ -138,9 +138,9 @@
       "eval_combined_score": 0.8567737171363892,
       "eval_f1": 0.8354371201496026,
       "eval_loss": 0.4176293909549713,
-      "eval_runtime": 50.4947,
-      "eval_samples_per_second": 800.677,
-      "eval_steps_per_second": 3.129,
+      "eval_runtime": 51.3123,
+      "eval_samples_per_second": 787.92,
+      "eval_steps_per_second": 3.079,
       "step": 11376
     },
     {
@@ -148,9 +148,9 @@
       "step": 11376,
       "total_flos": 3.676621197992264e+17,
       "train_loss": 0.20186867962071328,
-      "train_runtime": 10978.3186,
-      "train_samples_per_second": 1657.112,
-      "train_steps_per_second": 6.476
+      "train_runtime": 11093.9393,
+      "train_samples_per_second": 1639.841,
+      "train_steps_per_second": 6.409
     }
   ],
   "max_steps": 71100,