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: 0.8760079149146673
+      value: 0.8651001731387583
     - name: F1
       type: f1
-      value: 0.8322233006459385
+      value: 0.8160291438979962
 ---
 
 <!-- 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. -->
 
 # hBERTv2_qqp
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4723
-- Accuracy: 0.8760
-- F1: 0.8322
-- Combined Score: 0.8541
+- Loss: 0.3129
+- Accuracy: 0.8651
+- F1: 0.8160
+- Combined Score: 0.8406
 
 ## Model description
 

all_results.json

@@ -4,13 +4,13 @@
     "eval_combined_score": 0.8405646585183773,
     "eval_f1": 0.8160291438979962,
     "eval_loss": 0.31285223364830017,
-    "eval_runtime": 47.3472,
+    "eval_runtime": 47.1633,
     "eval_samples": 40430,
-    "eval_samples_per_second": 853.905,
-    "eval_steps_per_second": 3.337,
+    "eval_samples_per_second": 857.234,
+    "eval_steps_per_second": 3.35,
     "train_loss": 0.18701694115640075,
-    "train_runtime": 10256.0914,
+    "train_runtime": 10469.4901,
     "train_samples": 363846,
-    "train_samples_per_second": 1773.804,
-    "train_steps_per_second": 6.932
+    "train_samples_per_second": 1737.649,
+    "train_steps_per_second": 6.791
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.8405646585183773,
     "eval_f1": 0.8160291438979962,
     "eval_loss": 0.31285223364830017,
-    "eval_runtime": 47.3472,
+    "eval_runtime": 47.1633,
     "eval_samples": 40430,
-    "eval_samples_per_second": 853.905,
-    "eval_steps_per_second": 3.337
+    "eval_samples_per_second": 857.234,
+    "eval_steps_per_second": 3.35
 }

logs/events.out.tfevents.1677753647.serv-3317.65116.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92519fc133b9b58e3f1f9dc8107b0a48f71144ce5368cf2bf279b6f2104ffd65
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.0,
     "train_loss": 0.18701694115640075,
-    "train_runtime": 10256.0914,
+    "train_runtime": 10469.4901,
     "train_samples": 363846,
-    "train_samples_per_second": 1773.804,
-    "train_steps_per_second": 6.932
+    "train_samples_per_second": 1737.649,
+    "train_steps_per_second": 6.791
 }

trainer_state.json

@@ -19,9 +19,9 @@
       "eval_combined_score": 0.8083731607119745,
       "eval_f1": 0.7915917332468528,
       "eval_loss": 0.38297852873802185,
-      "eval_runtime": 47.7223,
-      "eval_samples_per_second": 847.193,
-      "eval_steps_per_second": 3.311,
+      "eval_runtime": 47.1453,
+      "eval_samples_per_second": 857.561,
+      "eval_steps_per_second": 3.351,
       "step": 1422
     },
     {
@@ -36,9 +36,9 @@
       "eval_combined_score": 0.8131408666041042,
       "eval_f1": 0.7905656807718988,
       "eval_loss": 0.35074833035469055,
-      "eval_runtime": 47.7241,
-      "eval_samples_per_second": 847.161,
-      "eval_steps_per_second": 3.311,
+      "eval_runtime": 47.1716,
+      "eval_samples_per_second": 857.083,
+      "eval_steps_per_second": 3.349,
       "step": 2844
     },
     {
@@ -53,9 +53,9 @@
       "eval_combined_score": 0.8405646585183773,
       "eval_f1": 0.8160291438979962,
       "eval_loss": 0.31285223364830017,
-      "eval_runtime": 47.7786,
-      "eval_samples_per_second": 846.194,
-      "eval_steps_per_second": 3.307,
+      "eval_runtime": 47.2025,
+      "eval_samples_per_second": 856.522,
+      "eval_steps_per_second": 3.347,
       "step": 4266
     },
     {
@@ -70,9 +70,9 @@
       "eval_combined_score": 0.8514036858419307,
       "eval_f1": 0.8327603768780241,
       "eval_loss": 0.35401350259780884,
-      "eval_runtime": 47.7873,
-      "eval_samples_per_second": 846.041,
-      "eval_steps_per_second": 3.306,
+      "eval_runtime": 47.169,
+      "eval_samples_per_second": 857.131,
+      "eval_steps_per_second": 3.35,
       "step": 5688
     },
     {
@@ -87,9 +87,9 @@
       "eval_combined_score": 0.8500331546757744,
       "eval_f1": 0.8266802099204335,
       "eval_loss": 0.4275738596916199,
-      "eval_runtime": 47.709,
-      "eval_samples_per_second": 847.43,
-      "eval_steps_per_second": 3.312,
+      "eval_runtime": 47.244,
+      "eval_samples_per_second": 855.769,
+      "eval_steps_per_second": 3.344,
       "step": 7110
     },
     {
@@ -104,9 +104,9 @@
       "eval_combined_score": 0.8520305093406406,
       "eval_f1": 0.8292156068583774,
       "eval_loss": 0.40782323479652405,
-      "eval_runtime": 47.8778,
-      "eval_samples_per_second": 844.441,
-      "eval_steps_per_second": 3.3,
+      "eval_runtime": 47.2138,
+      "eval_samples_per_second": 856.317,
+      "eval_steps_per_second": 3.346,
       "step": 8532
     },
     {
@@ -121,9 +121,9 @@
       "eval_combined_score": 0.855563447307603,
       "eval_f1": 0.8344511587754831,
       "eval_loss": 0.4068982005119324,
-      "eval_runtime": 47.8891,
-      "eval_samples_per_second": 844.242,
-      "eval_steps_per_second": 3.299,
+      "eval_runtime": 47.2202,
+      "eval_samples_per_second": 856.201,
+      "eval_steps_per_second": 3.346,
       "step": 9954
     },
     {
@@ -138,9 +138,9 @@
       "eval_combined_score": 0.8541156077803029,
       "eval_f1": 0.8322233006459385,
       "eval_loss": 0.4722978472709656,
-      "eval_runtime": 47.7389,
-      "eval_samples_per_second": 846.898,
-      "eval_steps_per_second": 3.31,
+      "eval_runtime": 46.9884,
+      "eval_samples_per_second": 860.425,
+      "eval_steps_per_second": 3.363,
       "step": 11376
     },
     {
@@ -148,9 +148,9 @@
       "step": 11376,
       "total_flos": 3.625461609146614e+17,
       "train_loss": 0.18701694115640075,
-      "train_runtime": 10256.0914,
-      "train_samples_per_second": 1773.804,
-      "train_steps_per_second": 6.932
+      "train_runtime": 10469.4901,
+      "train_samples_per_second": 1737.649,
+      "train_steps_per_second": 6.791
     }
   ],
   "max_steps": 71100,