End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE RTE
       type: glue
       config: rte
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5234657039711191
+      value: 0.5487364620938628
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8160
-- Accuracy: 0.5235
+- Loss: 0.6896
+- Accuracy: 0.5487
 
 ## Model description
 

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 12.0,
     "eval_accuracy": 0.5487364620938628,
     "eval_loss": 0.6896100044250488,
-    "eval_runtime": 0.3599,
+    "eval_runtime": 0.335,
     "eval_samples": 277,
-    "eval_samples_per_second": 769.561,
-    "eval_steps_per_second": 5.556,
+    "eval_samples_per_second": 826.972,
+    "eval_steps_per_second": 5.971,
     "train_loss": 0.660737669467926,
-    "train_runtime": 158.6499,
+    "train_runtime": 170.3259,
     "train_samples": 2490,
-    "train_samples_per_second": 784.747,
-    "train_steps_per_second": 3.152
+    "train_samples_per_second": 730.951,
+    "train_steps_per_second": 2.936
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 12.0,
     "eval_accuracy": 0.5487364620938628,
     "eval_loss": 0.6896100044250488,
-    "eval_runtime": 0.3599,
+    "eval_runtime": 0.335,
     "eval_samples": 277,
-    "eval_samples_per_second": 769.561,
-    "eval_steps_per_second": 5.556
+    "eval_samples_per_second": 826.972,
+    "eval_steps_per_second": 5.971
 }

logs/events.out.tfevents.1677754087.serv-3317.65116.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e5b72f4149e24f6712ddbcaeb2e85d1ebd5de496e6206690a64546dc1477aa
+size 357

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 12.0,
     "train_loss": 0.660737669467926,
-    "train_runtime": 158.6499,
+    "train_runtime": 170.3259,
     "train_samples": 2490,
-    "train_samples_per_second": 784.747,
-    "train_steps_per_second": 3.152
+    "train_samples_per_second": 730.951,
+    "train_steps_per_second": 2.936
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.4548736462093863,
       "eval_loss": 0.7174825668334961,
-      "eval_runtime": 0.3347,
-      "eval_samples_per_second": 827.629,
-      "eval_steps_per_second": 5.976,
+      "eval_runtime": 0.3321,
+      "eval_samples_per_second": 834.009,
+      "eval_steps_per_second": 6.022,
       "step": 10
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.4729241877256318,
       "eval_loss": 0.7052958011627197,
-      "eval_runtime": 0.3353,
-      "eval_samples_per_second": 826.133,
-      "eval_steps_per_second": 5.965,
+      "eval_runtime": 0.3299,
+      "eval_samples_per_second": 839.582,
+      "eval_steps_per_second": 6.062,
       "step": 20
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.4584837545126354,
       "eval_loss": 0.6975917220115662,
-      "eval_runtime": 0.3314,
-      "eval_samples_per_second": 835.799,
-      "eval_steps_per_second": 6.035,
+      "eval_runtime": 0.3315,
+      "eval_samples_per_second": 835.597,
+      "eval_steps_per_second": 6.033,
       "step": 30
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.4657039711191336,
       "eval_loss": 0.726104199886322,
-      "eval_runtime": 0.3334,
-      "eval_samples_per_second": 830.944,
-      "eval_steps_per_second": 6.0,
+      "eval_runtime": 0.3329,
+      "eval_samples_per_second": 832.075,
+      "eval_steps_per_second": 6.008,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.49458483754512633,
       "eval_loss": 0.7142461538314819,
-      "eval_runtime": 0.3346,
-      "eval_samples_per_second": 827.866,
-      "eval_steps_per_second": 5.977,
+      "eval_runtime": 0.3322,
+      "eval_samples_per_second": 833.768,
+      "eval_steps_per_second": 6.02,
       "step": 50
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.48014440433212996,
       "eval_loss": 0.694332480430603,
-      "eval_runtime": 0.3341,
-      "eval_samples_per_second": 829.027,
-      "eval_steps_per_second": 5.986,
+      "eval_runtime": 0.3388,
+      "eval_samples_per_second": 817.49,
+      "eval_steps_per_second": 5.902,
       "step": 60
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.5487364620938628,
       "eval_loss": 0.6896100044250488,
-      "eval_runtime": 0.3351,
-      "eval_samples_per_second": 826.637,
-      "eval_steps_per_second": 5.968,
+      "eval_runtime": 0.3322,
+      "eval_samples_per_second": 833.85,
+      "eval_steps_per_second": 6.021,
       "step": 70
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_accuracy": 0.516245487364621,
       "eval_loss": 0.7151486277580261,
-      "eval_runtime": 0.3354,
-      "eval_samples_per_second": 825.95,
-      "eval_steps_per_second": 5.964,
+      "eval_runtime": 0.3309,
+      "eval_samples_per_second": 837.215,
+      "eval_steps_per_second": 6.045,
       "step": 80
     },
     {
@@ -137,9 +137,9 @@
       "epoch": 9.0,
       "eval_accuracy": 0.5270758122743683,
       "eval_loss": 0.7244121432304382,
-      "eval_runtime": 0.3343,
-      "eval_samples_per_second": 828.517,
-      "eval_steps_per_second": 5.982,
+      "eval_runtime": 0.3318,
+      "eval_samples_per_second": 834.768,
+      "eval_steps_per_second": 6.027,
       "step": 90
     },
     {
@@ -152,9 +152,9 @@
       "epoch": 10.0,
       "eval_accuracy": 0.4729241877256318,
       "eval_loss": 0.7570322751998901,
-      "eval_runtime": 0.3345,
-      "eval_samples_per_second": 828.025,
-      "eval_steps_per_second": 5.979,
+      "eval_runtime": 0.3338,
+      "eval_samples_per_second": 829.795,
+      "eval_steps_per_second": 5.991,
       "step": 100
     },
     {
@@ -167,9 +167,9 @@
       "epoch": 11.0,
       "eval_accuracy": 0.5379061371841155,
       "eval_loss": 0.7605395913124084,
-      "eval_runtime": 0.3342,
-      "eval_samples_per_second": 828.846,
-      "eval_steps_per_second": 5.984,
+      "eval_runtime": 0.334,
+      "eval_samples_per_second": 829.304,
+      "eval_steps_per_second": 5.988,
       "step": 110
     },
     {
@@ -182,9 +182,9 @@
       "epoch": 12.0,
       "eval_accuracy": 0.5234657039711191,
       "eval_loss": 0.8159566521644592,
-      "eval_runtime": 0.335,
-      "eval_samples_per_second": 826.903,
-      "eval_steps_per_second": 5.97,
+      "eval_runtime": 0.3341,
+      "eval_samples_per_second": 829.158,
+      "eval_steps_per_second": 5.987,
       "step": 120
     },
     {
@@ -192,9 +192,9 @@
       "step": 120,
       "total_flos": 3721656539283456.0,
       "train_loss": 0.660737669467926,
-      "train_runtime": 158.6499,
-      "train_samples_per_second": 784.747,
-      "train_steps_per_second": 3.152
+      "train_runtime": 170.3259,
+      "train_samples_per_second": 730.951,
+      "train_steps_per_second": 2.936
     }
   ],
   "max_steps": 500,