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: 0.49097472924187724
+      value: 0.5451263537906137
 ---
 
 <!-- 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. -->
 
 # hBERTv1_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8230
-- Accuracy: 0.4910
+- Loss: 0.6896
+- Accuracy: 0.5451
 
 ## Model description
 

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 6.0,
     "eval_accuracy": 0.5451263537906137,
     "eval_loss": 0.6895958781242371,
-    "eval_runtime": 0.3771,
+    "eval_runtime": 0.3851,
     "eval_samples": 277,
-    "eval_samples_per_second": 734.458,
-    "eval_steps_per_second": 5.303,
+    "eval_samples_per_second": 719.226,
+    "eval_steps_per_second": 5.193,
     "train_loss": 0.6846395254135131,
-    "train_runtime": 78.7517,
+    "train_runtime": 109.2886,
     "train_samples": 2490,
-    "train_samples_per_second": 1580.919,
-    "train_steps_per_second": 6.349
+    "train_samples_per_second": 1139.185,
+    "train_steps_per_second": 4.575
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "eval_accuracy": 0.5451263537906137,
     "eval_loss": 0.6895958781242371,
-    "eval_runtime": 0.3771,
+    "eval_runtime": 0.3851,
     "eval_samples": 277,
-    "eval_samples_per_second": 734.458,
-    "eval_steps_per_second": 5.303
+    "eval_samples_per_second": 719.226,
+    "eval_steps_per_second": 5.193
 }

logs/events.out.tfevents.1677753258.serv-9223.249682.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f834d0a7871c23703a5e176626a04fc606740a1f36959e3e3d17608bb196e61
+size 357

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.0,
     "train_loss": 0.6846395254135131,
-    "train_runtime": 78.7517,
+    "train_runtime": 109.2886,
     "train_samples": 2490,
-    "train_samples_per_second": 1580.919,
-    "train_steps_per_second": 6.349
+    "train_samples_per_second": 1139.185,
+    "train_steps_per_second": 4.575
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5451263537906137,
       "eval_loss": 0.6895958781242371,
-      "eval_runtime": 0.3609,
-      "eval_samples_per_second": 767.565,
-      "eval_steps_per_second": 5.542,
+      "eval_runtime": 0.3617,
+      "eval_samples_per_second": 765.769,
+      "eval_steps_per_second": 5.529,
       "step": 10
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.4729241877256318,
       "eval_loss": 0.7013799548149109,
-      "eval_runtime": 0.3547,
-      "eval_samples_per_second": 780.85,
-      "eval_steps_per_second": 5.638,
+      "eval_runtime": 0.363,
+      "eval_samples_per_second": 763.011,
+      "eval_steps_per_second": 5.509,
       "step": 20
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.4729241877256318,
       "eval_loss": 0.6982845067977905,
-      "eval_runtime": 0.3536,
-      "eval_samples_per_second": 783.333,
-      "eval_steps_per_second": 5.656,
+      "eval_runtime": 0.3662,
+      "eval_samples_per_second": 756.401,
+      "eval_steps_per_second": 5.461,
       "step": 30
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.5126353790613718,
       "eval_loss": 0.7091580033302307,
-      "eval_runtime": 0.3613,
-      "eval_samples_per_second": 766.716,
-      "eval_steps_per_second": 5.536,
+      "eval_runtime": 0.3627,
+      "eval_samples_per_second": 763.647,
+      "eval_steps_per_second": 5.514,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.5126353790613718,
       "eval_loss": 0.713951826095581,
-      "eval_runtime": 0.3543,
-      "eval_samples_per_second": 781.867,
-      "eval_steps_per_second": 5.645,
+      "eval_runtime": 0.3618,
+      "eval_samples_per_second": 765.669,
+      "eval_steps_per_second": 5.528,
       "step": 50
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.49097472924187724,
       "eval_loss": 0.8229976892471313,
-      "eval_runtime": 0.3532,
-      "eval_samples_per_second": 784.179,
-      "eval_steps_per_second": 5.662,
+      "eval_runtime": 0.3616,
+      "eval_samples_per_second": 766.085,
+      "eval_steps_per_second": 5.531,
       "step": 60
     },
     {
@@ -102,9 +102,9 @@
       "step": 60,
       "total_flos": 1887086894383104.0,
       "train_loss": 0.6846395254135131,
-      "train_runtime": 78.7517,
-      "train_samples_per_second": 1580.919,
-      "train_steps_per_second": 6.349
+      "train_runtime": 109.2886,
+      "train_samples_per_second": 1139.185,
+      "train_steps_per_second": 4.575
     }
   ],
   "max_steps": 500,