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 SST2
       type: glue
       config: sst2
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6980
+- Loss: 0.6964
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 14.0,
     "eval_accuracy": 0.5091743119266054,
     "eval_loss": 0.6963669061660767,
-    "eval_runtime": 1.0895,
+    "eval_runtime": 1.0275,
     "eval_samples": 872,
-    "eval_samples_per_second": 800.333,
-    "eval_steps_per_second": 3.671,
+    "eval_samples_per_second": 848.683,
+    "eval_steps_per_second": 3.893,
     "train_loss": 0.6872374216715494,
-    "train_runtime": 3475.6313,
+    "train_runtime": 3525.1846,
     "train_samples": 67349,
-    "train_samples_per_second": 968.874,
-    "train_steps_per_second": 3.798
+    "train_samples_per_second": 955.255,
+    "train_steps_per_second": 3.744
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 14.0,
     "eval_accuracy": 0.5091743119266054,
     "eval_loss": 0.6963669061660767,
-    "eval_runtime": 1.0895,
+    "eval_runtime": 1.0275,
     "eval_samples": 872,
-    "eval_samples_per_second": 800.333,
-    "eval_steps_per_second": 3.671
+    "eval_samples_per_second": 848.683,
+    "eval_steps_per_second": 3.893
 }

logs/events.out.tfevents.1677757702.serv-3317.65116.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bde467b638e79fae02e71b35ba6b6e328139e28de1315c4b6e6837b09bfa8d
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 14.0,
     "train_loss": 0.6872374216715494,
-    "train_runtime": 3475.6313,
+    "train_runtime": 3525.1846,
     "train_samples": 67349,
-    "train_samples_per_second": 968.874,
-    "train_steps_per_second": 3.798
+    "train_samples_per_second": 955.255,
+    "train_steps_per_second": 3.744
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6998637914657593,
-      "eval_runtime": 1.0361,
-      "eval_samples_per_second": 841.637,
-      "eval_steps_per_second": 3.861,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 848.118,
+      "eval_steps_per_second": 3.89,
       "step": 264
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6977964639663696,
-      "eval_runtime": 1.037,
-      "eval_samples_per_second": 840.878,
-      "eval_steps_per_second": 3.857,
+      "eval_runtime": 1.0265,
+      "eval_samples_per_second": 849.502,
+      "eval_steps_per_second": 3.897,
       "step": 528
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.698425829410553,
-      "eval_runtime": 1.0359,
-      "eval_samples_per_second": 841.809,
-      "eval_steps_per_second": 3.862,
+      "eval_runtime": 1.0241,
+      "eval_samples_per_second": 851.447,
+      "eval_steps_per_second": 3.906,
       "step": 792
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.69902503490448,
-      "eval_runtime": 1.0372,
-      "eval_samples_per_second": 840.699,
-      "eval_steps_per_second": 3.856,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 849.176,
+      "eval_steps_per_second": 3.895,
       "step": 1056
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6974067091941833,
-      "eval_runtime": 1.0355,
-      "eval_samples_per_second": 842.083,
-      "eval_steps_per_second": 3.863,
+      "eval_runtime": 1.0288,
+      "eval_samples_per_second": 847.597,
+      "eval_steps_per_second": 3.888,
       "step": 1320
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6980025172233582,
-      "eval_runtime": 1.0358,
-      "eval_samples_per_second": 841.851,
-      "eval_steps_per_second": 3.862,
+      "eval_runtime": 1.0196,
+      "eval_samples_per_second": 855.224,
+      "eval_steps_per_second": 3.923,
       "step": 1584
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6984168887138367,
-      "eval_runtime": 1.0568,
-      "eval_samples_per_second": 825.136,
-      "eval_steps_per_second": 3.785,
+      "eval_runtime": 1.0285,
+      "eval_samples_per_second": 847.819,
+      "eval_steps_per_second": 3.889,
       "step": 1848
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6974700093269348,
-      "eval_runtime": 1.0448,
-      "eval_samples_per_second": 834.6,
-      "eval_steps_per_second": 3.828,
+      "eval_runtime": 1.0196,
+      "eval_samples_per_second": 855.241,
+      "eval_steps_per_second": 3.923,
       "step": 2112
     },
     {
@@ -137,9 +137,9 @@
       "epoch": 9.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6963669061660767,
-      "eval_runtime": 1.037,
-      "eval_samples_per_second": 840.85,
-      "eval_steps_per_second": 3.857,
+      "eval_runtime": 1.0241,
+      "eval_samples_per_second": 851.456,
+      "eval_steps_per_second": 3.906,
       "step": 2376
     },
     {
@@ -152,9 +152,9 @@
       "epoch": 10.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6977964639663696,
-      "eval_runtime": 1.0355,
-      "eval_samples_per_second": 842.138,
-      "eval_steps_per_second": 3.863,
+      "eval_runtime": 1.022,
+      "eval_samples_per_second": 853.257,
+      "eval_steps_per_second": 3.914,
       "step": 2640
     },
     {
@@ -167,9 +167,9 @@
       "epoch": 11.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6980271935462952,
-      "eval_runtime": 1.0325,
-      "eval_samples_per_second": 844.563,
-      "eval_steps_per_second": 3.874,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 849.06,
+      "eval_steps_per_second": 3.895,
       "step": 2904
     },
     {
@@ -182,9 +182,9 @@
       "epoch": 12.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.700083315372467,
-      "eval_runtime": 1.0347,
-      "eval_samples_per_second": 842.747,
-      "eval_steps_per_second": 3.866,
+      "eval_runtime": 1.0275,
+      "eval_samples_per_second": 848.679,
+      "eval_steps_per_second": 3.893,
       "step": 3168
     },
     {
@@ -197,9 +197,9 @@
       "epoch": 13.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6965734958648682,
-      "eval_runtime": 1.032,
-      "eval_samples_per_second": 844.972,
-      "eval_steps_per_second": 3.876,
+      "eval_runtime": 1.0183,
+      "eval_samples_per_second": 856.305,
+      "eval_steps_per_second": 3.928,
       "step": 3432
     },
     {
@@ -212,9 +212,9 @@
       "epoch": 14.0,
       "eval_accuracy": 0.5091743119266054,
       "eval_loss": 0.6980003118515015,
-      "eval_runtime": 1.0332,
-      "eval_samples_per_second": 843.945,
-      "eval_steps_per_second": 3.871,
+      "eval_runtime": 1.0301,
+      "eval_samples_per_second": 846.51,
+      "eval_steps_per_second": 3.883,
       "step": 3696
     },
     {
@@ -222,9 +222,9 @@
       "step": 3696,
       "total_flos": 1.1743968521879552e+17,
       "train_loss": 0.6872374216715494,
-      "train_runtime": 3475.6313,
-      "train_samples_per_second": 968.874,
-      "train_steps_per_second": 3.798
+      "train_runtime": 3525.1846,
+      "train_samples_per_second": 955.255,
+      "train_steps_per_second": 3.744
     }
   ],
   "max_steps": 13200,