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 QNLI
       type: glue
       config: qnli
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.4946000366099213
+      value: 0.5053999633900788
 ---
 
 <!-- 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_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6931
-- Accuracy: 0.4946
+- Loss: 0.6930
+- Accuracy: 0.5054
 
 ## Model description
 

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 13.0,
     "eval_accuracy": 0.5053999633900788,
     "eval_loss": 0.6929702162742615,
-    "eval_runtime": 6.4189,
+    "eval_runtime": 6.3354,
     "eval_samples": 5463,
-    "eval_samples_per_second": 851.081,
-    "eval_steps_per_second": 3.427,
+    "eval_samples_per_second": 862.297,
+    "eval_steps_per_second": 3.473,
     "train_loss": 0.6936567925601694,
-    "train_runtime": 4888.5149,
+    "train_runtime": 4977.7257,
     "train_samples": 104743,
-    "train_samples_per_second": 1071.317,
-    "train_steps_per_second": 4.194
+    "train_samples_per_second": 1052.117,
+    "train_steps_per_second": 4.118
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 13.0,
     "eval_accuracy": 0.5053999633900788,
     "eval_loss": 0.6929702162742615,
-    "eval_runtime": 6.4189,
+    "eval_runtime": 6.3354,
     "eval_samples": 5463,
-    "eval_samples_per_second": 851.081,
-    "eval_steps_per_second": 3.427
+    "eval_samples_per_second": 862.297,
+    "eval_steps_per_second": 3.473
 }

logs/events.out.tfevents.1677742931.serv-3317.65116.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7a91a9b610faac4f1fb0b2f5718622890ee9014c5760b6a1c7a97bb241a93d
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 13.0,
     "train_loss": 0.6936567925601694,
-    "train_runtime": 4888.5149,
+    "train_runtime": 4977.7257,
     "train_samples": 104743,
-    "train_samples_per_second": 1071.317,
-    "train_steps_per_second": 4.194
+    "train_samples_per_second": 1052.117,
+    "train_steps_per_second": 4.118
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6952407360076904,
-      "eval_runtime": 6.4563,
-      "eval_samples_per_second": 846.145,
-      "eval_steps_per_second": 3.408,
+      "eval_runtime": 6.3931,
+      "eval_samples_per_second": 854.51,
+      "eval_steps_per_second": 3.441,
       "step": 410
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.4946000366099213,
       "eval_loss": 0.6931500434875488,
-      "eval_runtime": 6.454,
-      "eval_samples_per_second": 846.448,
-      "eval_steps_per_second": 3.409,
+      "eval_runtime": 6.373,
+      "eval_samples_per_second": 857.211,
+      "eval_steps_per_second": 3.452,
       "step": 820
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6933012008666992,
-      "eval_runtime": 6.4678,
-      "eval_samples_per_second": 844.646,
-      "eval_steps_per_second": 3.401,
+      "eval_runtime": 6.3501,
+      "eval_samples_per_second": 860.304,
+      "eval_steps_per_second": 3.465,
       "step": 1230
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6930809617042542,
-      "eval_runtime": 6.4901,
-      "eval_samples_per_second": 841.738,
-      "eval_steps_per_second": 3.39,
+      "eval_runtime": 6.372,
+      "eval_samples_per_second": 857.351,
+      "eval_steps_per_second": 3.453,
       "step": 1640
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6931115388870239,
-      "eval_runtime": 6.4532,
-      "eval_samples_per_second": 846.551,
-      "eval_steps_per_second": 3.409,
+      "eval_runtime": 6.375,
+      "eval_samples_per_second": 856.943,
+      "eval_steps_per_second": 3.451,
       "step": 2050
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6930229663848877,
-      "eval_runtime": 6.4635,
-      "eval_samples_per_second": 845.204,
-      "eval_steps_per_second": 3.404,
+      "eval_runtime": 6.349,
+      "eval_samples_per_second": 860.452,
+      "eval_steps_per_second": 3.465,
       "step": 2460
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6931431889533997,
-      "eval_runtime": 6.4426,
-      "eval_samples_per_second": 847.944,
-      "eval_steps_per_second": 3.415,
+      "eval_runtime": 6.3713,
+      "eval_samples_per_second": 857.434,
+      "eval_steps_per_second": 3.453,
       "step": 2870
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6929702162742615,
-      "eval_runtime": 6.4464,
-      "eval_samples_per_second": 847.453,
-      "eval_steps_per_second": 3.413,
+      "eval_runtime": 6.3689,
+      "eval_samples_per_second": 857.766,
+      "eval_steps_per_second": 3.454,
       "step": 3280
     },
     {
@@ -137,9 +137,9 @@
       "epoch": 9.0,
       "eval_accuracy": 0.4946000366099213,
       "eval_loss": 0.6933699250221252,
-      "eval_runtime": 6.4536,
-      "eval_samples_per_second": 846.499,
-      "eval_steps_per_second": 3.409,
+      "eval_runtime": 6.3817,
+      "eval_samples_per_second": 856.035,
+      "eval_steps_per_second": 3.447,
       "step": 3690
     },
     {
@@ -152,9 +152,9 @@
       "epoch": 10.0,
       "eval_accuracy": 0.5053999633900788,
       "eval_loss": 0.6930176615715027,
-      "eval_runtime": 6.4577,
-      "eval_samples_per_second": 845.972,
-      "eval_steps_per_second": 3.407,
+      "eval_runtime": 6.3795,
+      "eval_samples_per_second": 856.338,
+      "eval_steps_per_second": 3.449,
       "step": 4100
     },
     {
@@ -167,9 +167,9 @@
       "epoch": 11.0,
       "eval_accuracy": 0.4946000366099213,
       "eval_loss": 0.6931337118148804,
-      "eval_runtime": 6.4617,
-      "eval_samples_per_second": 845.439,
-      "eval_steps_per_second": 3.405,
+      "eval_runtime": 6.3738,
+      "eval_samples_per_second": 857.109,
+      "eval_steps_per_second": 3.452,
       "step": 4510
     },
     {
@@ -182,9 +182,9 @@
       "epoch": 12.0,
       "eval_accuracy": 0.4946000366099213,
       "eval_loss": 0.6934068202972412,
-      "eval_runtime": 6.4533,
-      "eval_samples_per_second": 846.539,
-      "eval_steps_per_second": 3.409,
+      "eval_runtime": 6.3622,
+      "eval_samples_per_second": 858.665,
+      "eval_steps_per_second": 3.458,
       "step": 4920
     },
     {
@@ -197,9 +197,9 @@
       "epoch": 13.0,
       "eval_accuracy": 0.4946000366099213,
       "eval_loss": 0.6931495070457458,
-      "eval_runtime": 6.4356,
-      "eval_samples_per_second": 848.877,
-      "eval_steps_per_second": 3.419,
+      "eval_runtime": 6.3927,
+      "eval_samples_per_second": 854.572,
+      "eval_steps_per_second": 3.441,
       "step": 5330
     },
     {
@@ -207,9 +207,9 @@
       "step": 5330,
       "total_flos": 1.6959930780719514e+17,
       "train_loss": 0.6936567925601694,
-      "train_runtime": 4888.5149,
-      "train_samples_per_second": 1071.317,
-      "train_steps_per_second": 4.194
+      "train_runtime": 4977.7257,
+      "train_samples_per_second": 1052.117,
+      "train_steps_per_second": 4.118
     }
   ],
   "max_steps": 20500,