End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: hBERTv1_data_aug_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_data_aug_cola
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on an unknown 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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6187
+- Loss: 0.6183
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 7.0,
     "eval_loss": 0.618320643901825,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.408,
+    "eval_runtime": 1.3573,
     "eval_samples": 1043,
-    "eval_samples_per_second": 740.793,
-    "eval_steps_per_second": 3.551,
+    "eval_samples_per_second": 768.419,
+    "eval_steps_per_second": 3.684,
     "train_loss": 0.6066560117070546,
-    "train_runtime": 5653.074,
+    "train_runtime": 5543.8638,
     "train_samples": 213609,
-    "train_samples_per_second": 1889.317,
-    "train_steps_per_second": 7.385
+    "train_samples_per_second": 1926.535,
+    "train_steps_per_second": 7.531
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "eval_loss": 0.618320643901825,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.408,
+    "eval_runtime": 1.3573,
     "eval_samples": 1043,
-    "eval_samples_per_second": 740.793,
-    "eval_steps_per_second": 3.551
+    "eval_samples_per_second": 768.419,
+    "eval_steps_per_second": 3.684
 }

logs/events.out.tfevents.1677742649.serv-9223.249238.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2192e86038afa0790dc04af2e0bbf5fcfc2e12c363124c73b9498e8d111c83
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 7.0,
     "train_loss": 0.6066560117070546,
-    "train_runtime": 5653.074,
+    "train_runtime": 5543.8638,
     "train_samples": 213609,
-    "train_samples_per_second": 1889.317,
-    "train_steps_per_second": 7.385
+    "train_samples_per_second": 1926.535,
+    "train_steps_per_second": 7.531
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_loss": 0.6251746416091919,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4137,
-      "eval_samples_per_second": 737.758,
-      "eval_steps_per_second": 3.537,
+      "eval_runtime": 1.3477,
+      "eval_samples_per_second": 773.92,
+      "eval_steps_per_second": 3.71,
       "step": 835
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_loss": 0.618320643901825,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4125,
-      "eval_samples_per_second": 738.423,
-      "eval_steps_per_second": 3.54,
+      "eval_runtime": 1.336,
+      "eval_samples_per_second": 780.681,
+      "eval_steps_per_second": 3.742,
       "step": 1670
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.6184751391410828,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4126,
-      "eval_samples_per_second": 738.355,
-      "eval_steps_per_second": 3.54,
+      "eval_runtime": 1.3377,
+      "eval_samples_per_second": 779.697,
+      "eval_steps_per_second": 3.738,
       "step": 2505
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_loss": 0.6219027042388916,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.414,
-      "eval_samples_per_second": 737.6,
-      "eval_steps_per_second": 3.536,
+      "eval_runtime": 1.3355,
+      "eval_samples_per_second": 780.969,
+      "eval_steps_per_second": 3.744,
       "step": 3340
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_loss": 0.6204879879951477,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4116,
-      "eval_samples_per_second": 738.88,
-      "eval_steps_per_second": 3.542,
+      "eval_runtime": 1.34,
+      "eval_samples_per_second": 778.371,
+      "eval_steps_per_second": 3.731,
       "step": 4175
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_loss": 0.6183536648750305,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4244,
-      "eval_samples_per_second": 732.218,
-      "eval_steps_per_second": 3.51,
+      "eval_runtime": 1.3404,
+      "eval_samples_per_second": 778.146,
+      "eval_steps_per_second": 3.73,
       "step": 5010
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_loss": 0.6187195181846619,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.4085,
-      "eval_samples_per_second": 740.513,
-      "eval_steps_per_second": 3.55,
+      "eval_runtime": 1.3402,
+      "eval_samples_per_second": 778.271,
+      "eval_steps_per_second": 3.731,
       "step": 5845
     },
     {
@@ -117,9 +117,9 @@
       "step": 5845,
       "total_flos": 1.8886821472423117e+17,
       "train_loss": 0.6066560117070546,
-      "train_runtime": 5653.074,
-      "train_samples_per_second": 1889.317,
-      "train_steps_per_second": 7.385
+      "train_runtime": 5543.8638,
+      "train_samples_per_second": 1926.535,
+      "train_steps_per_second": 7.531
     }
   ],
   "max_steps": 41750,