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 COLA
       type: glue
       config: cola
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6196
+- Loss: 0.6182
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 7.0,
     "eval_loss": 0.6181691884994507,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.2226,
+    "eval_runtime": 1.2209,
     "eval_samples": 1043,
-    "eval_samples_per_second": 853.105,
-    "eval_steps_per_second": 4.09,
-    "train_loss": 0.43535192473595885,
-    "train_runtime": 180.6728,
+    "eval_samples_per_second": 854.273,
+    "eval_steps_per_second": 4.095,
+    "train_loss": 0.6130136441783745,
+    "train_runtime": 303.6084,
     "train_samples": 8551,
-    "train_samples_per_second": 2366.433,
-    "train_steps_per_second": 9.409
+    "train_samples_per_second": 1408.228,
+    "train_steps_per_second": 5.599
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "eval_loss": 0.6181691884994507,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.2226,
+    "eval_runtime": 1.2209,
     "eval_samples": 1043,
-    "eval_samples_per_second": 853.105,
-    "eval_steps_per_second": 4.09
+    "eval_samples_per_second": 854.273,
+    "eval_steps_per_second": 4.095
 }

logs/events.out.tfevents.1677737520.serv-3317.65116.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd247652e32e5ef210f9f8b5ce0463fd3e85f724ea97a604da5f5a79ec4128c
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 7.0,
-    "train_loss": 0.43535192473595885,
-    "train_runtime": 180.6728,
+    "train_loss": 0.6130136441783745,
+    "train_runtime": 303.6084,
     "train_samples": 8551,
-    "train_samples_per_second": 2366.433,
-    "train_steps_per_second": 9.409
+    "train_samples_per_second": 1408.228,
+    "train_steps_per_second": 5.599
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_loss": 0.618189811706543,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2309,
-      "eval_samples_per_second": 847.325,
-      "eval_steps_per_second": 4.062,
+      "eval_runtime": 1.2234,
+      "eval_samples_per_second": 852.526,
+      "eval_steps_per_second": 4.087,
       "step": 34
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_loss": 0.6181691884994507,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2378,
-      "eval_samples_per_second": 842.642,
-      "eval_steps_per_second": 4.04,
+      "eval_runtime": 1.2214,
+      "eval_samples_per_second": 853.934,
+      "eval_steps_per_second": 4.094,
       "step": 68
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.6213549971580505,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.218,
-      "eval_samples_per_second": 856.323,
-      "eval_steps_per_second": 4.105,
+      "eval_runtime": 1.2227,
+      "eval_samples_per_second": 853.001,
+      "eval_steps_per_second": 4.089,
       "step": 102
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_loss": 0.6190556287765503,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2211,
-      "eval_samples_per_second": 854.173,
-      "eval_steps_per_second": 4.095,
+      "eval_runtime": 1.2244,
+      "eval_samples_per_second": 851.842,
+      "eval_steps_per_second": 4.084,
       "step": 136
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_loss": 0.6221293210983276,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2273,
-      "eval_samples_per_second": 849.806,
-      "eval_steps_per_second": 4.074,
+      "eval_runtime": 1.2243,
+      "eval_samples_per_second": 851.906,
+      "eval_steps_per_second": 4.084,
       "step": 170
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_loss": 0.6182675361633301,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.243,
-      "eval_samples_per_second": 839.13,
-      "eval_steps_per_second": 4.023,
+      "eval_runtime": 1.2259,
+      "eval_samples_per_second": 850.776,
+      "eval_steps_per_second": 4.079,
       "step": 204
     },
     {
@@ -107,19 +107,19 @@
       "epoch": 7.0,
       "eval_loss": 0.6196076273918152,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.228,
-      "eval_samples_per_second": 849.376,
-      "eval_steps_per_second": 4.072,
+      "eval_runtime": 1.22,
+      "eval_samples_per_second": 854.907,
+      "eval_steps_per_second": 4.098,
       "step": 238
     },
     {
       "epoch": 7.0,
       "step": 238,
       "total_flos": 7455394754461696.0,
-      "train_loss": 0.43535192473595885,
-      "train_runtime": 180.6728,
-      "train_samples_per_second": 2366.433,
-      "train_steps_per_second": 9.409
+      "train_loss": 0.6130136441783745,
+      "train_runtime": 303.6084,
+      "train_samples_per_second": 1408.228,
+      "train_steps_per_second": 5.599
     }
   ],
   "max_steps": 1700,