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": 1.2427,
+    "eval_runtime": 1.2226,
     "eval_samples": 1043,
-    "eval_samples_per_second": 839.315,
-    "eval_steps_per_second": 4.024,
-    "train_loss": 0.6130136441783745,
-    "train_runtime": 229.4882,
+    "eval_samples_per_second": 853.105,
+    "eval_steps_per_second": 4.09,
+    "train_loss": 0.43535192473595885,
+    "train_runtime": 180.6728,
     "train_samples": 8551,
-    "train_samples_per_second": 1863.059,
-    "train_steps_per_second": 7.408
+    "train_samples_per_second": 2366.433,
+    "train_steps_per_second": 9.409
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 7.0,
     "eval_loss": 0.6181691884994507,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.2427,
+    "eval_runtime": 1.2226,
     "eval_samples": 1043,
-    "eval_samples_per_second": 839.315,
-    "eval_steps_per_second": 4.024
+    "eval_samples_per_second": 853.105,
+    "eval_steps_per_second": 4.09
 }

logs/events.out.tfevents.1677708725.serv-3317.3553245.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c4dce31de56c6b8335a52ea3efa5f5f5cd4436749ce86d6620f3121c23dfe9
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 7.0,
-    "train_loss": 0.6130136441783745,
-    "train_runtime": 229.4882,
+    "train_loss": 0.43535192473595885,
+    "train_runtime": 180.6728,
     "train_samples": 8551,
-    "train_samples_per_second": 1863.059,
-    "train_steps_per_second": 7.408
+    "train_samples_per_second": 2366.433,
+    "train_steps_per_second": 9.409
 }

trainer_state.json

@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.6213549971580505,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2389,
-      "eval_samples_per_second": 841.871,
-      "eval_steps_per_second": 4.036,
+      "eval_runtime": 1.218,
+      "eval_samples_per_second": 856.323,
+      "eval_steps_per_second": 4.105,
       "step": 102
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_loss": 0.6190556287765503,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2383,
-      "eval_samples_per_second": 842.292,
-      "eval_steps_per_second": 4.038,
+      "eval_runtime": 1.2211,
+      "eval_samples_per_second": 854.173,
+      "eval_steps_per_second": 4.095,
       "step": 136
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_loss": 0.6221293210983276,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2416,
-      "eval_samples_per_second": 840.076,
-      "eval_steps_per_second": 4.027,
+      "eval_runtime": 1.2273,
+      "eval_samples_per_second": 849.806,
+      "eval_steps_per_second": 4.074,
       "step": 170
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_loss": 0.6182675361633301,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2396,
-      "eval_samples_per_second": 841.387,
-      "eval_steps_per_second": 4.033,
+      "eval_runtime": 1.243,
+      "eval_samples_per_second": 839.13,
+      "eval_steps_per_second": 4.023,
       "step": 204
     },
     {
@@ -107,19 +107,19 @@
       "epoch": 7.0,
       "eval_loss": 0.6196076273918152,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.2395,
-      "eval_samples_per_second": 841.485,
-      "eval_steps_per_second": 4.034,
+      "eval_runtime": 1.228,
+      "eval_samples_per_second": 849.376,
+      "eval_steps_per_second": 4.072,
       "step": 238
     },
     {
       "epoch": 7.0,
       "step": 238,
       "total_flos": 7455394754461696.0,
-      "train_loss": 0.6130136441783745,
-      "train_runtime": 229.4882,
-      "train_samples_per_second": 1863.059,
-      "train_steps_per_second": 7.408
+      "train_loss": 0.43535192473595885,
+      "train_runtime": 180.6728,
+      "train_samples_per_second": 2366.433,
+      "train_steps_per_second": 9.409
     }
   ],
   "max_steps": 1700,