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. -->
 
 # hBERTv1_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 the glue 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: 0.6212
+- Loss: 0.6180
 - Matthews Correlation: 0.0
 
 ## Model description

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 6.0,
     "eval_loss": 0.6179953217506409,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.322,
+    "eval_runtime": 1.313,
     "eval_samples": 1043,
-    "eval_samples_per_second": 788.959,
-    "eval_steps_per_second": 3.782,
-    "train_loss": 0.6118226051330566,
-    "train_runtime": 236.3939,
+    "eval_samples_per_second": 794.374,
+    "eval_steps_per_second": 3.808,
+    "train_loss": 0.5082857468548942,
+    "train_runtime": 207.6378,
     "train_samples": 8551,
-    "train_samples_per_second": 1808.634,
-    "train_steps_per_second": 7.191
+    "train_samples_per_second": 2059.114,
+    "train_steps_per_second": 8.187
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 6.0,
     "eval_loss": 0.6179953217506409,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.322,
+    "eval_runtime": 1.313,
     "eval_samples": 1043,
-    "eval_samples_per_second": 788.959,
-    "eval_steps_per_second": 3.782
+    "eval_samples_per_second": 794.374,
+    "eval_steps_per_second": 3.808
 }

logs/events.out.tfevents.1677708978.serv-9225.3038038.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe2d80605e183b9b6e03ed2c0a20587cc90484c500f22ea0b0925644aa91f66
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.0,
-    "train_loss": 0.6118226051330566,
-    "train_runtime": 236.3939,
+    "train_loss": 0.5082857468548942,
+    "train_runtime": 207.6378,
     "train_samples": 8551,
-    "train_samples_per_second": 1808.634,
-    "train_steps_per_second": 7.191
+    "train_samples_per_second": 2059.114,
+    "train_steps_per_second": 8.187
 }

trainer_state.json

@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_loss": 0.6210665702819824,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3016,
-      "eval_samples_per_second": 801.321,
-      "eval_steps_per_second": 3.841,
+      "eval_runtime": 1.3002,
+      "eval_samples_per_second": 802.193,
+      "eval_steps_per_second": 3.846,
       "step": 68
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.6251837611198425,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3047,
-      "eval_samples_per_second": 799.413,
-      "eval_steps_per_second": 3.832,
+      "eval_runtime": 1.3073,
+      "eval_samples_per_second": 797.82,
+      "eval_steps_per_second": 3.825,
       "step": 102
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_loss": 0.6181675791740417,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3088,
-      "eval_samples_per_second": 796.936,
-      "eval_steps_per_second": 3.82,
+      "eval_runtime": 1.307,
+      "eval_samples_per_second": 798.007,
+      "eval_steps_per_second": 3.826,
       "step": 136
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_loss": 0.6210399270057678,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3101,
-      "eval_samples_per_second": 796.146,
-      "eval_steps_per_second": 3.817,
+      "eval_runtime": 1.3053,
+      "eval_samples_per_second": 799.078,
+      "eval_steps_per_second": 3.831,
       "step": 170
     },
     {
@@ -92,19 +92,19 @@
       "epoch": 6.0,
       "eval_loss": 0.6212285757064819,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.3069,
-      "eval_samples_per_second": 798.045,
-      "eval_steps_per_second": 3.826,
+      "eval_runtime": 1.3083,
+      "eval_samples_per_second": 797.202,
+      "eval_steps_per_second": 3.822,
       "step": 204
     },
     {
       "epoch": 6.0,
       "step": 204,
       "total_flos": 6480513749483520.0,
-      "train_loss": 0.6118226051330566,
-      "train_runtime": 236.3939,
-      "train_samples_per_second": 1808.634,
-      "train_steps_per_second": 7.191
+      "train_loss": 0.5082857468548942,
+      "train_runtime": 207.6378,
+      "train_samples_per_second": 2059.114,
+      "train_steps_per_second": 8.187
     }
   ],
   "max_steps": 1700,