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 SST2
       type: glue
       config: sst2
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8061926605504587
+      value: 0.7901376146788991
 ---
 
 <!-- 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. -->
 
 # hBERTv1_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6409
-- Accuracy: 0.8062
+- Loss: 0.4525
+- Accuracy: 0.7901
 
 ## Model description
 

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 8.0,
     "eval_accuracy": 0.7901376146788991,
     "eval_loss": 0.4525200426578522,
-    "eval_runtime": 1.0996,
+    "eval_runtime": 1.1426,
     "eval_samples": 872,
-    "eval_samples_per_second": 793.011,
-    "eval_steps_per_second": 3.638,
+    "eval_samples_per_second": 763.153,
+    "eval_steps_per_second": 3.501,
     "train_loss": 0.32838042577107746,
-    "train_runtime": 2121.3212,
+    "train_runtime": 2182.5269,
     "train_samples": 67349,
-    "train_samples_per_second": 1587.431,
-    "train_steps_per_second": 6.223
+    "train_samples_per_second": 1542.913,
+    "train_steps_per_second": 6.048
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "eval_accuracy": 0.7901376146788991,
     "eval_loss": 0.4525200426578522,
-    "eval_runtime": 1.0996,
+    "eval_runtime": 1.1426,
     "eval_samples": 872,
-    "eval_samples_per_second": 793.011,
-    "eval_steps_per_second": 3.638
+    "eval_samples_per_second": 763.153,
+    "eval_steps_per_second": 3.501
 }

logs/events.out.tfevents.1677755546.serv-9223.249682.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3599a715a0cc368e1c49a2ad4acabd6ba8e1b9d546c1771de7d31d5e31252f3
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.0,
     "train_loss": 0.32838042577107746,
-    "train_runtime": 2121.3212,
+    "train_runtime": 2182.5269,
     "train_samples": 67349,
-    "train_samples_per_second": 1587.431,
-    "train_steps_per_second": 6.223
+    "train_samples_per_second": 1542.913,
+    "train_steps_per_second": 6.048
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5252293577981652,
       "eval_loss": 0.6919494271278381,
-      "eval_runtime": 1.1023,
-      "eval_samples_per_second": 791.06,
-      "eval_steps_per_second": 3.629,
+      "eval_runtime": 1.12,
+      "eval_samples_per_second": 778.573,
+      "eval_steps_per_second": 3.571,
       "step": 264
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.6915137614678899,
       "eval_loss": 0.6088164448738098,
-      "eval_runtime": 1.0979,
-      "eval_samples_per_second": 794.271,
-      "eval_steps_per_second": 3.643,
+      "eval_runtime": 1.1165,
+      "eval_samples_per_second": 780.99,
+      "eval_steps_per_second": 3.583,
       "step": 528
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.7901376146788991,
       "eval_loss": 0.4525200426578522,
-      "eval_runtime": 1.0982,
-      "eval_samples_per_second": 794.011,
-      "eval_steps_per_second": 3.642,
+      "eval_runtime": 1.1346,
+      "eval_samples_per_second": 768.583,
+      "eval_steps_per_second": 3.526,
       "step": 792
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.8096330275229358,
       "eval_loss": 0.46269044280052185,
-      "eval_runtime": 1.0972,
-      "eval_samples_per_second": 794.783,
-      "eval_steps_per_second": 3.646,
+      "eval_runtime": 1.1242,
+      "eval_samples_per_second": 775.67,
+      "eval_steps_per_second": 3.558,
       "step": 1056
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.8073394495412844,
       "eval_loss": 0.48936158418655396,
-      "eval_runtime": 1.0982,
-      "eval_samples_per_second": 794.035,
-      "eval_steps_per_second": 3.642,
+      "eval_runtime": 1.1261,
+      "eval_samples_per_second": 774.387,
+      "eval_steps_per_second": 3.552,
       "step": 1320
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.801605504587156,
       "eval_loss": 0.6001835465431213,
-      "eval_runtime": 1.0997,
-      "eval_samples_per_second": 792.972,
-      "eval_steps_per_second": 3.637,
+      "eval_runtime": 1.1325,
+      "eval_samples_per_second": 769.975,
+      "eval_steps_per_second": 3.532,
       "step": 1584
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.8061926605504587,
       "eval_loss": 0.646708607673645,
-      "eval_runtime": 1.0961,
-      "eval_samples_per_second": 795.513,
-      "eval_steps_per_second": 3.649,
+      "eval_runtime": 1.1318,
+      "eval_samples_per_second": 770.474,
+      "eval_steps_per_second": 3.534,
       "step": 1848
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_accuracy": 0.8061926605504587,
       "eval_loss": 0.6409061551094055,
-      "eval_runtime": 1.0981,
-      "eval_samples_per_second": 794.077,
-      "eval_steps_per_second": 3.643,
+      "eval_runtime": 1.1343,
+      "eval_samples_per_second": 768.782,
+      "eval_steps_per_second": 3.527,
       "step": 2112
     },
     {
@@ -132,9 +132,9 @@
       "step": 2112,
       "total_flos": 6.805537600779059e+16,
       "train_loss": 0.32838042577107746,
-      "train_runtime": 2121.3212,
-      "train_samples_per_second": 1587.431,
-      "train_steps_per_second": 6.223
+      "train_runtime": 2182.5269,
+      "train_samples_per_second": 1542.913,
+      "train_steps_per_second": 6.048
     }
   ],
   "max_steps": 13200,