End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE COLA
       type: glue
       config: cola
       split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_w_init__cola
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6260
+- Loss: 0.6171
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 9.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6171762347221375,
+    "eval_loss": 0.6171294450759888,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.8974,
+    "eval_runtime": 1.8779,
     "eval_samples": 1043,
-    "eval_samples_per_second": 549.702,
-    "eval_steps_per_second": 4.743,
-    "train_loss": 0.7229372850104944,
-    "train_runtime": 479.5868,
+    "eval_samples_per_second": 555.393,
+    "eval_steps_per_second": 4.792,
+    "train_loss": 0.6151945009753479,
+    "train_runtime": 493.5949,
     "train_samples": 8551,
-    "train_samples_per_second": 891.497,
-    "train_steps_per_second": 6.985
+    "train_samples_per_second": 866.196,
+    "train_steps_per_second": 6.787
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 9.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6171762347221375,
+    "eval_loss": 0.6171294450759888,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.8974,
+    "eval_runtime": 1.8779,
     "eval_samples": 1043,
-    "eval_samples_per_second": 549.702,
-    "eval_steps_per_second": 4.743
+    "eval_samples_per_second": 555.393,
+    "eval_steps_per_second": 4.792
 }

logs/events.out.tfevents.1686033047.serv-3317.3377907.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dc7ee9f39b634ce4eddab4e0f593a00a158d0c2233f7d784a41464f904ee4e
+size 427

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.0,
-    "train_loss": 0.7229372850104944,
-    "train_runtime": 479.5868,
+    "train_loss": 0.6151945009753479,
+    "train_runtime": 493.5949,
     "train_samples": 8551,
-    "train_samples_per_second": 891.497,
-    "train_steps_per_second": 6.985
+    "train_samples_per_second": 866.196,
+    "train_steps_per_second": 6.787
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6171762347221375,
+  "best_metric": 0.6171294450759888,
   "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__cola/checkpoint-268",
   "epoch": 9.0,
   "global_step": 603,
@@ -9,156 +9,156 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.00049,
-      "loss": 1.5988,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6355,
       "step": 67
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6768448948860168,
+      "eval_loss": 0.6238539814949036,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8807,
-      "eval_samples_per_second": 554.574,
-      "eval_steps_per_second": 4.785,
+      "eval_runtime": 1.8831,
+      "eval_samples_per_second": 553.864,
+      "eval_steps_per_second": 4.779,
       "step": 67
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.00048,
-      "loss": 0.6348,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6177,
       "step": 134
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6294155716896057,
+      "eval_loss": 0.6210843920707703,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.89,
-      "eval_samples_per_second": 551.843,
-      "eval_steps_per_second": 4.762,
+      "eval_runtime": 1.8854,
+      "eval_samples_per_second": 553.187,
+      "eval_steps_per_second": 4.773,
       "step": 134
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.00047,
-      "loss": 0.6135,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6142,
       "step": 201
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6195020079612732,
+      "eval_loss": 0.6231480240821838,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8864,
-      "eval_samples_per_second": 552.896,
-      "eval_steps_per_second": 4.771,
+      "eval_runtime": 1.8881,
+      "eval_samples_per_second": 552.412,
+      "eval_steps_per_second": 4.767,
       "step": 201
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.00046,
-      "loss": 0.6111,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6145,
       "step": 268
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6171762347221375,
+      "eval_loss": 0.6171294450759888,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8924,
-      "eval_samples_per_second": 551.137,
-      "eval_steps_per_second": 4.756,
+      "eval_runtime": 1.8901,
+      "eval_samples_per_second": 551.824,
+      "eval_steps_per_second": 4.762,
       "step": 268
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.00045000000000000004,
-      "loss": 0.6093,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6102,
       "step": 335
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6190469861030579,
+      "eval_loss": 0.6199458241462708,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8886,
-      "eval_samples_per_second": 552.263,
-      "eval_steps_per_second": 4.765,
+      "eval_runtime": 1.8879,
+      "eval_samples_per_second": 552.46,
+      "eval_steps_per_second": 4.767,
       "step": 335
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.00044,
-      "loss": 0.6094,
+      "learning_rate": 3.52e-05,
+      "loss": 0.6126,
       "step": 402
     },
     {
       "epoch": 6.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6183953285217285,
+      "eval_loss": 0.6183897256851196,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8864,
-      "eval_samples_per_second": 552.902,
-      "eval_steps_per_second": 4.771,
+      "eval_runtime": 1.8897,
+      "eval_samples_per_second": 551.929,
+      "eval_steps_per_second": 4.763,
       "step": 402
     },
     {
       "epoch": 7.0,
-      "learning_rate": 0.00043,
-      "loss": 0.6096,
+      "learning_rate": 3.44e-05,
+      "loss": 0.6127,
       "step": 469
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6203241348266602,
+      "eval_loss": 0.6205731630325317,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8849,
-      "eval_samples_per_second": 553.337,
-      "eval_steps_per_second": 4.775,
+      "eval_runtime": 1.8922,
+      "eval_samples_per_second": 551.21,
+      "eval_steps_per_second": 4.756,
       "step": 469
     },
     {
       "epoch": 8.0,
-      "learning_rate": 0.00042,
-      "loss": 0.6103,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.6107,
       "step": 536
     },
     {
       "epoch": 8.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6184271574020386,
+      "eval_loss": 0.618511438369751,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.8889,
-      "eval_samples_per_second": 552.179,
-      "eval_steps_per_second": 4.765,
+      "eval_runtime": 1.8868,
+      "eval_samples_per_second": 552.792,
+      "eval_steps_per_second": 4.77,
       "step": 536
     },
     {
       "epoch": 9.0,
-      "learning_rate": 0.00041,
-      "loss": 0.6097,
+      "learning_rate": 3.28e-05,
+      "loss": 0.6086,
       "step": 603
     },
     {
       "epoch": 9.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6273332834243774,
+      "eval_loss": 0.6259681582450867,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.886,
-      "eval_samples_per_second": 553.026,
-      "eval_steps_per_second": 4.772,
+      "eval_runtime": 1.8926,
+      "eval_samples_per_second": 551.082,
+      "eval_steps_per_second": 4.755,
       "step": 603
     },
     {
       "epoch": 9.0,
       "step": 603,
       "total_flos": 1.1397379827695616e+16,
-      "train_loss": 0.7229372850104944,
-      "train_runtime": 479.5868,
-      "train_samples_per_second": 891.497,
-      "train_steps_per_second": 6.985
+      "train_loss": 0.6151945009753479,
+      "train_runtime": 493.5949,
+      "train_samples_per_second": 866.196,
+      "train_steps_per_second": 6.787
     }
   ],
   "max_steps": 3350,