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 MRPC
       type: glue
       config: mrpc
       split: validation
@@ -21,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5735294117647058
+      value: 0.6862745098039216
     - name: F1
       type: f1
-      value: 0.65748031496063
+      value: 0.7894736842105262
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_w_init__mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3076
-- Accuracy: 0.5735
-- F1: 0.6575
-- Combined Score: 0.6155
+- Loss: 0.6082
+- Accuracy: 0.6863
+- F1: 0.7895
+- Combined Score: 0.7379
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 9.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6237123012542725,
-    "eval_runtime": 0.7659,
+    "eval_accuracy": 0.6862745098039216,
+    "eval_combined_score": 0.737874097007224,
+    "eval_f1": 0.7894736842105262,
+    "eval_loss": 0.6082243323326111,
+    "eval_runtime": 0.748,
     "eval_samples": 408,
-    "eval_samples_per_second": 532.701,
-    "eval_steps_per_second": 5.223,
-    "train_loss": 0.9404267789760312,
-    "train_runtime": 225.9356,
+    "eval_samples_per_second": 545.43,
+    "eval_steps_per_second": 5.347,
+    "train_loss": 0.46000806216535894,
+    "train_runtime": 225.7005,
     "train_samples": 3668,
-    "train_samples_per_second": 811.736,
-    "train_steps_per_second": 6.418
+    "train_samples_per_second": 812.581,
+    "train_steps_per_second": 6.424
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 9.0,
-    "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6237123012542725,
-    "eval_runtime": 0.7659,
+    "eval_accuracy": 0.6862745098039216,
+    "eval_combined_score": 0.737874097007224,
+    "eval_f1": 0.7894736842105262,
+    "eval_loss": 0.6082243323326111,
+    "eval_runtime": 0.748,
     "eval_samples": 408,
-    "eval_samples_per_second": 532.701,
-    "eval_steps_per_second": 5.223
+    "eval_samples_per_second": 545.43,
+    "eval_steps_per_second": 5.347
 }

logs/events.out.tfevents.1686033598.serv-3317.3377907.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52302955d2af1b6fc5043f428ac37b205e9677853456c337d771e77f98b25884
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.0,
-    "train_loss": 0.9404267789760312,
-    "train_runtime": 225.9356,
+    "train_loss": 0.46000806216535894,
+    "train_runtime": 225.7005,
     "train_samples": 3668,
-    "train_samples_per_second": 811.736,
-    "train_steps_per_second": 6.418
+    "train_samples_per_second": 812.581,
+    "train_steps_per_second": 6.424
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6237123012542725,
+  "best_metric": 0.6082243323326111,
   "best_model_checkpoint": "hBERTv1_new_pretrain_w_init__mrpc/checkpoint-116",
   "epoch": 9.0,
   "global_step": 261,
@@ -9,8 +9,8 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.00049,
-      "loss": 3.2785,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.7111,
       "step": 29
     },
     {
@@ -18,16 +18,16 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6238367557525635,
-      "eval_runtime": 0.7409,
-      "eval_samples_per_second": 550.699,
-      "eval_steps_per_second": 5.399,
+      "eval_loss": 0.6563864350318909,
+      "eval_runtime": 0.7398,
+      "eval_samples_per_second": 551.531,
+      "eval_steps_per_second": 5.407,
       "step": 29
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.00048,
-      "loss": 0.7343,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6641,
       "step": 58
     },
     {
@@ -35,16 +35,16 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6785768866539001,
-      "eval_runtime": 0.7398,
-      "eval_samples_per_second": 551.485,
-      "eval_steps_per_second": 5.407,
+      "eval_loss": 0.6160457730293274,
+      "eval_runtime": 0.7439,
+      "eval_samples_per_second": 548.435,
+      "eval_steps_per_second": 5.377,
       "step": 58
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.00047,
-      "loss": 0.6377,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6156,
       "step": 87
     },
     {
@@ -52,122 +52,122 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.62451171875,
-      "eval_runtime": 0.7405,
-      "eval_samples_per_second": 550.974,
-      "eval_steps_per_second": 5.402,
+      "eval_loss": 0.6354035139083862,
+      "eval_runtime": 0.7456,
+      "eval_samples_per_second": 547.23,
+      "eval_steps_per_second": 5.365,
       "step": 87
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.00046,
-      "loss": 0.6353,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.5817,
       "step": 116
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6237123012542725,
-      "eval_runtime": 0.7399,
-      "eval_samples_per_second": 551.451,
-      "eval_steps_per_second": 5.406,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.737874097007224,
+      "eval_f1": 0.7894736842105262,
+      "eval_loss": 0.6082243323326111,
+      "eval_runtime": 0.7468,
+      "eval_samples_per_second": 546.334,
+      "eval_steps_per_second": 5.356,
       "step": 116
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.00045000000000000004,
-      "loss": 0.6344,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5091,
       "step": 145
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6243776679039001,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 549.914,
-      "eval_steps_per_second": 5.391,
+      "eval_accuracy": 0.5073529411764706,
+      "eval_combined_score": 0.5115077958894401,
+      "eval_f1": 0.5156626506024096,
+      "eval_loss": 0.7811743021011353,
+      "eval_runtime": 0.7431,
+      "eval_samples_per_second": 549.025,
+      "eval_steps_per_second": 5.383,
       "step": 145
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.00044,
-      "loss": 0.6314,
+      "learning_rate": 3.52e-05,
+      "loss": 0.3973,
       "step": 174
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6323529481887817,
-      "eval_runtime": 0.7418,
-      "eval_samples_per_second": 550.048,
-      "eval_steps_per_second": 5.393,
+      "eval_accuracy": 0.6544117647058824,
+      "eval_combined_score": 0.705444224321853,
+      "eval_f1": 0.7564766839378239,
+      "eval_loss": 0.7949338555335999,
+      "eval_runtime": 0.7416,
+      "eval_samples_per_second": 550.17,
+      "eval_steps_per_second": 5.394,
       "step": 174
     },
     {
       "epoch": 7.0,
-      "learning_rate": 0.00043,
-      "loss": 0.6431,
+      "learning_rate": 3.44e-05,
+      "loss": 0.2966,
       "step": 203
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6401510834693909,
-      "eval_runtime": 0.7429,
-      "eval_samples_per_second": 549.206,
-      "eval_steps_per_second": 5.384,
+      "eval_accuracy": 0.6078431372549019,
+      "eval_combined_score": 0.6482795452811474,
+      "eval_f1": 0.688715953307393,
+      "eval_loss": 1.0388320684432983,
+      "eval_runtime": 0.7411,
+      "eval_samples_per_second": 550.501,
+      "eval_steps_per_second": 5.397,
       "step": 203
     },
     {
       "epoch": 8.0,
-      "learning_rate": 0.00042,
-      "loss": 0.6347,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.2024,
       "step": 232
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6335784196853638,
-      "eval_runtime": 0.7439,
-      "eval_samples_per_second": 548.43,
-      "eval_steps_per_second": 5.377,
+      "eval_accuracy": 0.6200980392156863,
+      "eval_combined_score": 0.6662642329659136,
+      "eval_f1": 0.7124304267161411,
+      "eval_loss": 1.0064674615859985,
+      "eval_runtime": 0.7424,
+      "eval_samples_per_second": 549.6,
+      "eval_steps_per_second": 5.388,
       "step": 232
     },
     {
       "epoch": 9.0,
-      "learning_rate": 0.00041,
-      "loss": 0.6343,
+      "learning_rate": 3.28e-05,
+      "loss": 0.1621,
       "step": 261
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6257611513137817,
-      "eval_runtime": 0.7412,
-      "eval_samples_per_second": 550.441,
-      "eval_steps_per_second": 5.396,
+      "eval_accuracy": 0.5735294117647058,
+      "eval_combined_score": 0.6155048633626679,
+      "eval_f1": 0.65748031496063,
+      "eval_loss": 1.307615876197815,
+      "eval_runtime": 0.7454,
+      "eval_samples_per_second": 547.342,
+      "eval_steps_per_second": 5.366,
       "step": 261
     },
     {
       "epoch": 9.0,
       "step": 261,
       "total_flos": 4888970768941056.0,
-      "train_loss": 0.9404267789760312,
-      "train_runtime": 225.9356,
-      "train_samples_per_second": 811.736,
-      "train_steps_per_second": 6.418
+      "train_loss": 0.46000806216535894,
+      "train_runtime": 225.7005,
+      "train_samples_per_second": 812.581,
+      "train_steps_per_second": 6.424
     }
   ],
   "max_steps": 1450,