End of training

README.md

@@ -1,12 +1,30 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: hBERTv1_data_aug_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 1.0
+    - name: F1
+      type: f1
+      value: 1.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_data_aug_mrpc
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on an unknown 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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0164
-- Accuracy: 0.9975
-- F1: 0.9982
-- Combined Score: 0.9979
+- Loss: 0.0001
+- Accuracy: 1.0
+- F1: 1.0
+- Combined Score: 1.0
 
 ## Model description
 

all_results.json

@@ -4,13 +4,13 @@
     "eval_combined_score": 1.0,
     "eval_f1": 1.0,
     "eval_loss": 5.569791028392501e-05,
-    "eval_runtime": 0.5673,
+    "eval_runtime": 0.5567,
     "eval_samples": 408,
-    "eval_samples_per_second": 719.251,
-    "eval_steps_per_second": 3.526,
+    "eval_samples_per_second": 732.91,
+    "eval_steps_per_second": 3.593,
     "train_loss": 0.01846268490869172,
-    "train_runtime": 9463.9723,
+    "train_runtime": 9240.4943,
     "train_samples": 250736,
-    "train_samples_per_second": 1324.687,
-    "train_steps_per_second": 5.178
+    "train_samples_per_second": 1356.724,
+    "train_steps_per_second": 5.303
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 1.0,
     "eval_f1": 1.0,
     "eval_loss": 5.569791028392501e-05,
-    "eval_runtime": 0.5673,
+    "eval_runtime": 0.5567,
     "eval_samples": 408,
-    "eval_samples_per_second": 719.251,
-    "eval_steps_per_second": 3.526
+    "eval_samples_per_second": 732.91,
+    "eval_steps_per_second": 3.593
 }

logs/events.out.tfevents.1677752051.serv-9223.249238.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665afc9f886b5d6cbe7e0983d633e3eea6adb6757cd8bdeed6b7a8e9e3decc24
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "train_loss": 0.01846268490869172,
-    "train_runtime": 9463.9723,
+    "train_runtime": 9240.4943,
     "train_samples": 250736,
-    "train_samples_per_second": 1324.687,
-    "train_steps_per_second": 5.178
+    "train_samples_per_second": 1356.724,
+    "train_steps_per_second": 5.303
 }

trainer_state.json

@@ -19,9 +19,9 @@
       "eval_combined_score": 0.9978800554210951,
       "eval_f1": 0.998211091234347,
       "eval_loss": 0.004494799301028252,
-      "eval_runtime": 0.5596,
-      "eval_samples_per_second": 729.142,
-      "eval_steps_per_second": 3.574,
+      "eval_runtime": 0.5297,
+      "eval_samples_per_second": 770.282,
+      "eval_steps_per_second": 3.776,
       "step": 980
     },
     {
@@ -36,9 +36,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 6.0925009165657684e-05,
-      "eval_runtime": 0.5584,
-      "eval_samples_per_second": 730.667,
-      "eval_steps_per_second": 3.582,
+      "eval_runtime": 0.5295,
+      "eval_samples_per_second": 770.515,
+      "eval_steps_per_second": 3.777,
       "step": 1960
     },
     {
@@ -53,9 +53,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 8.451967732980847e-05,
-      "eval_runtime": 0.5589,
-      "eval_samples_per_second": 730.056,
-      "eval_steps_per_second": 3.579,
+      "eval_runtime": 0.5298,
+      "eval_samples_per_second": 770.156,
+      "eval_steps_per_second": 3.775,
       "step": 2940
     },
     {
@@ -70,9 +70,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 5.947695899521932e-05,
-      "eval_runtime": 0.5569,
-      "eval_samples_per_second": 732.679,
-      "eval_steps_per_second": 3.592,
+      "eval_runtime": 0.5287,
+      "eval_samples_per_second": 771.7,
+      "eval_steps_per_second": 3.783,
       "step": 3920
     },
     {
@@ -87,9 +87,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 5.569791028392501e-05,
-      "eval_runtime": 0.556,
-      "eval_samples_per_second": 733.848,
-      "eval_steps_per_second": 3.597,
+      "eval_runtime": 0.5323,
+      "eval_samples_per_second": 766.547,
+      "eval_steps_per_second": 3.758,
       "step": 4900
     },
     {
@@ -104,9 +104,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 0.00023545935982838273,
-      "eval_runtime": 0.5589,
-      "eval_samples_per_second": 730.007,
-      "eval_steps_per_second": 3.578,
+      "eval_runtime": 0.5293,
+      "eval_samples_per_second": 770.865,
+      "eval_steps_per_second": 3.779,
       "step": 5880
     },
     {
@@ -121,9 +121,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 0.0002702152996789664,
-      "eval_runtime": 0.5598,
-      "eval_samples_per_second": 728.83,
-      "eval_steps_per_second": 3.573,
+      "eval_runtime": 0.5311,
+      "eval_samples_per_second": 768.279,
+      "eval_steps_per_second": 3.766,
       "step": 6860
     },
     {
@@ -138,9 +138,9 @@
       "eval_combined_score": 0.997876843735699,
       "eval_f1": 0.9982046678635548,
       "eval_loss": 0.015019365586340427,
-      "eval_runtime": 0.558,
-      "eval_samples_per_second": 731.241,
-      "eval_steps_per_second": 3.585,
+      "eval_runtime": 0.5296,
+      "eval_samples_per_second": 770.328,
+      "eval_steps_per_second": 3.776,
       "step": 7840
     },
     {
@@ -155,9 +155,9 @@
       "eval_combined_score": 1.0,
       "eval_f1": 1.0,
       "eval_loss": 0.0014859754592180252,
-      "eval_runtime": 0.5575,
-      "eval_samples_per_second": 731.782,
-      "eval_steps_per_second": 3.587,
+      "eval_runtime": 0.5295,
+      "eval_samples_per_second": 770.576,
+      "eval_steps_per_second": 3.777,
       "step": 8820
     },
     {
@@ -172,9 +172,9 @@
       "eval_combined_score": 0.997876843735699,
       "eval_f1": 0.9982046678635548,
       "eval_loss": 0.016378218308091164,
-      "eval_runtime": 0.5579,
-      "eval_samples_per_second": 731.36,
-      "eval_steps_per_second": 3.585,
+      "eval_runtime": 0.5299,
+      "eval_samples_per_second": 770.0,
+      "eval_steps_per_second": 3.775,
       "step": 9800
     },
     {
@@ -182,9 +182,9 @@
       "step": 9800,
       "total_flos": 3.167072376848384e+17,
       "train_loss": 0.01846268490869172,
-      "train_runtime": 9463.9723,
-      "train_samples_per_second": 1324.687,
-      "train_steps_per_second": 5.178
+      "train_runtime": 9240.4943,
+      "train_samples_per_second": 1356.724,
+      "train_steps_per_second": 5.303
     }
   ],
   "max_steps": 49000,