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: 0.7622549019607843
+      value: 0.6936274509803921
     - name: F1
       type: f1
-      value: 0.8380634390651085
+      value: 0.8085758039816232
 ---
 
 <!-- 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. -->
 
 # hBERTv2_mrpc
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9954
-- Accuracy: 0.7623
-- F1: 0.8381
-- Combined Score: 0.8002
+- Loss: 0.5772
+- Accuracy: 0.6936
+- F1: 0.8086
+- Combined Score: 0.7511
 
 ## Model description
 

all_results.json

@@ -4,13 +4,13 @@
     "eval_combined_score": 0.7511016274810076,
     "eval_f1": 0.8085758039816232,
     "eval_loss": 0.5771955847740173,
-    "eval_runtime": 0.5133,
+    "eval_runtime": 0.4842,
     "eval_samples": 408,
-    "eval_samples_per_second": 794.855,
-    "eval_steps_per_second": 3.896,
-    "train_loss": 0.4106310119231542,
-    "train_runtime": 128.2586,
+    "eval_samples_per_second": 842.623,
+    "eval_steps_per_second": 4.131,
+    "train_loss": 0.18271473944187164,
+    "train_runtime": 94.8977,
     "train_samples": 3668,
-    "train_samples_per_second": 1429.924,
-    "train_steps_per_second": 5.848
+    "train_samples_per_second": 1932.608,
+    "train_steps_per_second": 7.903
 }

eval_results.json

@@ -4,8 +4,8 @@
     "eval_combined_score": 0.7511016274810076,
     "eval_f1": 0.8085758039816232,
     "eval_loss": 0.5771955847740173,
-    "eval_runtime": 0.5133,
+    "eval_runtime": 0.4842,
     "eval_samples": 408,
-    "eval_samples_per_second": 794.855,
-    "eval_steps_per_second": 3.896
+    "eval_samples_per_second": 842.623,
+    "eval_steps_per_second": 4.131
 }

logs/events.out.tfevents.1677709066.serv-3317.3553245.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a923498f21c79212da9c591788ff773e298dc0988f2946ab3d093df0a4ba50d
+size 459

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.0,
-    "train_loss": 0.4106310119231542,
-    "train_runtime": 128.2586,
+    "train_loss": 0.18271473944187164,
+    "train_runtime": 94.8977,
     "train_samples": 3668,
-    "train_samples_per_second": 1429.924,
-    "train_steps_per_second": 5.848
+    "train_samples_per_second": 1932.608,
+    "train_steps_per_second": 7.903
 }

trainer_state.json

@@ -70,9 +70,9 @@
       "eval_combined_score": 0.7580659536541889,
       "eval_f1": 0.8151515151515151,
       "eval_loss": 0.6260703206062317,
-      "eval_runtime": 0.4882,
-      "eval_samples_per_second": 835.793,
-      "eval_steps_per_second": 4.097,
+      "eval_runtime": 0.4844,
+      "eval_samples_per_second": 842.253,
+      "eval_steps_per_second": 4.129,
       "step": 60
     },
     {
@@ -87,9 +87,9 @@
       "eval_combined_score": 0.7737266857962697,
       "eval_f1": 0.8195121951219512,
       "eval_loss": 0.6433467268943787,
-      "eval_runtime": 0.4891,
-      "eval_samples_per_second": 834.113,
-      "eval_steps_per_second": 4.089,
+      "eval_runtime": 0.484,
+      "eval_samples_per_second": 842.954,
+      "eval_steps_per_second": 4.132,
       "step": 75
     },
     {
@@ -104,9 +104,9 @@
       "eval_combined_score": 0.7228365030222615,
       "eval_f1": 0.7593984962406015,
       "eval_loss": 0.7530680894851685,
-      "eval_runtime": 0.4871,
-      "eval_samples_per_second": 837.615,
-      "eval_steps_per_second": 4.106,
+      "eval_runtime": 0.4824,
+      "eval_samples_per_second": 845.726,
+      "eval_steps_per_second": 4.146,
       "step": 90
     },
     {
@@ -121,9 +121,9 @@
       "eval_combined_score": 0.7767899328406062,
       "eval_f1": 0.8158347676419966,
       "eval_loss": 0.7904398441314697,
-      "eval_runtime": 0.4881,
-      "eval_samples_per_second": 835.949,
-      "eval_steps_per_second": 4.098,
+      "eval_runtime": 0.4836,
+      "eval_samples_per_second": 843.759,
+      "eval_steps_per_second": 4.136,
       "step": 105
     },
     {
@@ -138,19 +138,19 @@
       "eval_combined_score": 0.8001591705129464,
       "eval_f1": 0.8380634390651085,
       "eval_loss": 0.9954336285591125,
-      "eval_runtime": 0.4868,
-      "eval_samples_per_second": 838.079,
-      "eval_steps_per_second": 4.108,
+      "eval_runtime": 0.4861,
+      "eval_samples_per_second": 839.39,
+      "eval_steps_per_second": 4.115,
       "step": 120
     },
     {
       "epoch": 8.0,
       "step": 120,
       "total_flos": 3654895836069888.0,
-      "train_loss": 0.4106310119231542,
-      "train_runtime": 128.2586,
-      "train_samples_per_second": 1429.924,
-      "train_steps_per_second": 5.848
+      "train_loss": 0.18271473944187164,
+      "train_runtime": 94.8977,
+      "train_samples_per_second": 1932.608,
+      "train_steps_per_second": 7.903
     }
   ],
   "max_steps": 750,