End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_20_v1_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8355181795696265
+    - name: F1
+      type: f1
+      value: 0.7821386450006552
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_20_v1_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4276
-- Accuracy: 0.8535
-- F1: 0.7964
-- Combined Score: 0.8249
+- Loss: 0.3641
+- Accuracy: 0.8355
+- F1: 0.7821
+- Combined Score: 0.8088
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 8.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6569345593452454,
-    "eval_runtime": 12.4853,
+    "eval_accuracy": 0.8355181795696265,
+    "eval_combined_score": 0.8088284122851408,
+    "eval_f1": 0.7821386450006552,
+    "eval_loss": 0.3640855848789215,
+    "eval_runtime": 12.4138,
     "eval_samples": 40430,
-    "eval_samples_per_second": 3238.216,
-    "eval_steps_per_second": 12.655,
+    "eval_samples_per_second": 3256.856,
+    "eval_steps_per_second": 12.728,
     "total_flos": 7.633075201391002e+16,
-    "train_loss": 0.6589229814446258,
-    "train_runtime": 1678.7379,
+    "train_loss": 0.2928101691180308,
+    "train_runtime": 1671.3114,
     "train_samples": 363846,
-    "train_samples_per_second": 10836.891,
-    "train_steps_per_second": 42.353
+    "train_samples_per_second": 10885.045,
+    "train_steps_per_second": 42.541
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 8.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6569345593452454,
-    "eval_runtime": 12.4853,
+    "eval_accuracy": 0.8355181795696265,
+    "eval_combined_score": 0.8088284122851408,
+    "eval_f1": 0.7821386450006552,
+    "eval_loss": 0.3640855848789215,
+    "eval_runtime": 12.4138,
     "eval_samples": 40430,
-    "eval_samples_per_second": 3238.216,
-    "eval_steps_per_second": 12.655
+    "eval_samples_per_second": 3256.856,
+    "eval_steps_per_second": 12.728
 }

logs/events.out.tfevents.1733325674.ki-g0008.1207389.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee653cce571097c8c8c3e394a37c5e7072236dbeb5ff7b0a029cf2c555ccfde5
+size 515

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 8.0,
     "total_flos": 7.633075201391002e+16,
-    "train_loss": 0.6589229814446258,
-    "train_runtime": 1678.7379,
+    "train_loss": 0.2928101691180308,
+    "train_runtime": 1671.3114,
     "train_samples": 363846,
-    "train_samples_per_second": 10836.891,
-    "train_steps_per_second": 42.353
+    "train_samples_per_second": 10885.045,
+    "train_steps_per_second": 42.541
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6569345593452454,
+  "best_metric": 0.3640855848789215,
   "best_model_checkpoint": "bert_tiny_lda_20_v1_qqp/checkpoint-4266",
   "epoch": 8.0,
   "eval_steps": 500,
@@ -10,156 +10,156 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.3419596254825592,
-      "learning_rate": 0.00098,
-      "loss": 0.6612,
+      "grad_norm": 2.2224717140197754,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4896,
       "step": 1422
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6581591367721558,
-      "eval_runtime": 12.6846,
-      "eval_samples_per_second": 3187.326,
-      "eval_steps_per_second": 12.456,
+      "eval_accuracy": 0.7902300272075191,
+      "eval_combined_score": 0.7359430605989925,
+      "eval_f1": 0.6816560939904658,
+      "eval_loss": 0.4397190511226654,
+      "eval_runtime": 12.5102,
+      "eval_samples_per_second": 3231.772,
+      "eval_steps_per_second": 12.63,
       "step": 1422
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.10207448154687881,
-      "learning_rate": 0.00096,
-      "loss": 0.659,
+      "grad_norm": 2.527693510055542,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3891,
       "step": 2844
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6575562953948975,
-      "eval_runtime": 12.7272,
-      "eval_samples_per_second": 3176.652,
-      "eval_steps_per_second": 12.414,
+      "eval_accuracy": 0.8246599060103883,
+      "eval_combined_score": 0.7960138699152457,
+      "eval_f1": 0.7673678338201031,
+      "eval_loss": 0.3805816173553467,
+      "eval_runtime": 12.45,
+      "eval_samples_per_second": 3247.397,
+      "eval_steps_per_second": 12.691,
       "step": 2844
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.05861695855855942,
-      "learning_rate": 0.00094,
-      "loss": 0.6587,
+      "grad_norm": 2.5017569065093994,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3332,
       "step": 4266
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6569345593452454,
-      "eval_runtime": 12.6759,
-      "eval_samples_per_second": 3189.518,
-      "eval_steps_per_second": 12.465,
+      "eval_accuracy": 0.8355181795696265,
+      "eval_combined_score": 0.8088284122851408,
+      "eval_f1": 0.7821386450006552,
+      "eval_loss": 0.3640855848789215,
+      "eval_runtime": 12.5303,
+      "eval_samples_per_second": 3226.578,
+      "eval_steps_per_second": 12.609,
       "step": 4266
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.08356954157352448,
-      "learning_rate": 0.00092,
-      "loss": 0.6585,
+      "grad_norm": 3.1053719520568848,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.29,
       "step": 5688
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 12.632,
-      "eval_samples_per_second": 3200.604,
-      "eval_steps_per_second": 12.508,
+      "eval_accuracy": 0.8448182043037349,
+      "eval_combined_score": 0.8157882062236504,
+      "eval_f1": 0.786758208143566,
+      "eval_loss": 0.3665860891342163,
+      "eval_runtime": 12.4885,
+      "eval_samples_per_second": 3237.387,
+      "eval_steps_per_second": 12.652,
       "step": 5688
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.12464679032564163,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6585,
+      "grad_norm": 2.464869976043701,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2535,
       "step": 7110
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 12.6421,
-      "eval_samples_per_second": 3198.044,
-      "eval_steps_per_second": 12.498,
+      "eval_accuracy": 0.8485035864457087,
+      "eval_combined_score": 0.8231024058991432,
+      "eval_f1": 0.7977012253525777,
+      "eval_loss": 0.37237754464149475,
+      "eval_runtime": 12.5228,
+      "eval_samples_per_second": 3228.523,
+      "eval_steps_per_second": 12.617,
       "step": 7110
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.03694356605410576,
-      "learning_rate": 0.00088,
-      "loss": 0.6585,
+      "grad_norm": 2.264439821243286,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2212,
       "step": 8532
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.658168613910675,
-      "eval_runtime": 12.4501,
-      "eval_samples_per_second": 3247.364,
-      "eval_steps_per_second": 12.691,
+      "eval_accuracy": 0.8517437546376453,
+      "eval_combined_score": 0.8279754900450264,
+      "eval_f1": 0.8042072254524074,
+      "eval_loss": 0.3715839982032776,
+      "eval_runtime": 12.4973,
+      "eval_samples_per_second": 3235.1,
+      "eval_steps_per_second": 12.643,
       "step": 8532
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.050063714385032654,
-      "learning_rate": 0.00086,
-      "loss": 0.6585,
+      "grad_norm": 2.810699701309204,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1947,
       "step": 9954
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 12.5094,
-      "eval_samples_per_second": 3231.962,
-      "eval_steps_per_second": 12.63,
+      "eval_accuracy": 0.8528320554044027,
+      "eval_combined_score": 0.8289389634820179,
+      "eval_f1": 0.805045871559633,
+      "eval_loss": 0.4038587510585785,
+      "eval_runtime": 12.2445,
+      "eval_samples_per_second": 3301.882,
+      "eval_steps_per_second": 12.904,
       "step": 9954
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.11186650395393372,
-      "learning_rate": 0.00084,
-      "loss": 0.6585,
+      "grad_norm": 2.704545259475708,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1711,
       "step": 11376
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 12.4754,
-      "eval_samples_per_second": 3240.777,
-      "eval_steps_per_second": 12.665,
+      "eval_accuracy": 0.8534504081127875,
+      "eval_combined_score": 0.8249385694575275,
+      "eval_f1": 0.7964267308022677,
+      "eval_loss": 0.4275510013103485,
+      "eval_runtime": 12.4169,
+      "eval_samples_per_second": 3256.041,
+      "eval_steps_per_second": 12.725,
       "step": 11376
     },
     {
       "epoch": 8.0,
       "step": 11376,
       "total_flos": 7.633075201391002e+16,
-      "train_loss": 0.6589229814446258,
-      "train_runtime": 1678.7379,
-      "train_samples_per_second": 10836.891,
-      "train_steps_per_second": 42.353
+      "train_loss": 0.2928101691180308,
+      "train_runtime": 1671.3114,
+      "train_samples_per_second": 10885.045,
+      "train_steps_per_second": 42.541
     }
   ],
   "logging_steps": 1,