End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_lda_5_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: 0.837867919861489
+    - name: F1
+      type: f1
+      value: 0.7795971890655996
 ---
 
 <!-- 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_base_lda_5_v1_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5420
-- Accuracy: 0.8560
-- F1: 0.8002
-- Combined Score: 0.8281
+- Loss: 0.3662
+- Accuracy: 0.8379
+- F1: 0.7796
+- Combined Score: 0.8087
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6573427319526672,
-    "eval_runtime": 25.4059,
+    "epoch": 7.0,
+    "eval_accuracy": 0.837867919861489,
+    "eval_combined_score": 0.8087325544635443,
+    "eval_f1": 0.7795971890655996,
+    "eval_loss": 0.36624589562416077,
+    "eval_runtime": 25.8147,
     "eval_samples": 40430,
-    "eval_samples_per_second": 1591.364,
-    "eval_steps_per_second": 6.219,
-    "total_flos": 2.8719571514554368e+17,
-    "train_loss": 0.662904584681658,
-    "train_runtime": 3658.7532,
+    "eval_samples_per_second": 1566.16,
+    "eval_steps_per_second": 6.121,
+    "total_flos": 3.3506166766980096e+17,
+    "train_loss": 0.2248973712304138,
+    "train_runtime": 4307.3931,
     "train_samples": 363846,
-    "train_samples_per_second": 4972.268,
-    "train_steps_per_second": 19.433
+    "train_samples_per_second": 4223.506,
+    "train_steps_per_second": 16.507
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 6.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6573427319526672,
-    "eval_runtime": 25.4059,
+    "epoch": 7.0,
+    "eval_accuracy": 0.837867919861489,
+    "eval_combined_score": 0.8087325544635443,
+    "eval_f1": 0.7795971890655996,
+    "eval_loss": 0.36624589562416077,
+    "eval_runtime": 25.8147,
     "eval_samples": 40430,
-    "eval_samples_per_second": 1591.364,
-    "eval_steps_per_second": 6.219
+    "eval_samples_per_second": 1566.16,
+    "eval_steps_per_second": 6.121
 }

logs/events.out.tfevents.1733315543.ki-g0008.1206925.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e77ca3599e097c4e1bbeb21d0758a01fa846544ed67765b83c8c9b94d98f31
+size 515

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "total_flos": 2.8719571514554368e+17,
-    "train_loss": 0.662904584681658,
-    "train_runtime": 3658.7532,
+    "epoch": 7.0,
+    "total_flos": 3.3506166766980096e+17,
+    "train_loss": 0.2248973712304138,
+    "train_runtime": 4307.3931,
     "train_samples": 363846,
-    "train_samples_per_second": 4972.268,
-    "train_steps_per_second": 19.433
+    "train_samples_per_second": 4223.506,
+    "train_steps_per_second": 16.507
 }

trainer_state.json

@@ -1,129 +1,147 @@
 {
-  "best_metric": 0.6573427319526672,
-  "best_model_checkpoint": "bert_base_lda_5_v1_qqp/checkpoint-1422",
-  "epoch": 6.0,
+  "best_metric": 0.36624589562416077,
+  "best_model_checkpoint": "bert_base_lda_5_v1_qqp/checkpoint-2844",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 8532,
+  "global_step": 9954,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.3263278603553772,
-      "learning_rate": 0.00098,
-      "loss": 0.6633,
+      "grad_norm": 2.1425893306732178,
+      "learning_rate": 4.9e-05,
+      "loss": 0.449,
       "step": 1422
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 25.7365,
-      "eval_samples_per_second": 1570.918,
-      "eval_steps_per_second": 6.139,
+      "eval_accuracy": 0.8140489735345041,
+      "eval_combined_score": 0.7716723335193765,
+      "eval_f1": 0.7292956935042488,
+      "eval_loss": 0.3985694944858551,
+      "eval_runtime": 26.0018,
+      "eval_samples_per_second": 1554.894,
+      "eval_steps_per_second": 6.077,
       "step": 1422
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.06645578891038895,
-      "learning_rate": 0.00096,
-      "loss": 0.6589,
+      "grad_norm": 2.969003438949585,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3328,
       "step": 2844
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6579644680023193,
-      "eval_runtime": 25.7118,
-      "eval_samples_per_second": 1572.431,
-      "eval_steps_per_second": 6.145,
+      "eval_accuracy": 0.837867919861489,
+      "eval_combined_score": 0.8087325544635443,
+      "eval_f1": 0.7795971890655996,
+      "eval_loss": 0.36624589562416077,
+      "eval_runtime": 26.1365,
+      "eval_samples_per_second": 1546.878,
+      "eval_steps_per_second": 6.045,
       "step": 2844
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.055242717266082764,
-      "learning_rate": 0.00094,
-      "loss": 0.6797,
+      "grad_norm": 3.918194055557251,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2532,
       "step": 4266
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.658168613910675,
-      "eval_runtime": 25.8276,
-      "eval_samples_per_second": 1565.378,
-      "eval_steps_per_second": 6.117,
+      "eval_accuracy": 0.8429631461785803,
+      "eval_combined_score": 0.8202442098211203,
+      "eval_f1": 0.7975252734636604,
+      "eval_loss": 0.36973831057548523,
+      "eval_runtime": 25.9614,
+      "eval_samples_per_second": 1557.314,
+      "eval_steps_per_second": 6.086,
       "step": 4266
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.08355461061000824,
-      "learning_rate": 0.00092,
-      "loss": 0.6585,
+      "grad_norm": 3.43363618850708,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1908,
       "step": 5688
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 25.6995,
-      "eval_samples_per_second": 1573.185,
-      "eval_steps_per_second": 6.148,
+      "eval_accuracy": 0.8527825871877319,
+      "eval_combined_score": 0.8250288957737024,
+      "eval_f1": 0.797275204359673,
+      "eval_loss": 0.4016028940677643,
+      "eval_runtime": 26.0725,
+      "eval_samples_per_second": 1550.676,
+      "eval_steps_per_second": 6.06,
       "step": 5688
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.12464568763971329,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6585,
+      "grad_norm": 4.095367908477783,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1448,
       "step": 7110
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 25.7443,
-      "eval_samples_per_second": 1570.443,
-      "eval_steps_per_second": 6.137,
+      "eval_accuracy": 0.854167697254514,
+      "eval_combined_score": 0.8237032903441879,
+      "eval_f1": 0.7932388834338616,
+      "eval_loss": 0.46372607350349426,
+      "eval_runtime": 26.0419,
+      "eval_samples_per_second": 1552.5,
+      "eval_steps_per_second": 6.067,
       "step": 7110
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.03694356605410576,
-      "learning_rate": 0.00088,
-      "loss": 0.6585,
+      "grad_norm": 3.066826820373535,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.112,
       "step": 8532
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6579644680023193,
-      "eval_runtime": 25.7207,
-      "eval_samples_per_second": 1571.886,
-      "eval_steps_per_second": 6.143,
+      "eval_accuracy": 0.8571852584714321,
+      "eval_combined_score": 0.8304354144934339,
+      "eval_f1": 0.8036855705154358,
+      "eval_loss": 0.4905352294445038,
+      "eval_runtime": 26.1458,
+      "eval_samples_per_second": 1546.328,
+      "eval_steps_per_second": 6.043,
       "step": 8532
     },
     {
-      "epoch": 6.0,
-      "step": 8532,
-      "total_flos": 2.8719571514554368e+17,
-      "train_loss": 0.662904584681658,
-      "train_runtime": 3658.7532,
-      "train_samples_per_second": 4972.268,
-      "train_steps_per_second": 19.433
+      "epoch": 7.0,
+      "grad_norm": 3.6318132877349854,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0917,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8559980212713332,
+      "eval_combined_score": 0.8281156727273493,
+      "eval_f1": 0.8002333241833653,
+      "eval_loss": 0.5419512987136841,
+      "eval_runtime": 26.1065,
+      "eval_samples_per_second": 1548.654,
+      "eval_steps_per_second": 6.052,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "step": 9954,
+      "total_flos": 3.3506166766980096e+17,
+      "train_loss": 0.2248973712304138,
+      "train_runtime": 4307.3931,
+      "train_samples_per_second": 4223.506,
+      "train_steps_per_second": 16.507
     }
   ],
   "logging_steps": 1,
@@ -152,7 +170,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8719571514554368e+17,
+  "total_flos": 3.3506166766980096e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null