End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_lda_100_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: 0.8609448429384121
+    - name: F1
+      type: f1
+      value: 0.818621757646148
 ---
 
 <!-- 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_100_v1_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4346
-- Accuracy: 0.8693
-- F1: 0.8285
-- Combined Score: 0.8489
+- Loss: 0.3234
+- Accuracy: 0.8609
+- F1: 0.8186
+- Combined Score: 0.8398
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6573427319526672,
-    "eval_runtime": 25.19,
+    "epoch": 8.0,
+    "eval_accuracy": 0.8609448429384121,
+    "eval_combined_score": 0.8397833002922801,
+    "eval_f1": 0.818621757646148,
+    "eval_loss": 0.3234252333641052,
+    "eval_runtime": 25.7849,
     "eval_samples": 40430,
-    "eval_samples_per_second": 1604.999,
-    "eval_steps_per_second": 6.272,
-    "total_flos": 5.7439143029108736e+17,
-    "train_loss": 0.660555789909953,
-    "train_runtime": 7311.012,
+    "eval_samples_per_second": 1567.975,
+    "eval_steps_per_second": 6.128,
+    "total_flos": 3.8292762019405824e+17,
+    "train_loss": 0.2082672454469147,
+    "train_runtime": 4927.5674,
     "train_samples": 363846,
-    "train_samples_per_second": 2488.342,
-    "train_steps_per_second": 9.725
+    "train_samples_per_second": 3691.943,
+    "train_steps_per_second": 14.429
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.6318327974276527,
-    "eval_combined_score": 0.3159163987138264,
-    "eval_f1": 0.0,
-    "eval_loss": 0.6573427319526672,
-    "eval_runtime": 25.19,
+    "epoch": 8.0,
+    "eval_accuracy": 0.8609448429384121,
+    "eval_combined_score": 0.8397833002922801,
+    "eval_f1": 0.818621757646148,
+    "eval_loss": 0.3234252333641052,
+    "eval_runtime": 25.7849,
     "eval_samples": 40430,
-    "eval_samples_per_second": 1604.999,
-    "eval_steps_per_second": 6.272
+    "eval_samples_per_second": 1567.975,
+    "eval_steps_per_second": 6.128
 }

logs/events.out.tfevents.1733316279.ki-g0008.1208741.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fae320ae069ee9be859bcf4f0d45fd3d43c1dd5295f8ff3997edb82c78a37a0
+size 515

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "total_flos": 5.7439143029108736e+17,
-    "train_loss": 0.660555789909953,
-    "train_runtime": 7311.012,
+    "epoch": 8.0,
+    "total_flos": 3.8292762019405824e+17,
+    "train_loss": 0.2082672454469147,
+    "train_runtime": 4927.5674,
     "train_samples": 363846,
-    "train_samples_per_second": 2488.342,
-    "train_steps_per_second": 9.725
+    "train_samples_per_second": 3691.943,
+    "train_steps_per_second": 14.429
 }

trainer_state.json

@@ -1,237 +1,165 @@
 {
-  "best_metric": 0.6573427319526672,
-  "best_model_checkpoint": "bert_base_lda_100_v1_qqp/checkpoint-9954",
-  "epoch": 12.0,
+  "best_metric": 0.3234252333641052,
+  "best_model_checkpoint": "bert_base_lda_100_v1_qqp/checkpoint-4266",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 17064,
+  "global_step": 11376,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.40524590015411377,
-      "learning_rate": 0.00098,
-      "loss": 0.6618,
+      "grad_norm": 1.8851810693740845,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4474,
       "step": 1422
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6579644680023193,
-      "eval_runtime": 25.8103,
-      "eval_samples_per_second": 1566.428,
-      "eval_steps_per_second": 6.122,
+      "eval_accuracy": 0.8283947563690329,
+      "eval_combined_score": 0.7949221753238371,
+      "eval_f1": 0.7614495942786413,
+      "eval_loss": 0.3685195744037628,
+      "eval_runtime": 26.2526,
+      "eval_samples_per_second": 1540.036,
+      "eval_steps_per_second": 6.018,
       "step": 1422
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.11123429983854294,
-      "learning_rate": 0.00096,
-      "loss": 0.659,
+      "grad_norm": 2.972749710083008,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3271,
       "step": 2844
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6577603816986084,
-      "eval_runtime": 25.8043,
-      "eval_samples_per_second": 1566.796,
-      "eval_steps_per_second": 6.123,
+      "eval_accuracy": 0.847588424437299,
+      "eval_combined_score": 0.8289650340099699,
+      "eval_f1": 0.8103416435826409,
+      "eval_loss": 0.3386009633541107,
+      "eval_runtime": 26.2178,
+      "eval_samples_per_second": 1542.084,
+      "eval_steps_per_second": 6.026,
       "step": 2844
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.05524620786309242,
-      "learning_rate": 0.00094,
-      "loss": 0.6586,
+      "grad_norm": 3.082465887069702,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2564,
       "step": 4266
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.658168613910675,
-      "eval_runtime": 25.7089,
-      "eval_samples_per_second": 1572.608,
-      "eval_steps_per_second": 6.146,
+      "eval_accuracy": 0.8609448429384121,
+      "eval_combined_score": 0.8397833002922801,
+      "eval_f1": 0.818621757646148,
+      "eval_loss": 0.3234252333641052,
+      "eval_runtime": 26.1778,
+      "eval_samples_per_second": 1544.441,
+      "eval_steps_per_second": 6.036,
       "step": 4266
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.08355461061000824,
-      "learning_rate": 0.00092,
-      "loss": 0.679,
+      "grad_norm": 3.214107036590576,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1978,
       "step": 5688
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 25.8178,
-      "eval_samples_per_second": 1565.971,
-      "eval_steps_per_second": 6.12,
+      "eval_accuracy": 0.865322780113777,
+      "eval_combined_score": 0.845827594247875,
+      "eval_f1": 0.8263324083819731,
+      "eval_loss": 0.3627840280532837,
+      "eval_runtime": 26.0619,
+      "eval_samples_per_second": 1551.309,
+      "eval_steps_per_second": 6.062,
       "step": 5688
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.12464568763971329,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6585,
+      "grad_norm": 4.68060302734375,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1516,
       "step": 7110
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573521494865417,
-      "eval_runtime": 25.7885,
-      "eval_samples_per_second": 1567.756,
-      "eval_steps_per_second": 6.127,
+      "eval_accuracy": 0.869527578530794,
+      "eval_combined_score": 0.8474033176016561,
+      "eval_f1": 0.8252790566725182,
+      "eval_loss": 0.40143004059791565,
+      "eval_runtime": 26.1999,
+      "eval_samples_per_second": 1543.138,
+      "eval_steps_per_second": 6.031,
       "step": 7110
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.03694356605410576,
-      "learning_rate": 0.00088,
-      "loss": 0.6585,
+      "grad_norm": 4.411165237426758,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1169,
       "step": 8532
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6579644680023193,
-      "eval_runtime": 25.7865,
-      "eval_samples_per_second": 1567.876,
-      "eval_steps_per_second": 6.127,
+      "eval_accuracy": 0.867276774672273,
+      "eval_combined_score": 0.8475178249685433,
+      "eval_f1": 0.8277588752648135,
+      "eval_loss": 0.3963766396045685,
+      "eval_runtime": 26.1361,
+      "eval_samples_per_second": 1546.904,
+      "eval_steps_per_second": 6.045,
       "step": 8532
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.050063714385032654,
-      "learning_rate": 0.00086,
-      "loss": 0.6585,
+      "grad_norm": 2.608915090560913,
+      "learning_rate": 4.3e-05,
+      "loss": 0.093,
       "step": 9954
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 25.6987,
-      "eval_samples_per_second": 1573.233,
-      "eval_steps_per_second": 6.148,
+      "eval_accuracy": 0.8676230521889686,
+      "eval_combined_score": 0.8477775754772003,
+      "eval_f1": 0.8279320987654322,
+      "eval_loss": 0.4813096225261688,
+      "eval_runtime": 25.9104,
+      "eval_samples_per_second": 1560.379,
+      "eval_steps_per_second": 6.098,
       "step": 9954
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.11186650395393372,
-      "learning_rate": 0.00084,
-      "loss": 0.6585,
+      "grad_norm": 4.501567840576172,
+      "learning_rate": 4.2e-05,
+      "loss": 0.076,
       "step": 11376
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6573427319526672,
-      "eval_runtime": 25.6137,
-      "eval_samples_per_second": 1578.449,
-      "eval_steps_per_second": 6.169,
+      "eval_accuracy": 0.8693297056641108,
+      "eval_combined_score": 0.8489380492102074,
+      "eval_f1": 0.8285463927563042,
+      "eval_loss": 0.43455520272254944,
+      "eval_runtime": 26.0711,
+      "eval_samples_per_second": 1550.762,
+      "eval_steps_per_second": 6.06,
       "step": 11376
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.12153594195842743,
-      "learning_rate": 0.00082,
-      "loss": 0.6586,
-      "step": 12798
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6577603816986084,
-      "eval_runtime": 25.881,
-      "eval_samples_per_second": 1562.148,
-      "eval_steps_per_second": 6.105,
-      "step": 12798
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.039975930005311966,
-      "learning_rate": 0.0008,
-      "loss": 0.6586,
-      "step": 14220
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6577603816986084,
-      "eval_runtime": 25.6778,
-      "eval_samples_per_second": 1574.515,
-      "eval_steps_per_second": 6.153,
-      "step": 14220
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.04083885997533798,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6585,
-      "step": 15642
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6577603816986084,
-      "eval_runtime": 25.5811,
-      "eval_samples_per_second": 1580.466,
-      "eval_steps_per_second": 6.176,
-      "step": 15642
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.040914136916399,
-      "learning_rate": 0.00076,
-      "loss": 0.6585,
-      "step": 17064
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.6318327974276527,
-      "eval_combined_score": 0.3159163987138264,
-      "eval_f1": 0.0,
-      "eval_loss": 0.6575562953948975,
-      "eval_runtime": 25.6413,
-      "eval_samples_per_second": 1576.755,
-      "eval_steps_per_second": 6.162,
-      "step": 17064
-    },
-    {
-      "epoch": 12.0,
-      "step": 17064,
-      "total_flos": 5.7439143029108736e+17,
-      "train_loss": 0.660555789909953,
-      "train_runtime": 7311.012,
-      "train_samples_per_second": 2488.342,
-      "train_steps_per_second": 9.725
+      "epoch": 8.0,
+      "step": 11376,
+      "total_flos": 3.8292762019405824e+17,
+      "train_loss": 0.2082672454469147,
+      "train_runtime": 4927.5674,
+      "train_samples_per_second": 3691.943,
+      "train_steps_per_second": 14.429
     }
   ],
   "logging_steps": 1,
@@ -260,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.7439143029108736e+17,
+  "total_flos": 3.8292762019405824e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null