End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_5_v1_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7721032399780341
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_5_v1_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9600
-- Accuracy: 0.7428
+- Loss: 0.4835
+- Accuracy: 0.7721
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.691364049911499,
-    "eval_runtime": 3.5379,
+    "epoch": 7.0,
+    "eval_accuracy": 0.7721032399780341,
+    "eval_loss": 0.48353341221809387,
+    "eval_runtime": 3.5158,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1544.143,
-    "eval_steps_per_second": 6.218,
-    "total_flos": 1.6535424762943488e+17,
-    "train_loss": 0.6953946369450267,
-    "train_runtime": 2094.0003,
+    "eval_samples_per_second": 1553.845,
+    "eval_steps_per_second": 6.257,
+    "total_flos": 9.645664445050368e+16,
+    "train_loss": 0.3142849300796562,
+    "train_runtime": 1232.997,
     "train_samples": 104743,
-    "train_samples_per_second": 2501.026,
-    "train_steps_per_second": 9.79
+    "train_samples_per_second": 4247.496,
+    "train_steps_per_second": 16.626
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.691364049911499,
-    "eval_runtime": 3.5379,
+    "epoch": 7.0,
+    "eval_accuracy": 0.7721032399780341,
+    "eval_loss": 0.48353341221809387,
+    "eval_runtime": 3.5158,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1544.143,
-    "eval_steps_per_second": 6.218
+    "eval_samples_per_second": 1553.845,
+    "eval_steps_per_second": 6.257
 }

logs/events.out.tfevents.1733311142.ki-g0008.1206925.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51900596be796b22c6ce959ac917967a0e43abafa83b34505fb2d806bc4ac44
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 12.0,
-    "total_flos": 1.6535424762943488e+17,
-    "train_loss": 0.6953946369450267,
-    "train_runtime": 2094.0003,
+    "epoch": 7.0,
+    "total_flos": 9.645664445050368e+16,
+    "train_loss": 0.3142849300796562,
+    "train_runtime": 1232.997,
     "train_samples": 104743,
-    "train_samples_per_second": 2501.026,
-    "train_steps_per_second": 9.79
+    "train_samples_per_second": 4247.496,
+    "train_steps_per_second": 16.626
 }

trainer_state.json

@@ -1,213 +1,133 @@
 {
-  "best_metric": 0.691364049911499,
-  "best_model_checkpoint": "bert_base_lda_5_v1_qnli/checkpoint-2870",
-  "epoch": 12.0,
+  "best_metric": 0.48353341221809387,
+  "best_model_checkpoint": "bert_base_lda_5_v1_qnli/checkpoint-820",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 4920,
+  "global_step": 2870,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.2550521492958069,
-      "learning_rate": 0.00098,
-      "loss": 0.7195,
+      "grad_norm": 2.9573304653167725,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6432,
       "step": 410
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6935492157936096,
-      "eval_runtime": 3.531,
-      "eval_samples_per_second": 1547.152,
-      "eval_steps_per_second": 6.231,
+      "eval_accuracy": 0.7056562328390994,
+      "eval_loss": 0.5685960650444031,
+      "eval_runtime": 3.5298,
+      "eval_samples_per_second": 1547.692,
+      "eval_steps_per_second": 6.233,
       "step": 410
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.3675061762332916,
-      "learning_rate": 0.00096,
-      "loss": 0.6932,
+      "grad_norm": 3.638329267501831,
+      "learning_rate": 4.8e-05,
+      "loss": 0.514,
       "step": 820
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934226751327515,
-      "eval_runtime": 3.5215,
-      "eval_samples_per_second": 1551.347,
-      "eval_steps_per_second": 6.247,
+      "eval_accuracy": 0.7721032399780341,
+      "eval_loss": 0.48353341221809387,
+      "eval_runtime": 3.544,
+      "eval_samples_per_second": 1541.473,
+      "eval_steps_per_second": 6.208,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.12713126838207245,
-      "learning_rate": 0.00094,
-      "loss": 0.6932,
+      "grad_norm": 4.854526042938232,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3845,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6932539343833923,
-      "eval_runtime": 3.5229,
-      "eval_samples_per_second": 1550.697,
-      "eval_steps_per_second": 6.245,
+      "eval_accuracy": 0.7651473549331869,
+      "eval_loss": 0.5230943560600281,
+      "eval_runtime": 3.5214,
+      "eval_samples_per_second": 1551.356,
+      "eval_steps_per_second": 6.247,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.01812651753425598,
-      "learning_rate": 0.00092,
-      "loss": 0.6932,
+      "grad_norm": 8.325188636779785,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2671,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4831,
-      "eval_samples_per_second": 1568.421,
-      "eval_steps_per_second": 6.316,
+      "eval_accuracy": 0.7607541643785466,
+      "eval_loss": 0.6301699280738831,
+      "eval_runtime": 3.5684,
+      "eval_samples_per_second": 1530.923,
+      "eval_steps_per_second": 6.165,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.047646842896938324,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6932,
+      "grad_norm": 6.31276273727417,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1749,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934648156166077,
-      "eval_runtime": 3.5307,
-      "eval_samples_per_second": 1547.287,
-      "eval_steps_per_second": 6.231,
+      "eval_accuracy": 0.7634999084751968,
+      "eval_loss": 0.7120682597160339,
+      "eval_runtime": 3.6011,
+      "eval_samples_per_second": 1517.049,
+      "eval_steps_per_second": 6.109,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.05455608665943146,
-      "learning_rate": 0.00088,
-      "loss": 0.6932,
+      "grad_norm": 8.96873950958252,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1231,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.5763,
-      "eval_samples_per_second": 1527.541,
-      "eval_steps_per_second": 6.152,
+      "eval_accuracy": 0.7618524620172067,
+      "eval_loss": 0.7853891849517822,
+      "eval_runtime": 3.5353,
+      "eval_samples_per_second": 1545.281,
+      "eval_steps_per_second": 6.223,
       "step": 2460
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.019881071522831917,
-      "learning_rate": 0.00086,
-      "loss": 0.6931,
+      "grad_norm": 4.691504001617432,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0932,
       "step": 2870
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.691364049911499,
-      "eval_runtime": 3.6965,
-      "eval_samples_per_second": 1477.89,
-      "eval_steps_per_second": 5.952,
+      "eval_accuracy": 0.7428153029470986,
+      "eval_loss": 0.9599586129188538,
+      "eval_runtime": 3.5825,
+      "eval_samples_per_second": 1524.904,
+      "eval_steps_per_second": 6.141,
       "step": 2870
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.13051092624664307,
-      "learning_rate": 0.00084,
-      "loss": 0.693,
-      "step": 3280
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934226751327515,
-      "eval_runtime": 3.4868,
-      "eval_samples_per_second": 1566.758,
-      "eval_steps_per_second": 6.309,
-      "step": 3280
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.05455218255519867,
-      "learning_rate": 0.00082,
-      "loss": 0.6932,
-      "step": 3690
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.5099,
-      "eval_samples_per_second": 1556.447,
-      "eval_steps_per_second": 6.268,
-      "step": 3690
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 0.2007143646478653,
-      "learning_rate": 0.0008,
-      "loss": 0.6933,
-      "step": 4100
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6936336159706116,
-      "eval_runtime": 3.4934,
-      "eval_samples_per_second": 1563.794,
-      "eval_steps_per_second": 6.298,
-      "step": 4100
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.09045995026826859,
-      "learning_rate": 0.0007800000000000001,
-      "loss": 0.6935,
-      "step": 4510
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.5482,
-      "eval_samples_per_second": 1539.66,
-      "eval_steps_per_second": 6.2,
-      "step": 4510
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.014760163612663746,
-      "learning_rate": 0.00076,
-      "loss": 0.6932,
-      "step": 4920
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934226751327515,
-      "eval_runtime": 3.5278,
-      "eval_samples_per_second": 1548.578,
-      "eval_steps_per_second": 6.236,
-      "step": 4920
-    },
-    {
-      "epoch": 12.0,
-      "step": 4920,
-      "total_flos": 1.6535424762943488e+17,
-      "train_loss": 0.6953946369450267,
-      "train_runtime": 2094.0003,
-      "train_samples_per_second": 2501.026,
-      "train_steps_per_second": 9.79
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 9.645664445050368e+16,
+      "train_loss": 0.3142849300796562,
+      "train_runtime": 1232.997,
+      "train_samples_per_second": 4247.496,
+      "train_steps_per_second": 16.626
     }
   ],
   "logging_steps": 1,
@@ -236,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6535424762943488e+17,
+  "total_flos": 9.645664445050368e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null