End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_100_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: 0.8063335163829398
 ---
 
 <!-- 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_100_v1_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7340
-- Accuracy: 0.7917
+- Loss: 0.4155
+- Accuracy: 0.8063
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 8.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.69140625,
-    "eval_runtime": 3.5427,
+    "eval_accuracy": 0.8063335163829398,
+    "eval_loss": 0.4154828190803528,
+    "eval_runtime": 3.5226,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1542.042,
-    "eval_steps_per_second": 6.21,
+    "eval_samples_per_second": 1550.833,
+    "eval_steps_per_second": 6.245,
     "total_flos": 1.1023616508628992e+17,
-    "train_loss": 0.6958369836574647,
-    "train_runtime": 1397.9533,
+    "train_loss": 0.2866605537693675,
+    "train_runtime": 1408.5203,
     "train_samples": 104743,
-    "train_samples_per_second": 3746.298,
-    "train_steps_per_second": 14.664
+    "train_samples_per_second": 3718.193,
+    "train_steps_per_second": 14.554
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 8.0,
-    "eval_accuracy": 0.5053999633900788,
-    "eval_loss": 0.69140625,
-    "eval_runtime": 3.5427,
+    "eval_accuracy": 0.8063335163829398,
+    "eval_loss": 0.4154828190803528,
+    "eval_runtime": 3.5226,
     "eval_samples": 5463,
-    "eval_samples_per_second": 1542.042,
-    "eval_steps_per_second": 6.21
+    "eval_samples_per_second": 1550.833,
+    "eval_steps_per_second": 6.245
 }

logs/events.out.tfevents.1733311243.ki-g0008.1208741.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78dfcc53aceb6ee29364c195850fa1251d90c880642aba447222118e6b97b94
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 8.0,
     "total_flos": 1.1023616508628992e+17,
-    "train_loss": 0.6958369836574647,
-    "train_runtime": 1397.9533,
+    "train_loss": 0.2866605537693675,
+    "train_runtime": 1408.5203,
     "train_samples": 104743,
-    "train_samples_per_second": 3746.298,
-    "train_steps_per_second": 14.664
+    "train_samples_per_second": 3718.193,
+    "train_steps_per_second": 14.554
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.69140625,
+  "best_metric": 0.4154828190803528,
   "best_model_checkpoint": "bert_base_lda_100_v1_qnli/checkpoint-1230",
   "epoch": 8.0,
   "eval_steps": 500,
@@ -10,140 +10,140 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.23485292494297028,
-      "learning_rate": 0.00098,
-      "loss": 0.7139,
+      "grad_norm": 3.7200541496276855,
+      "learning_rate": 4.9e-05,
+      "loss": 0.636,
       "step": 410
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6933804750442505,
-      "eval_runtime": 3.5205,
-      "eval_samples_per_second": 1551.757,
-      "eval_steps_per_second": 6.249,
+      "eval_accuracy": 0.7078528281164196,
+      "eval_loss": 0.5723043084144592,
+      "eval_runtime": 3.5417,
+      "eval_samples_per_second": 1542.464,
+      "eval_steps_per_second": 6.212,
       "step": 410
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.09086626023054123,
-      "learning_rate": 0.00096,
-      "loss": 0.6933,
+      "grad_norm": 3.76737904548645,
+      "learning_rate": 4.8e-05,
+      "loss": 0.471,
       "step": 820
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6933804750442505,
-      "eval_runtime": 3.45,
-      "eval_samples_per_second": 1583.494,
-      "eval_steps_per_second": 6.377,
+      "eval_accuracy": 0.80907926047959,
+      "eval_loss": 0.4177427887916565,
+      "eval_runtime": 3.541,
+      "eval_samples_per_second": 1542.774,
+      "eval_steps_per_second": 6.213,
       "step": 820
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.12760137021541595,
-      "learning_rate": 0.00094,
-      "loss": 0.6933,
+      "grad_norm": 4.409963607788086,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3689,
       "step": 1230
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.69140625,
-      "eval_runtime": 3.4972,
-      "eval_samples_per_second": 1562.095,
-      "eval_steps_per_second": 6.291,
+      "eval_accuracy": 0.8063335163829398,
+      "eval_loss": 0.4154828190803528,
+      "eval_runtime": 3.5825,
+      "eval_samples_per_second": 1524.909,
+      "eval_steps_per_second": 6.141,
       "step": 1230
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.01812651753425598,
-      "learning_rate": 0.00092,
-      "loss": 0.6931,
+      "grad_norm": 7.4005537033081055,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2829,
       "step": 1640
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.4925,
-      "eval_samples_per_second": 1564.198,
-      "eval_steps_per_second": 6.299,
+      "eval_accuracy": 0.7990115321252059,
+      "eval_loss": 0.48499900102615356,
+      "eval_runtime": 3.537,
+      "eval_samples_per_second": 1544.511,
+      "eval_steps_per_second": 6.22,
       "step": 1640
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.051437895745038986,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6932,
+      "grad_norm": 3.301100254058838,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2021,
       "step": 2050
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934648156166077,
-      "eval_runtime": 3.4809,
-      "eval_samples_per_second": 1569.414,
-      "eval_steps_per_second": 6.32,
+      "eval_accuracy": 0.7889438037708218,
+      "eval_loss": 0.5746128559112549,
+      "eval_runtime": 3.5393,
+      "eval_samples_per_second": 1543.523,
+      "eval_steps_per_second": 6.216,
       "step": 2050
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.05455218255519867,
-      "learning_rate": 0.00088,
-      "loss": 0.6932,
+      "grad_norm": 3.967524290084839,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1431,
       "step": 2460
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6933382749557495,
-      "eval_runtime": 3.5969,
-      "eval_samples_per_second": 1518.792,
-      "eval_steps_per_second": 6.116,
+      "eval_accuracy": 0.7920556470803588,
+      "eval_loss": 0.6877047419548035,
+      "eval_runtime": 3.5292,
+      "eval_samples_per_second": 1547.962,
+      "eval_steps_per_second": 6.234,
       "step": 2460
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.06181074306368828,
-      "learning_rate": 0.00086,
-      "loss": 0.6933,
+      "grad_norm": 6.012539386749268,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1066,
       "step": 2870
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5053999633900788,
-      "eval_loss": 0.6932539343833923,
-      "eval_runtime": 3.6153,
-      "eval_samples_per_second": 1511.066,
-      "eval_steps_per_second": 6.085,
+      "eval_accuracy": 0.7841845140032949,
+      "eval_loss": 0.7942188382148743,
+      "eval_runtime": 3.5505,
+      "eval_samples_per_second": 1538.67,
+      "eval_steps_per_second": 6.196,
       "step": 2870
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.13051092624664307,
-      "learning_rate": 0.00084,
-      "loss": 0.6934,
+      "grad_norm": 9.717620849609375,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0827,
       "step": 3280
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4946000366099213,
-      "eval_loss": 0.6934226751327515,
-      "eval_runtime": 3.4839,
-      "eval_samples_per_second": 1568.091,
-      "eval_steps_per_second": 6.315,
+      "eval_accuracy": 0.791689547867472,
+      "eval_loss": 0.7339684963226318,
+      "eval_runtime": 3.5897,
+      "eval_samples_per_second": 1521.835,
+      "eval_steps_per_second": 6.129,
       "step": 3280
     },
     {
       "epoch": 8.0,
       "step": 3280,
       "total_flos": 1.1023616508628992e+17,
-      "train_loss": 0.6958369836574647,
-      "train_runtime": 1397.9533,
-      "train_samples_per_second": 3746.298,
-      "train_steps_per_second": 14.664
+      "train_loss": 0.2866605537693675,
+      "train_runtime": 1408.5203,
+      "train_samples_per_second": 3718.193,
+      "train_steps_per_second": 14.554
     }
   ],
   "logging_steps": 1,