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_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5270758122743683
 ---
 
 <!-- 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_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0650
-- Accuracy: 0.5126
+- Loss: 0.6911
+- Accuracy: 0.5271
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 9.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.690503716468811,
-    "eval_runtime": 0.1895,
+    "eval_loss": 0.6910678148269653,
+    "eval_runtime": 0.1923,
     "eval_samples": 277,
-    "eval_samples_per_second": 1461.776,
-    "eval_steps_per_second": 10.554,
+    "eval_samples_per_second": 1440.095,
+    "eval_steps_per_second": 10.398,
     "total_flos": 2948159375308800.0,
-    "train_loss": 0.7451369815402561,
-    "train_runtime": 60.675,
+    "train_loss": 0.6356894334157308,
+    "train_runtime": 61.1905,
     "train_samples": 2490,
-    "train_samples_per_second": 2051.916,
-    "train_steps_per_second": 8.241
+    "train_samples_per_second": 2034.631,
+    "train_steps_per_second": 8.171
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 9.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.690503716468811,
-    "eval_runtime": 0.1895,
+    "eval_loss": 0.6910678148269653,
+    "eval_runtime": 0.1923,
     "eval_samples": 277,
-    "eval_samples_per_second": 1461.776,
-    "eval_steps_per_second": 10.554
+    "eval_samples_per_second": 1440.095,
+    "eval_steps_per_second": 10.398
 }

logs/events.out.tfevents.1733316540.ki-g0008.1208741.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73cf91ec9ac0fd934711d823fecc94f53d793051edd3df78dc6a312e21916f33
+size 405

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 9.0,
     "total_flos": 2948159375308800.0,
-    "train_loss": 0.7451369815402561,
-    "train_runtime": 60.675,
+    "train_loss": 0.6356894334157308,
+    "train_runtime": 61.1905,
     "train_samples": 2490,
-    "train_samples_per_second": 2051.916,
-    "train_steps_per_second": 8.241
+    "train_samples_per_second": 2034.631,
+    "train_steps_per_second": 8.171
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.690503716468811,
+  "best_metric": 0.6910678148269653,
   "best_model_checkpoint": "bert_base_lda_100_v1_rte/checkpoint-40",
   "epoch": 9.0,
   "eval_steps": 500,
@@ -10,156 +10,156 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.40931814908981323,
-      "learning_rate": 0.00098,
-      "loss": 1.1399,
+      "grad_norm": 0.8062904477119446,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7572,
       "step": 10
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7164514064788818,
-      "eval_runtime": 0.1901,
-      "eval_samples_per_second": 1456.892,
-      "eval_steps_per_second": 10.519,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.713447630405426,
+      "eval_runtime": 0.1924,
+      "eval_samples_per_second": 1439.88,
+      "eval_steps_per_second": 10.396,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.5890483260154724,
-      "learning_rate": 0.00096,
-      "loss": 0.7007,
+      "grad_norm": 1.4334803819656372,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7126,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6976816058158875,
-      "eval_runtime": 0.1858,
-      "eval_samples_per_second": 1490.725,
-      "eval_steps_per_second": 10.763,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6923933625221252,
+      "eval_runtime": 0.1913,
+      "eval_samples_per_second": 1448.012,
+      "eval_steps_per_second": 10.455,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.2279863804578781,
-      "learning_rate": 0.00094,
-      "loss": 0.6974,
+      "grad_norm": 0.9001538753509521,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6911,
       "step": 30
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6907293796539307,
-      "eval_runtime": 0.1855,
-      "eval_samples_per_second": 1493.531,
-      "eval_steps_per_second": 10.784,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.6912652254104614,
+      "eval_runtime": 0.2155,
+      "eval_samples_per_second": 1285.155,
+      "eval_steps_per_second": 9.279,
       "step": 30
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.2956705391407013,
-      "learning_rate": 0.00092,
-      "loss": 0.6952,
+      "grad_norm": 0.8192620873451233,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6914,
       "step": 40
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.690503716468811,
-      "eval_runtime": 0.184,
-      "eval_samples_per_second": 1505.452,
-      "eval_steps_per_second": 10.87,
+      "eval_loss": 0.6910678148269653,
+      "eval_runtime": 0.1917,
+      "eval_samples_per_second": 1444.602,
+      "eval_steps_per_second": 10.43,
       "step": 40
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.8746032118797302,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6971,
+      "grad_norm": 2.557899236679077,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6774,
       "step": 50
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6917870044708252,
-      "eval_runtime": 0.2041,
-      "eval_samples_per_second": 1356.868,
-      "eval_steps_per_second": 9.797,
+      "eval_accuracy": 0.5090252707581228,
+      "eval_loss": 0.7089632153511047,
+      "eval_runtime": 0.1914,
+      "eval_samples_per_second": 1447.292,
+      "eval_steps_per_second": 10.45,
       "step": 50
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.19928425550460815,
-      "learning_rate": 0.00088,
-      "loss": 0.6953,
+      "grad_norm": 2.7362091541290283,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6709,
       "step": 60
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6960035562515259,
-      "eval_runtime": 0.1859,
-      "eval_samples_per_second": 1490.395,
-      "eval_steps_per_second": 10.761,
+      "eval_accuracy": 0.48014440433212996,
+      "eval_loss": 0.7789549231529236,
+      "eval_runtime": 0.2059,
+      "eval_samples_per_second": 1345.393,
+      "eval_steps_per_second": 9.714,
       "step": 60
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.15525557100772858,
-      "learning_rate": 0.00086,
-      "loss": 0.6941,
+      "grad_norm": 3.2326953411102295,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5927,
       "step": 70
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6930421590805054,
-      "eval_runtime": 0.1867,
-      "eval_samples_per_second": 1483.886,
-      "eval_steps_per_second": 10.714,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.823212206363678,
+      "eval_runtime": 0.1901,
+      "eval_samples_per_second": 1457.47,
+      "eval_steps_per_second": 10.523,
       "step": 70
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.09055319428443909,
-      "learning_rate": 0.00084,
-      "loss": 0.6933,
+      "grad_norm": 2.318673610687256,
+      "learning_rate": 4.2e-05,
+      "loss": 0.511,
       "step": 80
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6934510469436646,
-      "eval_runtime": 0.1875,
-      "eval_samples_per_second": 1477.333,
-      "eval_steps_per_second": 10.667,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.9742180705070496,
+      "eval_runtime": 0.1994,
+      "eval_samples_per_second": 1389.271,
+      "eval_steps_per_second": 10.031,
       "step": 80
     },
     {
       "epoch": 9.0,
-      "grad_norm": 0.2684151828289032,
-      "learning_rate": 0.00082,
-      "loss": 0.6933,
+      "grad_norm": 9.328105926513672,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4169,
       "step": 90
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6934651136398315,
-      "eval_runtime": 0.1888,
-      "eval_samples_per_second": 1466.799,
-      "eval_steps_per_second": 10.591,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 1.0650445222854614,
+      "eval_runtime": 0.192,
+      "eval_samples_per_second": 1443.08,
+      "eval_steps_per_second": 10.419,
       "step": 90
     },
     {
       "epoch": 9.0,
       "step": 90,
       "total_flos": 2948159375308800.0,
-      "train_loss": 0.7451369815402561,
-      "train_runtime": 60.675,
-      "train_samples_per_second": 2051.916,
-      "train_steps_per_second": 8.241
+      "train_loss": 0.6356894334157308,
+      "train_runtime": 61.1905,
+      "train_samples_per_second": 2034.631,
+      "train_steps_per_second": 8.171
     }
   ],
   "logging_steps": 1,