End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_lda_50_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_50_v1_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6751
-- Matthews Correlation: 0.1011
-- Accuracy: 0.6529
+- Loss: 0.6144
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 7.0,
+    "epoch": 9.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6180264353752136,
+    "eval_loss": 0.6143654584884644,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6567,
+    "eval_runtime": 0.6808,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1588.131,
-    "eval_steps_per_second": 7.613,
-    "total_flos": 7874519220341760.0,
-    "train_loss": 0.6522878198062673,
-    "train_runtime": 116.2945,
+    "eval_samples_per_second": 1531.933,
+    "eval_steps_per_second": 7.344,
+    "total_flos": 1.012438185472512e+16,
+    "train_loss": 0.5555953512004778,
+    "train_runtime": 156.1294,
     "train_samples": 8551,
-    "train_samples_per_second": 3676.442,
-    "train_steps_per_second": 14.618
+    "train_samples_per_second": 2738.434,
+    "train_steps_per_second": 10.888
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 7.0,
+    "epoch": 9.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6180264353752136,
+    "eval_loss": 0.6143654584884644,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6567,
+    "eval_runtime": 0.6808,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1588.131,
-    "eval_steps_per_second": 7.613
+    "eval_samples_per_second": 1531.933,
+    "eval_steps_per_second": 7.344
 }

logs/events.out.tfevents.1733309492.ki-g0008.1207984.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af472d2c158fc91455af730d1d8660c2f92cc8ce5b947d7fb210d637ebdd457
+size 475

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 7874519220341760.0,
-    "train_loss": 0.6522878198062673,
-    "train_runtime": 116.2945,
+    "epoch": 9.0,
+    "total_flos": 1.012438185472512e+16,
+    "train_loss": 0.5555953512004778,
+    "train_runtime": 156.1294,
     "train_samples": 8551,
-    "train_samples_per_second": 3676.442,
-    "train_steps_per_second": 14.618
+    "train_samples_per_second": 2738.434,
+    "train_steps_per_second": 10.888
 }

trainer_state.json

@@ -1,140 +1,174 @@
 {
-  "best_metric": 0.6180264353752136,
-  "best_model_checkpoint": "bert_base_lda_50_v1_cola/checkpoint-68",
-  "epoch": 7.0,
+  "best_metric": 0.6143654584884644,
+  "best_model_checkpoint": "bert_base_lda_50_v1_cola/checkpoint-136",
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 238,
+  "global_step": 306,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.4958297610282898,
-      "learning_rate": 0.00098,
-      "loss": 0.9041,
+      "grad_norm": 1.0722399950027466,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6197,
       "step": 34
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6206743121147156,
+      "eval_loss": 0.6198203563690186,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6845,
-      "eval_samples_per_second": 1523.666,
-      "eval_steps_per_second": 7.304,
+      "eval_runtime": 0.6997,
+      "eval_samples_per_second": 1490.583,
+      "eval_steps_per_second": 7.146,
       "step": 34
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.8084903359413147,
-      "learning_rate": 0.00096,
-      "loss": 0.6134,
+      "grad_norm": 0.8135132789611816,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6125,
       "step": 68
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6180264353752136,
+      "eval_loss": 0.617854118347168,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.676,
-      "eval_samples_per_second": 1542.859,
-      "eval_steps_per_second": 7.396,
+      "eval_runtime": 0.6932,
+      "eval_samples_per_second": 1504.688,
+      "eval_steps_per_second": 7.213,
       "step": 68
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.8251405358314514,
-      "learning_rate": 0.00094,
-      "loss": 0.6096,
+      "grad_norm": 1.1037389039993286,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6104,
       "step": 102
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6191930770874023,
+      "eval_loss": 0.6171332001686096,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6728,
-      "eval_samples_per_second": 1550.274,
-      "eval_steps_per_second": 7.432,
+      "eval_runtime": 0.693,
+      "eval_samples_per_second": 1505.018,
+      "eval_steps_per_second": 7.215,
       "step": 102
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.5498630404472351,
-      "learning_rate": 0.00092,
-      "loss": 0.6106,
+      "grad_norm": 1.4333645105361938,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6101,
       "step": 136
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6188915967941284,
+      "eval_loss": 0.6143654584884644,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6722,
-      "eval_samples_per_second": 1551.733,
-      "eval_steps_per_second": 7.439,
+      "eval_runtime": 0.6884,
+      "eval_samples_per_second": 1514.999,
+      "eval_steps_per_second": 7.263,
       "step": 136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.8158091306686401,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6105,
+      "grad_norm": 0.863571286201477,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5982,
       "step": 170
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6191930770874023,
+      "eval_loss": 0.6144019961357117,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6636,
-      "eval_samples_per_second": 1571.701,
-      "eval_steps_per_second": 7.535,
+      "eval_runtime": 0.6975,
+      "eval_samples_per_second": 1495.254,
+      "eval_steps_per_second": 7.168,
       "step": 170
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.35109996795654297,
-      "learning_rate": 0.00088,
-      "loss": 0.609,
+      "grad_norm": 1.4660353660583496,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5682,
       "step": 204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6192848086357117,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6699,
-      "eval_samples_per_second": 1556.948,
-      "eval_steps_per_second": 7.464,
+      "eval_accuracy": 0.6874400973320007,
+      "eval_loss": 0.6281394362449646,
+      "eval_matthews_correlation": 0.05263079744232175,
+      "eval_runtime": 0.6831,
+      "eval_samples_per_second": 1526.915,
+      "eval_steps_per_second": 7.32,
       "step": 204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 1.0719987154006958,
-      "learning_rate": 0.00086,
-      "loss": 0.6089,
+      "grad_norm": 2.6993749141693115,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5152,
       "step": 238
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6189046502113342,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6659,
-      "eval_samples_per_second": 1566.356,
-      "eval_steps_per_second": 7.509,
+      "eval_accuracy": 0.6567593216896057,
+      "eval_loss": 0.6455426812171936,
+      "eval_matthews_correlation": 0.10027467906851985,
+      "eval_runtime": 0.6842,
+      "eval_samples_per_second": 1524.455,
+      "eval_steps_per_second": 7.308,
       "step": 238
     },
     {
-      "epoch": 7.0,
-      "step": 238,
-      "total_flos": 7874519220341760.0,
-      "train_loss": 0.6522878198062673,
-      "train_runtime": 116.2945,
-      "train_samples_per_second": 3676.442,
-      "train_steps_per_second": 14.618
+      "epoch": 8.0,
+      "grad_norm": 2.5550780296325684,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4552,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6634707450866699,
+      "eval_loss": 0.6827359795570374,
+      "eval_matthews_correlation": 0.09702614755535717,
+      "eval_runtime": 0.6854,
+      "eval_samples_per_second": 1521.657,
+      "eval_steps_per_second": 7.295,
+      "step": 272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.5828475952148438,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4108,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6529242396354675,
+      "eval_loss": 0.675087034702301,
+      "eval_matthews_correlation": 0.10114728369225008,
+      "eval_runtime": 0.6887,
+      "eval_samples_per_second": 1514.398,
+      "eval_steps_per_second": 7.26,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "step": 306,
+      "total_flos": 1.012438185472512e+16,
+      "train_loss": 0.5555953512004778,
+      "train_runtime": 156.1294,
+      "train_samples_per_second": 2738.434,
+      "train_steps_per_second": 10.888
     }
   ],
   "logging_steps": 1,
@@ -163,7 +197,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7874519220341760.0,
+  "total_flos": 1.012438185472512e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null