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:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_lda_100_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_100_v1_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8737
-- Matthews Correlation: 0.1050
-- Accuracy: 0.6558
+- Loss: 0.6179
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 9.0,
+    "epoch": 8.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6172530651092529,
+    "eval_loss": 0.6178625822067261,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.657,
+    "eval_runtime": 0.666,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1587.412,
-    "eval_steps_per_second": 7.61,
-    "total_flos": 1.012438185472512e+16,
-    "train_loss": 0.6354695613088172,
-    "train_runtime": 151.3706,
+    "eval_samples_per_second": 1566.008,
+    "eval_steps_per_second": 7.507,
+    "total_flos": 8999450537533440.0,
+    "train_loss": 0.5321676205186283,
+    "train_runtime": 137.2005,
     "train_samples": 8551,
-    "train_samples_per_second": 2824.524,
-    "train_steps_per_second": 11.231
+    "train_samples_per_second": 3116.242,
+    "train_steps_per_second": 12.391
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 9.0,
+    "epoch": 8.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6172530651092529,
+    "eval_loss": 0.6178625822067261,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.657,
+    "eval_runtime": 0.666,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1587.412,
-    "eval_steps_per_second": 7.61
+    "eval_samples_per_second": 1566.008,
+    "eval_steps_per_second": 7.507
 }

logs/events.out.tfevents.1733309477.ki-g0008.1208741.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33703337af4cc66bd9093002a4cabe02300735d24d14c6eac9685e62d48b0e6b
+size 475

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "total_flos": 1.012438185472512e+16,
-    "train_loss": 0.6354695613088172,
-    "train_runtime": 151.3706,
+    "epoch": 8.0,
+    "total_flos": 8999450537533440.0,
+    "train_loss": 0.5321676205186283,
+    "train_runtime": 137.2005,
     "train_samples": 8551,
-    "train_samples_per_second": 2824.524,
-    "train_steps_per_second": 11.231
+    "train_samples_per_second": 3116.242,
+    "train_steps_per_second": 12.391
 }

trainer_state.json

@@ -1,174 +1,157 @@
 {
-  "best_metric": 0.6172530651092529,
-  "best_model_checkpoint": "bert_base_lda_100_v1_cola/checkpoint-136",
-  "epoch": 9.0,
+  "best_metric": 0.6178625822067261,
+  "best_model_checkpoint": "bert_base_lda_100_v1_cola/checkpoint-102",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 306,
+  "global_step": 272,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.44009315967559814,
-      "learning_rate": 0.00098,
-      "loss": 0.8363,
+      "grad_norm": 0.8181986808776855,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6207,
       "step": 34
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.62235027551651,
+      "eval_loss": 0.6229906678199768,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6729,
-      "eval_samples_per_second": 1550.034,
-      "eval_steps_per_second": 7.431,
+      "eval_runtime": 0.7078,
+      "eval_samples_per_second": 1473.659,
+      "eval_steps_per_second": 7.065,
       "step": 34
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.086220145225525,
-      "learning_rate": 0.00096,
-      "loss": 0.614,
+      "grad_norm": 1.3978294134140015,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6135,
       "step": 68
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6187998056411743,
+      "eval_loss": 0.6196237802505493,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6802,
-      "eval_samples_per_second": 1533.396,
-      "eval_steps_per_second": 7.351,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 1517.614,
+      "eval_steps_per_second": 7.275,
       "step": 68
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.9242515563964844,
-      "learning_rate": 0.00094,
-      "loss": 0.6097,
+      "grad_norm": 1.9987629652023315,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6074,
       "step": 102
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6179346442222595,
+      "eval_loss": 0.6178625822067261,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6775,
-      "eval_samples_per_second": 1539.536,
-      "eval_steps_per_second": 7.38,
+      "eval_runtime": 0.6803,
+      "eval_samples_per_second": 1533.121,
+      "eval_steps_per_second": 7.35,
       "step": 102
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.8711050152778625,
-      "learning_rate": 0.00092,
-      "loss": 0.6099,
+      "grad_norm": 1.9304279088974,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5969,
       "step": 136
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6172530651092529,
+      "eval_loss": 0.6277948617935181,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6749,
-      "eval_samples_per_second": 1545.458,
-      "eval_steps_per_second": 7.409,
+      "eval_runtime": 0.6899,
+      "eval_samples_per_second": 1511.79,
+      "eval_steps_per_second": 7.247,
       "step": 136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.8325810432434082,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6106,
+      "grad_norm": 1.3234096765518188,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5522,
       "step": 170
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6188990473747253,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6649,
-      "eval_samples_per_second": 1568.772,
-      "eval_steps_per_second": 7.52,
+      "eval_accuracy": 0.6615532040596008,
+      "eval_loss": 0.623870849609375,
+      "eval_matthews_correlation": 0.055798711473707796,
+      "eval_runtime": 0.6815,
+      "eval_samples_per_second": 1530.554,
+      "eval_steps_per_second": 7.337,
       "step": 170
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.4087560772895813,
-      "learning_rate": 0.00088,
-      "loss": 0.6084,
+      "grad_norm": 2.008174419403076,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4812,
       "step": 204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6180058121681213,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6712,
-      "eval_samples_per_second": 1553.955,
-      "eval_steps_per_second": 7.449,
+      "eval_accuracy": 0.6845637559890747,
+      "eval_loss": 0.6719733476638794,
+      "eval_matthews_correlation": 0.12095523242891448,
+      "eval_runtime": 0.6877,
+      "eval_samples_per_second": 1516.73,
+      "eval_steps_per_second": 7.271,
       "step": 204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 1.4120560884475708,
-      "learning_rate": 0.00086,
-      "loss": 0.6109,
+      "grad_norm": 2.082489490509033,
+      "learning_rate": 4.3e-05,
+      "loss": 0.416,
       "step": 238
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6191930770874023,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6707,
-      "eval_samples_per_second": 1555.096,
-      "eval_steps_per_second": 7.455,
+      "eval_accuracy": 0.6251198649406433,
+      "eval_loss": 0.7045519351959229,
+      "eval_matthews_correlation": 0.10103917683294436,
+      "eval_runtime": 0.6722,
+      "eval_samples_per_second": 1551.541,
+      "eval_steps_per_second": 7.438,
       "step": 238
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.43506714701652527,
-      "learning_rate": 0.00084,
-      "loss": 0.6102,
+      "grad_norm": 3.2819783687591553,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3693,
       "step": 272
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6204514503479004,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.664,
-      "eval_samples_per_second": 1570.867,
-      "eval_steps_per_second": 7.531,
+      "eval_accuracy": 0.6558005809783936,
+      "eval_loss": 0.8737056255340576,
+      "eval_matthews_correlation": 0.1049535667908795,
+      "eval_runtime": 0.6691,
+      "eval_samples_per_second": 1558.794,
+      "eval_steps_per_second": 7.473,
       "step": 272
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.45157426595687866,
-      "learning_rate": 0.00082,
-      "loss": 0.6094,
-      "step": 306
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6259568929672241,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6606,
-      "eval_samples_per_second": 1578.79,
-      "eval_steps_per_second": 7.569,
-      "step": 306
-    },
-    {
-      "epoch": 9.0,
-      "step": 306,
-      "total_flos": 1.012438185472512e+16,
-      "train_loss": 0.6354695613088172,
-      "train_runtime": 151.3706,
-      "train_samples_per_second": 2824.524,
-      "train_steps_per_second": 11.231
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 8999450537533440.0,
+      "train_loss": 0.5321676205186283,
+      "train_runtime": 137.2005,
+      "train_samples_per_second": 3116.242,
+      "train_steps_per_second": 12.391
     }
   ],
   "logging_steps": 1,
@@ -197,7 +180,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.012438185472512e+16,
+  "total_flos": 8999450537533440.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null