End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_lda_5_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: 0.014335296446004425
+    - name: Accuracy
+      type: accuracy
+      value: 0.6788111329078674
 ---
 
 <!-- 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_5_v1_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9654
-- Matthews Correlation: 0.1201
-- Accuracy: 0.6424
+- Loss: 0.6141
+- Matthews Correlation: 0.0143
+- Accuracy: 0.6788
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6183110475540161,
-    "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6645,
+    "epoch": 8.0,
+    "eval_accuracy": 0.6788111329078674,
+    "eval_loss": 0.6140850782394409,
+    "eval_matthews_correlation": 0.014335296446004425,
+    "eval_runtime": 0.6747,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1569.501,
-    "eval_steps_per_second": 7.524,
-    "total_flos": 1.012438185472512e+16,
-    "train_loss": 0.6631240346073325,
-    "train_runtime": 151.6801,
+    "eval_samples_per_second": 1545.816,
+    "eval_steps_per_second": 7.41,
+    "total_flos": 8999450537533440.0,
+    "train_loss": 0.47134509156731996,
+    "train_runtime": 138.7221,
     "train_samples": 8551,
-    "train_samples_per_second": 2818.761,
-    "train_steps_per_second": 11.208
+    "train_samples_per_second": 3082.061,
+    "train_steps_per_second": 12.255
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6183110475540161,
-    "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.6645,
+    "epoch": 8.0,
+    "eval_accuracy": 0.6788111329078674,
+    "eval_loss": 0.6140850782394409,
+    "eval_matthews_correlation": 0.014335296446004425,
+    "eval_runtime": 0.6747,
     "eval_samples": 1043,
-    "eval_samples_per_second": 1569.501,
-    "eval_steps_per_second": 7.524
+    "eval_samples_per_second": 1545.816,
+    "eval_steps_per_second": 7.41
 }

logs/events.out.tfevents.1733309485.ki-g0008.1206925.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6de4dfc7f801c3383ca1c209d13a2cfa3406b7db32b6e242c8203776eb2750
+size 475

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "total_flos": 1.012438185472512e+16,
-    "train_loss": 0.6631240346073325,
-    "train_runtime": 151.6801,
+    "epoch": 8.0,
+    "total_flos": 8999450537533440.0,
+    "train_loss": 0.47134509156731996,
+    "train_runtime": 138.7221,
     "train_samples": 8551,
-    "train_samples_per_second": 2818.761,
-    "train_steps_per_second": 11.208
+    "train_samples_per_second": 3082.061,
+    "train_steps_per_second": 12.255
 }

trainer_state.json

@@ -1,174 +1,157 @@
 {
-  "best_metric": 0.6183110475540161,
-  "best_model_checkpoint": "bert_base_lda_5_v1_cola/checkpoint-136",
-  "epoch": 9.0,
+  "best_metric": 0.6140850782394409,
+  "best_model_checkpoint": "bert_base_lda_5_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": 2.0946457386016846,
-      "learning_rate": 0.00098,
-      "loss": 1.0659,
+      "grad_norm": 0.8962923884391785,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6165,
       "step": 34
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.620131254196167,
+      "eval_loss": 0.6255748867988586,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.673,
-      "eval_samples_per_second": 1549.697,
-      "eval_steps_per_second": 7.429,
+      "eval_runtime": 0.6921,
+      "eval_samples_per_second": 1507.045,
+      "eval_steps_per_second": 7.225,
       "step": 34
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.8950899243354797,
-      "learning_rate": 0.00096,
-      "loss": 0.6315,
+      "grad_norm": 1.1500860452651978,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6085,
       "step": 68
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.619966447353363,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6704,
-      "eval_samples_per_second": 1555.756,
-      "eval_steps_per_second": 7.458,
+      "eval_accuracy": 0.6922339200973511,
+      "eval_loss": 0.6206546425819397,
+      "eval_matthews_correlation": 0.0437601222642778,
+      "eval_runtime": 0.6888,
+      "eval_samples_per_second": 1514.269,
+      "eval_steps_per_second": 7.259,
       "step": 68
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.0940829515457153,
-      "learning_rate": 0.00094,
-      "loss": 0.61,
+      "grad_norm": 1.3318846225738525,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5767,
       "step": 102
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6210225820541382,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6796,
-      "eval_samples_per_second": 1534.67,
-      "eval_steps_per_second": 7.357,
+      "eval_accuracy": 0.6788111329078674,
+      "eval_loss": 0.6140850782394409,
+      "eval_matthews_correlation": 0.014335296446004425,
+      "eval_runtime": 0.6907,
+      "eval_samples_per_second": 1510.046,
+      "eval_steps_per_second": 7.239,
       "step": 102
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.41540974378585815,
-      "learning_rate": 0.00092,
-      "loss": 0.6103,
+      "grad_norm": 3.0688295364379883,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5249,
       "step": 136
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6183110475540161,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6842,
-      "eval_samples_per_second": 1524.426,
-      "eval_steps_per_second": 7.308,
+      "eval_accuracy": 0.6625120043754578,
+      "eval_loss": 0.6585533022880554,
+      "eval_matthews_correlation": 0.05998312692220892,
+      "eval_runtime": 0.7395,
+      "eval_samples_per_second": 1410.335,
+      "eval_steps_per_second": 6.761,
       "step": 136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.882623016834259,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6103,
+      "grad_norm": 2.6873955726623535,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4572,
       "step": 170
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.622185468673706,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6821,
-      "eval_samples_per_second": 1529.048,
-      "eval_steps_per_second": 7.33,
+      "eval_accuracy": 0.6519654989242554,
+      "eval_loss": 0.7236359715461731,
+      "eval_matthews_correlation": 0.13356139258109112,
+      "eval_runtime": 0.6908,
+      "eval_samples_per_second": 1509.857,
+      "eval_steps_per_second": 7.238,
       "step": 170
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.45722779631614685,
-      "learning_rate": 0.00088,
-      "loss": 0.6105,
+      "grad_norm": 3.0232486724853516,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3844,
       "step": 204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6192323565483093,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6777,
-      "eval_samples_per_second": 1539.028,
-      "eval_steps_per_second": 7.378,
+      "eval_accuracy": 0.640460193157196,
+      "eval_loss": 0.8147491812705994,
+      "eval_matthews_correlation": 0.08177474609901102,
+      "eval_runtime": 0.6894,
+      "eval_samples_per_second": 1513.007,
+      "eval_steps_per_second": 7.253,
       "step": 204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 1.1227401494979858,
-      "learning_rate": 0.00086,
-      "loss": 0.6098,
+      "grad_norm": 2.7721943855285645,
+      "learning_rate": 4.3e-05,
+      "loss": 0.327,
       "step": 238
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6202510595321655,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6848,
-      "eval_samples_per_second": 1523.07,
-      "eval_steps_per_second": 7.301,
+      "eval_accuracy": 0.6126558184623718,
+      "eval_loss": 0.9067552089691162,
+      "eval_matthews_correlation": 0.08937795209450178,
+      "eval_runtime": 0.684,
+      "eval_samples_per_second": 1524.939,
+      "eval_steps_per_second": 7.31,
       "step": 238
     },
     {
       "epoch": 8.0,
-      "grad_norm": 0.3862515985965729,
-      "learning_rate": 0.00084,
-      "loss": 0.6104,
+      "grad_norm": 4.930617332458496,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2756,
       "step": 272
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6233483552932739,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6616,
-      "eval_samples_per_second": 1576.417,
-      "eval_steps_per_second": 7.557,
+      "eval_accuracy": 0.6423777341842651,
+      "eval_loss": 0.9654455184936523,
+      "eval_matthews_correlation": 0.12007934236570234,
+      "eval_runtime": 0.6807,
+      "eval_samples_per_second": 1532.247,
+      "eval_steps_per_second": 7.345,
       "step": 272
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.5181242227554321,
-      "learning_rate": 0.00082,
-      "loss": 0.6095,
-      "step": 306
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6256685256958008,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.6813,
-      "eval_samples_per_second": 1530.94,
-      "eval_steps_per_second": 7.339,
-      "step": 306
-    },
-    {
-      "epoch": 9.0,
-      "step": 306,
-      "total_flos": 1.012438185472512e+16,
-      "train_loss": 0.6631240346073325,
-      "train_runtime": 151.6801,
-      "train_samples_per_second": 2818.761,
-      "train_steps_per_second": 11.208
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 8999450537533440.0,
+      "train_loss": 0.47134509156731996,
+      "train_runtime": 138.7221,
+      "train_samples_per_second": 3082.061,
+      "train_steps_per_second": 12.255
     }
   ],
   "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