End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE COLA
       type: glue
       config: cola
       split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_cola
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6310
+- Loss: 0.6181
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 13.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6180832982063293,
+    "eval_loss": 0.6180649399757385,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.6203,
+    "eval_runtime": 1.9599,
     "eval_samples": 1043,
-    "eval_samples_per_second": 643.698,
-    "eval_steps_per_second": 5.554,
-    "train_loss": 0.6883503271162031,
-    "train_runtime": 605.2526,
+    "eval_samples_per_second": 532.163,
+    "eval_steps_per_second": 4.592,
+    "train_loss": 0.6162634493699715,
+    "train_runtime": 600.8403,
     "train_samples": 8551,
-    "train_samples_per_second": 706.399,
-    "train_steps_per_second": 5.535
+    "train_samples_per_second": 711.587,
+    "train_steps_per_second": 5.576
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 13.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6180832982063293,
+    "eval_loss": 0.6180649399757385,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 1.6203,
+    "eval_runtime": 1.9599,
     "eval_samples": 1043,
-    "eval_samples_per_second": 643.698,
-    "eval_steps_per_second": 5.554
+    "eval_samples_per_second": 532.163,
+    "eval_steps_per_second": 4.592
 }

logs/events.out.tfevents.1686746780.serv-9219.1715196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11c2056a66d010a95f99be60e4c4466642ff33464d3b86e4550849a888d4e45
+size 427

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 13.0,
-    "train_loss": 0.6883503271162031,
-    "train_runtime": 605.2526,
+    "epoch": 10.0,
+    "train_loss": 0.6162634493699715,
+    "train_runtime": 600.8403,
     "train_samples": 8551,
-    "train_samples_per_second": 706.399,
-    "train_steps_per_second": 5.535
+    "train_samples_per_second": 711.587,
+    "train_steps_per_second": 5.576
 }

trainer_state.json

@@ -1,233 +1,185 @@
 {
-  "best_metric": 0.6180832982063293,
-  "best_model_checkpoint": "add_BERT_no_pretrain_cola/checkpoint-536",
-  "epoch": 13.0,
-  "global_step": 871,
+  "best_metric": 0.6180649399757385,
+  "best_model_checkpoint": "add_BERT_no_pretrain_cola/checkpoint-335",
+  "epoch": 10.0,
+  "global_step": 670,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.0004902985074626866,
-      "loss": 0.9141,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6339,
       "step": 67
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6220115423202515,
+      "eval_loss": 0.6182041168212891,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6311,
-      "eval_samples_per_second": 639.436,
-      "eval_steps_per_second": 5.518,
+      "eval_runtime": 1.9602,
+      "eval_samples_per_second": 532.087,
+      "eval_steps_per_second": 4.591,
       "step": 67
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.00048029850746268655,
-      "loss": 0.6242,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6177,
       "step": 134
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6457749009132385,
+      "eval_loss": 0.6420519351959229,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6344,
-      "eval_samples_per_second": 638.155,
-      "eval_steps_per_second": 5.507,
+      "eval_runtime": 1.9688,
+      "eval_samples_per_second": 529.756,
+      "eval_steps_per_second": 4.571,
       "step": 134
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.0004702985074626866,
-      "loss": 0.62,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6204,
       "step": 201
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6181411147117615,
+      "eval_loss": 0.6295004487037659,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6358,
-      "eval_samples_per_second": 637.592,
-      "eval_steps_per_second": 5.502,
+      "eval_runtime": 1.961,
+      "eval_samples_per_second": 531.871,
+      "eval_steps_per_second": 4.589,
       "step": 201
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.0004602985074626866,
-      "loss": 0.6121,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6182,
       "step": 268
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6184491515159607,
+      "eval_loss": 0.6267786026000977,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6381,
-      "eval_samples_per_second": 636.709,
-      "eval_steps_per_second": 5.494,
+      "eval_runtime": 1.9603,
+      "eval_samples_per_second": 532.067,
+      "eval_steps_per_second": 4.591,
       "step": 268
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.0004502985074626866,
-      "loss": 0.6096,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6149,
       "step": 335
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6188187599182129,
+      "eval_loss": 0.6180649399757385,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6398,
-      "eval_samples_per_second": 636.038,
-      "eval_steps_per_second": 5.488,
+      "eval_runtime": 1.9731,
+      "eval_samples_per_second": 528.608,
+      "eval_steps_per_second": 4.561,
       "step": 335
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.00044029850746268656,
-      "loss": 0.6098,
+      "learning_rate": 3.52e-05,
+      "loss": 0.612,
       "step": 402
     },
     {
       "epoch": 6.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6184147596359253,
+      "eval_loss": 0.6188631057739258,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.634,
-      "eval_samples_per_second": 638.322,
-      "eval_steps_per_second": 5.508,
+      "eval_runtime": 1.9662,
+      "eval_samples_per_second": 530.452,
+      "eval_steps_per_second": 4.577,
       "step": 402
     },
     {
       "epoch": 7.0,
-      "learning_rate": 0.0004302985074626866,
-      "loss": 0.6106,
+      "learning_rate": 3.44e-05,
+      "loss": 0.6132,
       "step": 469
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.618549108505249,
+      "eval_loss": 0.6292060017585754,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6338,
-      "eval_samples_per_second": 638.4,
-      "eval_steps_per_second": 5.509,
+      "eval_runtime": 1.9618,
+      "eval_samples_per_second": 531.664,
+      "eval_steps_per_second": 4.588,
       "step": 469
     },
     {
       "epoch": 8.0,
-      "learning_rate": 0.00042029850746268656,
-      "loss": 0.6117,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.6125,
       "step": 536
     },
     {
       "epoch": 8.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6180832982063293,
+      "eval_loss": 0.6185278296470642,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6419,
-      "eval_samples_per_second": 635.247,
-      "eval_steps_per_second": 5.482,
+      "eval_runtime": 1.9633,
+      "eval_samples_per_second": 531.253,
+      "eval_steps_per_second": 4.584,
       "step": 536
     },
     {
       "epoch": 9.0,
-      "learning_rate": 0.0004102985074626866,
-      "loss": 0.6088,
+      "learning_rate": 3.28e-05,
+      "loss": 0.6108,
       "step": 603
     },
     {
       "epoch": 9.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6262354254722595,
+      "eval_loss": 0.6280407309532166,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6351,
-      "eval_samples_per_second": 637.891,
-      "eval_steps_per_second": 5.504,
+      "eval_runtime": 1.9674,
+      "eval_samples_per_second": 530.136,
+      "eval_steps_per_second": 4.575,
       "step": 603
     },
     {
       "epoch": 10.0,
-      "learning_rate": 0.0004002985074626866,
-      "loss": 0.6086,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6092,
       "step": 670
     },
     {
       "epoch": 10.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6217857003211975,
+      "eval_loss": 0.6309932470321655,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6389,
-      "eval_samples_per_second": 636.396,
-      "eval_steps_per_second": 5.491,
+      "eval_runtime": 1.9598,
+      "eval_samples_per_second": 532.187,
+      "eval_steps_per_second": 4.592,
       "step": 670
     },
     {
-      "epoch": 11.0,
-      "learning_rate": 0.0003902985074626866,
-      "loss": 0.6087,
-      "step": 737
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6183873414993286,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6414,
-      "eval_samples_per_second": 635.439,
-      "eval_steps_per_second": 5.483,
-      "step": 737
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 0.00038044776119402986,
-      "loss": 0.7274,
-      "step": 804
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6210523247718811,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6384,
-      "eval_samples_per_second": 636.613,
-      "eval_steps_per_second": 5.493,
-      "step": 804
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 0.00037059701492537313,
-      "loss": 1.183,
-      "step": 871
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6277084946632385,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6383,
-      "eval_samples_per_second": 636.652,
-      "eval_steps_per_second": 5.494,
-      "step": 871
-    },
-    {
-      "epoch": 13.0,
-      "step": 871,
-      "total_flos": 1.5876741075566592e+16,
-      "train_loss": 0.6883503271162031,
-      "train_runtime": 605.2526,
-      "train_samples_per_second": 706.399,
-      "train_steps_per_second": 5.535
+      "epoch": 10.0,
+      "step": 670,
+      "total_flos": 1.221287775043584e+16,
+      "train_loss": 0.6162634493699715,
+      "train_runtime": 600.8403,
+      "train_samples_per_second": 711.587,
+      "train_steps_per_second": 5.576
     }
   ],
   "max_steps": 3350,
   "num_train_epochs": 50,
-  "total_flos": 1.5876741075566592e+16,
+  "total_flos": 1.221287775043584e+16,
   "trial_name": null,
   "trial_params": null
 }