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_24_cola
 
-This model is a fine-tuned version of [gokuls/add_bert_12_layer_model_complete_training_new](https://huggingface.co/gokuls/add_bert_12_layer_model_complete_training_new) on the glue dataset.
+This model is a fine-tuned version of [gokuls/add_bert_12_layer_model_complete_training_new](https://huggingface.co/gokuls/add_bert_12_layer_model_complete_training_new) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6294
+- Loss: 0.6181
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180886626243591,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.9771,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 527.553,
+    "eval_steps_per_second": 4.552,
+    "train_loss": 0.6149293656464149,
+    "train_runtime": 800.9683,
+    "train_samples": 8551,
+    "train_samples_per_second": 533.791,
+    "train_steps_per_second": 4.182
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6180886626243591,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.9771,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 527.553,
+    "eval_steps_per_second": 4.552
+}

logs/events.out.tfevents.1686863428.serv-3317.1852327.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b89920e2e898f727d7a3a126ba3b8390f884bf27db4328e7fc47170a67083b
+size 427

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.0,
+    "train_loss": 0.6149293656464149,
+    "train_runtime": 800.9683,
+    "train_samples": 8551,
+    "train_samples_per_second": 533.791,
+    "train_steps_per_second": 4.182
+}

trainer_state.json

@@ -0,0 +1,233 @@
+{
+  "best_metric": 0.6180886626243591,
+  "best_model_checkpoint": "add_BERT_24_cola/checkpoint-536",
+  "epoch": 13.0,
+  "global_step": 871,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6232,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6213637590408325,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9802,
+      "eval_samples_per_second": 526.709,
+      "eval_steps_per_second": 4.545,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6217,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6500605344772339,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9963,
+      "eval_samples_per_second": 522.465,
+      "eval_steps_per_second": 4.508,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6147,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.620943009853363,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9897,
+      "eval_samples_per_second": 524.211,
+      "eval_steps_per_second": 4.523,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6131,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6193134784698486,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.99,
+      "eval_samples_per_second": 524.111,
+      "eval_steps_per_second": 4.523,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6115,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6181042790412903,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9928,
+      "eval_samples_per_second": 523.387,
+      "eval_steps_per_second": 4.516,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.6109,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.620335578918457,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9904,
+      "eval_samples_per_second": 524.011,
+      "eval_steps_per_second": 4.522,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.6113,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6236723065376282,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9953,
+      "eval_samples_per_second": 522.727,
+      "eval_steps_per_second": 4.511,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.6124,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6180886626243591,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9861,
+      "eval_samples_per_second": 525.137,
+      "eval_steps_per_second": 4.531,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.28e-05,
+      "loss": 0.6094,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6277194619178772,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9925,
+      "eval_samples_per_second": 523.465,
+      "eval_steps_per_second": 4.517,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6362,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6505111455917358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9863,
+      "eval_samples_per_second": 525.09,
+      "eval_steps_per_second": 4.531,
+      "step": 670
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.6097,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6185837388038635,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9937,
+      "eval_samples_per_second": 523.155,
+      "eval_steps_per_second": 4.514,
+      "step": 737
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.0400000000000004e-05,
+      "loss": 0.6113,
+      "step": 804
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.619999885559082,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9983,
+      "eval_samples_per_second": 521.949,
+      "eval_steps_per_second": 4.504,
+      "step": 804
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.96e-05,
+      "loss": 0.6086,
+      "step": 871
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6294378638267517,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9933,
+      "eval_samples_per_second": 523.252,
+      "eval_steps_per_second": 4.515,
+      "step": 871
+    },
+    {
+      "epoch": 13.0,
+      "step": 871,
+      "total_flos": 1.5876741075566592e+16,
+      "train_loss": 0.6149293656464149,
+      "train_runtime": 800.9683,
+      "train_samples_per_second": 533.791,
+      "train_steps_per_second": 4.182
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 1.5876741075566592e+16,
+  "trial_name": null,
+  "trial_params": null
+}