End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QQP
       type: glue
       config: qqp
       split: validation
@@ -22,10 +24,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7621815483551818
+      value: 0.7599802127133317
     - name: F1
       type: f1
-      value: 0.6619317182940121
+      value: 0.6401928068223952
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_qqp
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5302
-- Accuracy: 0.7622
-- F1: 0.6619
-- Combined Score: 0.7121
+- Loss: 0.5008
+- Accuracy: 0.7600
+- F1: 0.6402
+- Combined Score: 0.7001
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7599802127133317,
+    "eval_combined_score": 0.7000865097678635,
+    "eval_f1": 0.6401928068223952,
+    "eval_loss": 0.5008143186569214,
+    "eval_runtime": 86.209,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 468.976,
+    "eval_steps_per_second": 3.666,
+    "train_loss": 0.5180756985645023,
+    "train_runtime": 29413.6297,
+    "train_samples": 363846,
+    "train_samples_per_second": 618.499,
+    "train_steps_per_second": 4.833
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7599802127133317,
+    "eval_combined_score": 0.7000865097678635,
+    "eval_f1": 0.6401928068223952,
+    "eval_loss": 0.5008143186569214,
+    "eval_runtime": 86.209,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 468.976,
+    "eval_steps_per_second": 3.666
+}

logs/events.out.tfevents.1674772718.garda.473409.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba777b67d13951b87951c2eb0d2d640b0768326c4ff068c78efe5fc9a3e552a
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 0.5180756985645023,
+    "train_runtime": 29413.6297,
+    "train_samples": 363846,
+    "train_samples_per_second": 618.499,
+    "train_steps_per_second": 4.833
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 0.5008143186569214,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qqp/checkpoint-19901",
+  "epoch": 12.0,
+  "global_step": 34116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6505,
+      "step": 2843
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6320554044026713,
+      "eval_combined_score": 0.3166319723772454,
+      "eval_f1": 0.0012085403518195246,
+      "eval_loss": 0.6498478651046753,
+      "eval_runtime": 84.4187,
+      "eval_samples_per_second": 478.923,
+      "eval_steps_per_second": 3.743,
+      "step": 2843
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6474,
+      "step": 5686
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6320554044026713,
+      "eval_combined_score": 0.3166319723772454,
+      "eval_f1": 0.0012085403518195246,
+      "eval_loss": 0.6484191417694092,
+      "eval_runtime": 84.4998,
+      "eval_samples_per_second": 478.463,
+      "eval_steps_per_second": 3.74,
+      "step": 5686
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.646,
+      "step": 8529
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6322038090526837,
+      "eval_combined_score": 0.3173094719488563,
+      "eval_f1": 0.0024151348450288474,
+      "eval_loss": 0.6478633880615234,
+      "eval_runtime": 84.5145,
+      "eval_samples_per_second": 478.38,
+      "eval_steps_per_second": 3.739,
+      "step": 8529
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5481,
+      "step": 11372
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7486272569873856,
+      "eval_combined_score": 0.6866867038546203,
+      "eval_f1": 0.624746150721855,
+      "eval_loss": 0.5139716267585754,
+      "eval_runtime": 85.5613,
+      "eval_samples_per_second": 472.527,
+      "eval_steps_per_second": 3.693,
+      "step": 11372
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4934,
+      "step": 14215
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7529062577294089,
+      "eval_combined_score": 0.7038665764495293,
+      "eval_f1": 0.6548268951696496,
+      "eval_loss": 0.508634090423584,
+      "eval_runtime": 85.77,
+      "eval_samples_per_second": 471.377,
+      "eval_steps_per_second": 3.684,
+      "step": 14215
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4794,
+      "step": 17058
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7575315359881276,
+      "eval_combined_score": 0.7051322705269201,
+      "eval_f1": 0.6527330050657125,
+      "eval_loss": 0.5043991208076477,
+      "eval_runtime": 85.6759,
+      "eval_samples_per_second": 471.895,
+      "eval_steps_per_second": 3.688,
+      "step": 17058
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4708,
+      "step": 19901
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7599802127133317,
+      "eval_combined_score": 0.7000865097678635,
+      "eval_f1": 0.6401928068223952,
+      "eval_loss": 0.5008143186569214,
+      "eval_runtime": 85.4807,
+      "eval_samples_per_second": 472.972,
+      "eval_steps_per_second": 3.697,
+      "step": 19901
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4652,
+      "step": 22744
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7618600049468217,
+      "eval_combined_score": 0.7001156995887954,
+      "eval_f1": 0.6383713942307692,
+      "eval_loss": 0.5009844303131104,
+      "eval_runtime": 85.8727,
+      "eval_samples_per_second": 470.813,
+      "eval_steps_per_second": 3.68,
+      "step": 22744
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4604,
+      "step": 25587
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7614147909967846,
+      "eval_combined_score": 0.7051723831239565,
+      "eval_f1": 0.6489299752511283,
+      "eval_loss": 0.5014066100120544,
+      "eval_runtime": 86.3999,
+      "eval_samples_per_second": 467.94,
+      "eval_steps_per_second": 3.657,
+      "step": 25587
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.4562,
+      "step": 28430
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7599802127133317,
+      "eval_combined_score": 0.7108365712848488,
+      "eval_f1": 0.661692929856366,
+      "eval_loss": 0.5057373642921448,
+      "eval_runtime": 86.4384,
+      "eval_samples_per_second": 467.732,
+      "eval_steps_per_second": 3.656,
+      "step": 28430
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.452,
+      "step": 31273
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7619836754884987,
+      "eval_combined_score": 0.6991856786662217,
+      "eval_f1": 0.6363876818439448,
+      "eval_loss": 0.5101634860038757,
+      "eval_runtime": 86.4692,
+      "eval_samples_per_second": 467.565,
+      "eval_steps_per_second": 3.654,
+      "step": 31273
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 3.8e-05,
+      "loss": 0.4476,
+      "step": 34116
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7621815483551818,
+      "eval_combined_score": 0.712056633324597,
+      "eval_f1": 0.6619317182940121,
+      "eval_loss": 0.5301799774169922,
+      "eval_runtime": 86.4861,
+      "eval_samples_per_second": 467.474,
+      "eval_steps_per_second": 3.654,
+      "step": 34116
+    },
+    {
+      "epoch": 12.0,
+      "step": 34116,
+      "total_flos": 1.2915236812514918e+17,
+      "train_loss": 0.5180756985645023,
+      "train_runtime": 29413.6297,
+      "train_samples_per_second": 618.499,
+      "train_steps_per_second": 4.833
+    }
+  ],
+  "max_steps": 142150,
+  "num_train_epochs": 50,
+  "total_flos": 1.2915236812514918e+17,
+  "trial_name": null,
+  "trial_params": null
+}