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: 0.6318327974276527
+      value: 0.7558496166213208
     - name: F1
       type: f1
-      value: 0.0
+      value: 0.6390991188621988
 ---
 
 <!-- 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_256
 
-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: nan
-- Accuracy: 0.6318
-- F1: 0.0
-- Combined Score: 0.3159
+- Loss: 0.5069
+- Accuracy: 0.7558
+- F1: 0.6391
+- Combined Score: 0.6975
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7558496166213208,
+    "eval_combined_score": 0.6974743677417599,
+    "eval_f1": 0.6390991188621988,
+    "eval_loss": 0.5068832039833069,
+    "eval_runtime": 71.8456,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 562.735,
+    "eval_steps_per_second": 4.398,
+    "train_loss": 0.4166359809180443,
+    "train_runtime": 17752.6964,
+    "train_samples": 363846,
+    "train_samples_per_second": 1024.763,
+    "train_steps_per_second": 8.007
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7558496166213208,
+    "eval_combined_score": 0.6974743677417599,
+    "eval_f1": 0.6390991188621988,
+    "eval_loss": 0.5068832039833069,
+    "eval_runtime": 71.8456,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 562.735,
+    "eval_steps_per_second": 4.398
+}

logs/events.out.tfevents.1674759909.gera.2823283.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd66164fa5f36abb8083bc59150050ce631bc230a98ff875c3d27948aa68ecb
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.4166359809180443,
+    "train_runtime": 17752.6964,
+    "train_samples": 363846,
+    "train_samples_per_second": 1024.763,
+    "train_steps_per_second": 8.007
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.5068832039833069,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qqp_256/checkpoint-11372",
+  "epoch": 9.0,
+  "global_step": 25587,
+  "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": 0.6497330069541931,
+      "eval_runtime": 72.4365,
+      "eval_samples_per_second": 558.144,
+      "eval_steps_per_second": 4.362,
+      "step": 2843
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6473,
+      "step": 5686
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6320554044026713,
+      "eval_combined_score": 0.3166319723772454,
+      "eval_f1": 0.0012085403518195246,
+      "eval_loss": 0.6478642821311951,
+      "eval_runtime": 72.1974,
+      "eval_samples_per_second": 559.992,
+      "eval_steps_per_second": 4.377,
+      "step": 5686
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5376,
+      "step": 8529
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7485777887707148,
+      "eval_combined_score": 0.6682443814733697,
+      "eval_f1": 0.5879109741760247,
+      "eval_loss": 0.5166534185409546,
+      "eval_runtime": 72.1129,
+      "eval_samples_per_second": 560.649,
+      "eval_steps_per_second": 4.382,
+      "step": 8529
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4943,
+      "step": 11372
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7558496166213208,
+      "eval_combined_score": 0.6974743677417599,
+      "eval_f1": 0.6390991188621988,
+      "eval_loss": 0.5068832039833069,
+      "eval_runtime": 72.1575,
+      "eval_samples_per_second": 560.302,
+      "eval_steps_per_second": 4.379,
+      "step": 11372
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4816,
+      "step": 14215
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7547118476378927,
+      "eval_combined_score": 0.7060719416433963,
+      "eval_f1": 0.6574320356488997,
+      "eval_loss": 0.5071504712104797,
+      "eval_runtime": 72.2689,
+      "eval_samples_per_second": 559.439,
+      "eval_steps_per_second": 4.373,
+      "step": 14215
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4738,
+      "step": 17058
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7587682414048974,
+      "eval_combined_score": 0.7056762875531594,
+      "eval_f1": 0.6525843337014213,
+      "eval_loss": NaN,
+      "eval_runtime": 72.2755,
+      "eval_samples_per_second": 559.387,
+      "eval_steps_per_second": 4.372,
+      "step": 17058
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4646,
+      "step": 19901
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 72.2634,
+      "eval_samples_per_second": 559.481,
+      "eval_steps_per_second": 4.373,
+      "step": 19901
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0,
+      "step": 22744
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 72.256,
+      "eval_samples_per_second": 559.539,
+      "eval_steps_per_second": 4.373,
+      "step": 22744
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.0,
+      "step": 25587
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 71.9984,
+      "eval_samples_per_second": 561.54,
+      "eval_steps_per_second": 4.389,
+      "step": 25587
+    },
+    {
+      "epoch": 9.0,
+      "step": 25587,
+      "total_flos": 8.4403873741013e+16,
+      "train_loss": 0.4166359809180443,
+      "train_runtime": 17752.6964,
+      "train_samples_per_second": 1024.763,
+      "train_steps_per_second": 8.007
+    }
+  ],
+  "max_steps": 142150,
+  "num_train_epochs": 50,
+  "total_flos": 8.4403873741013e+16,
+  "trial_name": null,
+  "trial_params": null
+}