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: 0.7568142468464012
     - name: F1
       type: f1
-      value: 0.0
+      value: 0.6361483235881874
 ---
 
 <!-- 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_128
 
-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: 0.5071
+- Accuracy: 0.7568
+- F1: 0.6361
+- Combined Score: 0.6965
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7568142468464012,
+    "eval_combined_score": 0.6964812852172944,
+    "eval_f1": 0.6361483235881874,
+    "eval_loss": 0.5071280002593994,
+    "eval_runtime": 70.0657,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 577.03,
+    "eval_steps_per_second": 4.51,
+    "train_loss": 0.30765416115544514,
+    "train_runtime": 17142.0128,
+    "train_samples": 363846,
+    "train_samples_per_second": 1061.27,
+    "train_steps_per_second": 8.292
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.7568142468464012,
+    "eval_combined_score": 0.6964812852172944,
+    "eval_f1": 0.6361483235881874,
+    "eval_loss": 0.5071280002593994,
+    "eval_runtime": 70.0657,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 577.03,
+    "eval_steps_per_second": 4.51
+}

logs/events.out.tfevents.1674758860.gera.2822633.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c8ff4118d8270b31fcdc693a942c9e561fe649df3be67fcbc64541a534c1bd
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.30765416115544514,
+    "train_runtime": 17142.0128,
+    "train_samples": 363846,
+    "train_samples_per_second": 1061.27,
+    "train_steps_per_second": 8.292
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.5071280002593994,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qqp_128/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": 0.6507,
+      "step": 2843
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6496740579605103,
+      "eval_runtime": 70.2237,
+      "eval_samples_per_second": 575.732,
+      "eval_steps_per_second": 4.5,
+      "step": 2843
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6311,
+      "step": 5686
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7259460796438288,
+      "eval_combined_score": 0.6440872239388642,
+      "eval_f1": 0.5622283682338997,
+      "eval_loss": 0.5445142984390259,
+      "eval_runtime": 70.5366,
+      "eval_samples_per_second": 573.178,
+      "eval_steps_per_second": 4.48,
+      "step": 5686
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5153,
+      "step": 8529
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7493198120207767,
+      "eval_combined_score": 0.6692568011504313,
+      "eval_f1": 0.5891937902800859,
+      "eval_loss": 0.5152718424797058,
+      "eval_runtime": 70.4498,
+      "eval_samples_per_second": 573.884,
+      "eval_steps_per_second": 4.485,
+      "step": 8529
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4912,
+      "step": 11372
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7568142468464012,
+      "eval_combined_score": 0.6964812852172944,
+      "eval_f1": 0.6361483235881874,
+      "eval_loss": 0.5071280002593994,
+      "eval_runtime": 70.7466,
+      "eval_samples_per_second": 571.476,
+      "eval_steps_per_second": 4.467,
+      "step": 11372
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4805,
+      "step": 14215
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 70.2577,
+      "eval_samples_per_second": 575.453,
+      "eval_steps_per_second": 4.498,
+      "step": 14215
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0,
+      "step": 17058
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 70.2761,
+      "eval_samples_per_second": 575.302,
+      "eval_steps_per_second": 4.497,
+      "step": 17058
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0,
+      "step": 19901
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 69.9273,
+      "eval_samples_per_second": 578.172,
+      "eval_steps_per_second": 4.519,
+      "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": 70.3246,
+      "eval_samples_per_second": 574.906,
+      "eval_steps_per_second": 4.493,
+      "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": 70.2338,
+      "eval_samples_per_second": 575.649,
+      "eval_steps_per_second": 4.499,
+      "step": 25587
+    },
+    {
+      "epoch": 9.0,
+      "step": 25587,
+      "total_flos": 7.817367256458854e+16,
+      "train_loss": 0.30765416115544514,
+      "train_runtime": 17142.0128,
+      "train_samples_per_second": 1061.27,
+      "train_steps_per_second": 8.292
+    }
+  ],
+  "max_steps": 142150,
+  "num_train_epochs": 50,
+  "total_flos": 7.817367256458854e+16,
+  "trial_name": null,
+  "trial_params": null
+}