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 MRPC
       type: glue
       config: mrpc
       split: validation
@@ -22,10 +24,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6813725490196079
+      value: 0.6838235294117647
     - name: F1
       type: f1
-      value: 0.8036253776435045
+      value: 0.8122270742358079
 ---
 
 <!-- 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_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6290
-- Accuracy: 0.6814
-- F1: 0.8036
-- Combined Score: 0.7425
+- Loss: 0.6197
+- Accuracy: 0.6838
+- F1: 0.8122
+- Combined Score: 0.7480
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6196601390838623,
+    "eval_runtime": 0.9274,
+    "eval_samples": 408,
+    "eval_samples_per_second": 439.94,
+    "eval_steps_per_second": 4.313,
+    "train_loss": 0.6142688882761989,
+    "train_runtime": 370.7483,
+    "train_samples": 3668,
+    "train_samples_per_second": 494.675,
+    "train_steps_per_second": 3.911
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6196601390838623,
+    "eval_runtime": 0.9274,
+    "eval_samples": 408,
+    "eval_samples_per_second": 439.94,
+    "eval_steps_per_second": 4.313
+}

logs/events.out.tfevents.1674737152.garda.473409.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f815f21e8b3461140d19539831021acfd8ccf7fadba69378b2cb7014b90bcfc1
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6142688882761989,
+    "train_runtime": 370.7483,
+    "train_samples": 3668,
+    "train_samples_per_second": 494.675,
+    "train_steps_per_second": 3.911
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.6196601390838623,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_mrpc/checkpoint-145",
+  "epoch": 10.0,
+  "global_step": 290,
+  "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": 0.6387,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6245394349098206,
+      "eval_runtime": 0.9008,
+      "eval_samples_per_second": 452.914,
+      "eval_steps_per_second": 4.44,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6307,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6234116554260254,
+      "eval_runtime": 0.8983,
+      "eval_samples_per_second": 454.198,
+      "eval_steps_per_second": 4.453,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6307,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.623303234577179,
+      "eval_runtime": 0.8949,
+      "eval_samples_per_second": 455.912,
+      "eval_steps_per_second": 4.47,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6295,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6230832934379578,
+      "eval_runtime": 0.9002,
+      "eval_samples_per_second": 453.238,
+      "eval_steps_per_second": 4.444,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6261,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6196601390838623,
+      "eval_runtime": 0.8998,
+      "eval_samples_per_second": 453.436,
+      "eval_steps_per_second": 4.445,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6147,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6344165205955505,
+      "eval_runtime": 0.8969,
+      "eval_samples_per_second": 454.893,
+      "eval_steps_per_second": 4.46,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6209,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.639832079410553,
+      "eval_runtime": 0.8982,
+      "eval_samples_per_second": 454.262,
+      "eval_steps_per_second": 4.454,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6007,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6323529411764706,
+      "eval_combined_score": 0.6920042851577717,
+      "eval_f1": 0.7516556291390729,
+      "eval_loss": 0.6337530016899109,
+      "eval_runtime": 0.8948,
+      "eval_samples_per_second": 455.949,
+      "eval_steps_per_second": 4.47,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5795,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.625,
+      "eval_combined_score": 0.6839285714285714,
+      "eval_f1": 0.7428571428571428,
+      "eval_loss": 0.6376703381538391,
+      "eval_runtime": 0.8989,
+      "eval_samples_per_second": 453.912,
+      "eval_steps_per_second": 4.45,
+      "step": 261
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.5712,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.7424989633315562,
+      "eval_f1": 0.8036253776435045,
+      "eval_loss": 0.6289607286453247,
+      "eval_runtime": 0.9002,
+      "eval_samples_per_second": 453.227,
+      "eval_steps_per_second": 4.443,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "step": 290,
+      "total_flos": 1085007808430080.0,
+      "train_loss": 0.6142688882761989,
+      "train_runtime": 370.7483,
+      "train_samples_per_second": 494.675,
+      "train_steps_per_second": 3.911
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 1085007808430080.0,
+  "trial_name": null,
+  "trial_params": null
+}