End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_data_aug_cola_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.09390288672705373
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_data_aug_cola_256
 
-This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0809
-- Matthews Correlation: 0.1026
+- Loss: 0.6609
+- Matthews Correlation: 0.0939
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6609398126602173,
+    "eval_matthews_correlation": 0.09390288672705373,
+    "eval_runtime": 1.5484,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 673.591,
+    "eval_steps_per_second": 5.812,
+    "train_loss": 0.4082020370455971,
+    "train_runtime": 6186.1806,
+    "train_samples": 213609,
+    "train_samples_per_second": 1726.501,
+    "train_steps_per_second": 13.49
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6609398126602173,
+    "eval_matthews_correlation": 0.09390288672705373,
+    "eval_runtime": 1.5484,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 673.591,
+    "eval_steps_per_second": 5.812
+}

logs/events.out.tfevents.1675296755.serv-3332.749437.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6438ddd55b922674314520b7bb9651443487bcc5c2931f508e3857dbcab6eb08
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.4082020370455971,
+    "train_runtime": 6186.1806,
+    "train_samples": 213609,
+    "train_samples_per_second": 1726.501,
+    "train_steps_per_second": 13.49
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6609398126602173,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_cola_256/checkpoint-1669",
+  "epoch": 6.0,
+  "global_step": 10014,
+  "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": 0.5394,
+      "step": 1669
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6609398126602173,
+      "eval_matthews_correlation": 0.09390288672705373,
+      "eval_runtime": 1.5393,
+      "eval_samples_per_second": 677.575,
+      "eval_steps_per_second": 5.847,
+      "step": 1669
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4545,
+      "step": 3338
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7807448506355286,
+      "eval_matthews_correlation": 0.04738043679310804,
+      "eval_runtime": 1.5509,
+      "eval_samples_per_second": 672.507,
+      "eval_steps_per_second": 5.803,
+      "step": 3338
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4253,
+      "step": 5007
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8028568625450134,
+      "eval_matthews_correlation": 0.08459402343109,
+      "eval_runtime": 1.5345,
+      "eval_samples_per_second": 679.705,
+      "eval_steps_per_second": 5.865,
+      "step": 5007
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.388,
+      "step": 6676
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8929793238639832,
+      "eval_matthews_correlation": 0.07382848474505407,
+      "eval_runtime": 1.5345,
+      "eval_samples_per_second": 679.693,
+      "eval_steps_per_second": 5.865,
+      "step": 6676
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3433,
+      "step": 8345
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.9283742308616638,
+      "eval_matthews_correlation": 0.0834401861698737,
+      "eval_runtime": 1.5422,
+      "eval_samples_per_second": 676.307,
+      "eval_steps_per_second": 5.836,
+      "step": 8345
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2986,
+      "step": 10014
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.0809475183486938,
+      "eval_matthews_correlation": 0.10257980116603183,
+      "eval_runtime": 1.5331,
+      "eval_samples_per_second": 680.304,
+      "eval_steps_per_second": 5.87,
+      "step": 10014
+    },
+    {
+      "epoch": 6.0,
+      "step": 10014,
+      "total_flos": 3.3760240390373376e+16,
+      "train_loss": 0.4082020370455971,
+      "train_runtime": 6186.1806,
+      "train_samples_per_second": 1726.501,
+      "train_steps_per_second": 13.49
+    }
+  ],
+  "max_steps": 83450,
+  "num_train_epochs": 50,
+  "total_flos": 3.3760240390373376e+16,
+  "trial_name": null,
+  "trial_params": null
+}