End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE COLA
       type: glue
       config: cola
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Matthews Correlation
       type: matthews_correlation
-      value: 0.0437601222642778
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_add_GLUE_Experiment_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6156
-- Matthews Correlation: 0.0438
+- Loss: 0.6127
+- Matthews Correlation: 0.0
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6127391457557678,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 2.2769,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 458.084,
+    "eval_steps_per_second": 3.953,
+    "train_loss": 0.5952504741611765,
+    "train_runtime": 701.2614,
+    "train_samples": 8551,
+    "train_samples_per_second": 609.687,
+    "train_steps_per_second": 4.777
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.6127391457557678,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 2.2769,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 458.084,
+    "eval_steps_per_second": 3.953
+}

logs/events.out.tfevents.1674736691.garda.473409.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9183c7609864b974b4877627e1f5c524c0d98516f7ac6f196ea3746922ae769b
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.5952504741611765,
+    "train_runtime": 701.2614,
+    "train_samples": 8551,
+    "train_samples_per_second": 609.687,
+    "train_steps_per_second": 4.777
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.6127391457557678,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_cola/checkpoint-335",
+  "epoch": 10.0,
+  "global_step": 670,
+  "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": 0.6126,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6183119416236877,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2731,
+      "eval_samples_per_second": 458.836,
+      "eval_steps_per_second": 3.959,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6078,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6178781390190125,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2536,
+      "eval_samples_per_second": 462.812,
+      "eval_steps_per_second": 3.994,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6072,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6183475255966187,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2545,
+      "eval_samples_per_second": 462.63,
+      "eval_steps_per_second": 3.992,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6062,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6163871884346008,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2538,
+      "eval_samples_per_second": 462.764,
+      "eval_steps_per_second": 3.993,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.601,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6127391457557678,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2614,
+      "eval_samples_per_second": 461.209,
+      "eval_steps_per_second": 3.98,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5928,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6148296594619751,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.256,
+      "eval_samples_per_second": 462.326,
+      "eval_steps_per_second": 3.989,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.588,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.622357964515686,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.2548,
+      "eval_samples_per_second": 462.562,
+      "eval_steps_per_second": 3.991,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.582,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6174187064170837,
+      "eval_matthews_correlation": 0.00286100001416597,
+      "eval_runtime": 2.2525,
+      "eval_samples_per_second": 463.04,
+      "eval_steps_per_second": 3.996,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5807,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.6301043033599854,
+      "eval_matthews_correlation": 0.00286100001416597,
+      "eval_runtime": 2.2518,
+      "eval_samples_per_second": 463.189,
+      "eval_steps_per_second": 3.997,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.5743,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.6156460642814636,
+      "eval_matthews_correlation": 0.0437601222642778,
+      "eval_runtime": 2.2578,
+      "eval_samples_per_second": 461.958,
+      "eval_steps_per_second": 3.986,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "step": 670,
+      "total_flos": 2529416970240000.0,
+      "train_loss": 0.5952504741611765,
+      "train_runtime": 701.2614,
+      "train_samples_per_second": 609.687,
+      "train_steps_per_second": 4.777
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 2529416970240000.0,
+  "trial_name": null,
+  "trial_params": null
+}