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: 0.0463559874942472
+      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_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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6185
-- Matthews Correlation: 0.0464
+- Loss: 0.6168
+- Matthews Correlation: 0.0
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 11.0,
+    "eval_loss": 0.6167517900466919,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.8768,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 555.726,
+    "eval_steps_per_second": 4.795,
+    "train_loss": 0.5990640233944359,
+    "train_runtime": 596.1692,
+    "train_samples": 8551,
+    "train_samples_per_second": 717.162,
+    "train_steps_per_second": 5.619
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "eval_loss": 0.6167517900466919,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 1.8768,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 555.726,
+    "eval_steps_per_second": 4.795
+}

logs/events.out.tfevents.1674736557.gera.2822633.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee05008e533c90a3b2232716d5ebc3348500c3de596482bdb1556f5dc0cec3f
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 0.5990640233944359,
+    "train_runtime": 596.1692,
+    "train_samples": 8551,
+    "train_samples_per_second": 717.162,
+    "train_steps_per_second": 5.619
+}

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": 0.6167517900466919,
+  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_cola_128/checkpoint-402",
+  "epoch": 11.0,
+  "global_step": 737,
+  "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": 0.617,
+      "step": 67
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6180861592292786,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8368,
+      "eval_samples_per_second": 567.845,
+      "eval_steps_per_second": 4.9,
+      "step": 67
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.608,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6181017756462097,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9583,
+      "eval_samples_per_second": 532.607,
+      "eval_steps_per_second": 4.596,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6075,
+      "step": 201
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6182523965835571,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8497,
+      "eval_samples_per_second": 563.867,
+      "eval_steps_per_second": 4.866,
+      "step": 201
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6072,
+      "step": 268
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6176720261573792,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8571,
+      "eval_samples_per_second": 561.629,
+      "eval_steps_per_second": 4.846,
+      "step": 268
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6069,
+      "step": 335
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6185395121574402,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8719,
+      "eval_samples_per_second": 557.191,
+      "eval_steps_per_second": 4.808,
+      "step": 335
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.606,
+      "step": 402
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.6167517900466919,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8173,
+      "eval_samples_per_second": 573.928,
+      "eval_steps_per_second": 4.952,
+      "step": 402
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6014,
+      "step": 469
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.6234214901924133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8314,
+      "eval_samples_per_second": 569.522,
+      "eval_steps_per_second": 4.914,
+      "step": 469
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5947,
+      "step": 536
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6217920184135437,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8379,
+      "eval_samples_per_second": 567.481,
+      "eval_steps_per_second": 4.897,
+      "step": 536
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5858,
+      "step": 603
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.6321389675140381,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.8577,
+      "eval_samples_per_second": 561.444,
+      "eval_steps_per_second": 4.845,
+      "step": 603
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.579,
+      "step": 670
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.6177334785461426,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.8263,
+      "eval_samples_per_second": 571.085,
+      "eval_steps_per_second": 4.928,
+      "step": 670
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.5762,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.6184676289558411,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 1.8441,
+      "eval_samples_per_second": 565.593,
+      "eval_steps_per_second": 4.88,
+      "step": 737
+    },
+    {
+      "epoch": 11.0,
+      "step": 737,
+      "total_flos": 2245484232048640.0,
+      "train_loss": 0.5990640233944359,
+      "train_runtime": 596.1692,
+      "train_samples_per_second": 717.162,
+      "train_steps_per_second": 5.619
+    }
+  ],
+  "max_steps": 3350,
+  "num_train_epochs": 50,
+  "total_flos": 2245484232048640.0,
+  "trial_name": null,
+  "trial_params": null
+}