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_logit_kd_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: 0.09303560843725145
 ---
 
 <!-- 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_logit_kd_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: 0.7829
-- Matthews Correlation: 0.1253
+- Loss: 0.6759
+- Matthews Correlation: 0.0930
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6759397387504578,
+    "eval_matthews_correlation": 0.09303560843725145,
+    "eval_runtime": 1.9096,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 546.19,
+    "eval_steps_per_second": 4.713,
+    "train_loss": 0.5057331540043158,
+    "train_runtime": 5414.9838,
+    "train_samples": 213609,
+    "train_samples_per_second": 1972.388,
+    "train_steps_per_second": 15.411
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.6759397387504578,
+    "eval_matthews_correlation": 0.09303560843725145,
+    "eval_runtime": 1.9096,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 546.19,
+    "eval_steps_per_second": 4.713
+}

logs/events.out.tfevents.1675297811.serv-3331.4063650.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ac208659e94f77b38a47fe88ab4ebcd00a44046b42a3b1b68de4c563c0edd9
+size 375

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.5057331540043158,
+    "train_runtime": 5414.9838,
+    "train_samples": 213609,
+    "train_samples_per_second": 1972.388,
+    "train_steps_per_second": 15.411
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6759397387504578,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_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": 0.6287,
+      "step": 1669
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6759397387504578,
+      "eval_matthews_correlation": 0.09303560843725145,
+      "eval_runtime": 1.9002,
+      "eval_samples_per_second": 548.888,
+      "eval_steps_per_second": 4.736,
+      "step": 1669
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5492,
+      "step": 3338
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7164148688316345,
+      "eval_matthews_correlation": 0.07190454015023796,
+      "eval_runtime": 1.8926,
+      "eval_samples_per_second": 551.086,
+      "eval_steps_per_second": 4.755,
+      "step": 3338
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5243,
+      "step": 5007
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7166932225227356,
+      "eval_matthews_correlation": 0.09362160966096678,
+      "eval_runtime": 1.8934,
+      "eval_samples_per_second": 550.867,
+      "eval_steps_per_second": 4.753,
+      "step": 5007
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4881,
+      "step": 6676
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7532314658164978,
+      "eval_matthews_correlation": 0.10273739156178968,
+      "eval_runtime": 1.9251,
+      "eval_samples_per_second": 541.779,
+      "eval_steps_per_second": 4.675,
+      "step": 6676
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4422,
+      "step": 8345
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7825189828872681,
+      "eval_matthews_correlation": 0.13693365735983404,
+      "eval_runtime": 1.8943,
+      "eval_samples_per_second": 550.606,
+      "eval_steps_per_second": 4.751,
+      "step": 8345
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4019,
+      "step": 10014
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.7828965783119202,
+      "eval_matthews_correlation": 0.12533414798451334,
+      "eval_runtime": 1.891,
+      "eval_samples_per_second": 551.569,
+      "eval_steps_per_second": 4.759,
+      "step": 10014
+    },
+    {
+      "epoch": 6.0,
+      "step": 10014,
+      "total_flos": 3.3760240390373376e+16,
+      "train_loss": 0.5057331540043158,
+      "train_runtime": 5414.9838,
+      "train_samples_per_second": 1972.388,
+      "train_steps_per_second": 15.411
+    }
+  ],
+  "max_steps": 83450,
+  "num_train_epochs": 50,
+  "total_flos": 3.3760240390373376e+16,
+  "trial_name": null,
+  "trial_params": null
+}