End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: mobilebert_sa_GLUE_Experiment_data_aug_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.48736462093862815
 ---
 
 <!-- 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_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.3303
-- Accuracy: 0.5054
+- Loss: 2.9188
+- Accuracy: 0.4874
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 2.9187636375427246,
+    "eval_runtime": 0.3231,
+    "eval_samples": 277,
+    "eval_samples_per_second": 857.273,
+    "eval_steps_per_second": 9.285,
+    "train_loss": 0.058194815412933275,
+    "train_runtime": 3187.5077,
+    "train_samples": 145398,
+    "train_samples_per_second": 2280.747,
+    "train_steps_per_second": 17.82
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.48736462093862815,
+    "eval_loss": 2.9187636375427246,
+    "eval_runtime": 0.3231,
+    "eval_samples": 277,
+    "eval_samples_per_second": 857.273,
+    "eval_steps_per_second": 9.285
+}

logs/events.out.tfevents.1675398798.serv-3331.1280613.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10ccb661511ea8dfccaff41fae0b5e45dafbd06201006348f82fc9143c9c957
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.058194815412933275,
+    "train_runtime": 3187.5077,
+    "train_samples": 145398,
+    "train_samples_per_second": 2280.747,
+    "train_steps_per_second": 17.82
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 2.9187636375427246,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_rte/checkpoint-1136",
+  "epoch": 6.0,
+  "global_step": 6816,
+  "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": 0.2441,
+      "step": 1136
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.48736462093862815,
+      "eval_loss": 2.9187636375427246,
+      "eval_runtime": 0.3156,
+      "eval_samples_per_second": 877.665,
+      "eval_steps_per_second": 9.505,
+      "step": 1136
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.0476,
+      "step": 2272
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5054151624548736,
+      "eval_loss": 4.320844650268555,
+      "eval_runtime": 0.3125,
+      "eval_samples_per_second": 886.386,
+      "eval_steps_per_second": 9.6,
+      "step": 2272
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.0262,
+      "step": 3408
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.48014440433212996,
+      "eval_loss": 5.102660655975342,
+      "eval_runtime": 0.3128,
+      "eval_samples_per_second": 885.5,
+      "eval_steps_per_second": 9.59,
+      "step": 3408
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0145,
+      "step": 4544
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.51985559566787,
+      "eval_loss": 7.759298324584961,
+      "eval_runtime": 0.312,
+      "eval_samples_per_second": 887.722,
+      "eval_steps_per_second": 9.614,
+      "step": 4544
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0091,
+      "step": 5680
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 7.344573020935059,
+      "eval_runtime": 0.3113,
+      "eval_samples_per_second": 889.686,
+      "eval_steps_per_second": 9.636,
+      "step": 5680
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0076,
+      "step": 6816
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5054151624548736,
+      "eval_loss": 9.330328941345215,
+      "eval_runtime": 0.3115,
+      "eval_samples_per_second": 889.366,
+      "eval_steps_per_second": 9.632,
+      "step": 6816
+    },
+    {
+      "epoch": 6.0,
+      "step": 6816,
+      "total_flos": 2.735308119264461e+16,
+      "train_loss": 0.058194815412933275,
+      "train_runtime": 3187.5077,
+      "train_samples_per_second": 2280.747,
+      "train_steps_per_second": 17.82
+    }
+  ],
+  "max_steps": 56800,
+  "num_train_epochs": 50,
+  "total_flos": 2.735308119264461e+16,
+  "trial_name": null,
+  "trial_params": null
+}