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_logit_kd_data_aug_qnli_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5881383855024712
 ---
 
 <!-- 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_qnli_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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2517
-- Accuracy: 0.5949
+- Loss: 1.1777
+- Accuracy: 0.5881
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5881383855024712,
+    "eval_loss": 1.1776939630508423,
+    "eval_runtime": 9.819,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 556.368,
+    "eval_steps_per_second": 4.379,
+    "train_loss": 0.4690695021091805,
+    "train_runtime": 107868.9496,
+    "train_samples": 4250511,
+    "train_samples_per_second": 1970.22,
+    "train_steps_per_second": 15.393
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5881383855024712,
+    "eval_loss": 1.1776939630508423,
+    "eval_runtime": 9.819,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 556.368,
+    "eval_steps_per_second": 4.379
+}

logs/events.out.tfevents.1675782067.serv-3334.2664389.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3a96209993c22a9f752d9cc6c2faa8fa54683a4c1c936babf34ff65bb74449
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.4690695021091805,
+    "train_runtime": 107868.9496,
+    "train_samples": 4250511,
+    "train_samples_per_second": 1970.22,
+    "train_steps_per_second": 15.393
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.1776939630508423,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_qnli_256/checkpoint-33208",
+  "epoch": 6.0,
+  "global_step": 199248,
+  "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": 0.6984,
+      "step": 33208
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5881383855024712,
+      "eval_loss": 1.1776939630508423,
+      "eval_runtime": 9.8533,
+      "eval_samples_per_second": 554.434,
+      "eval_steps_per_second": 4.364,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5294,
+      "step": 66416
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6011349075599487,
+      "eval_loss": 1.209543228149414,
+      "eval_runtime": 9.8475,
+      "eval_samples_per_second": 554.76,
+      "eval_steps_per_second": 4.367,
+      "step": 66416
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4577,
+      "step": 99624
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5958264689730917,
+      "eval_loss": 1.227351188659668,
+      "eval_runtime": 9.8414,
+      "eval_samples_per_second": 555.104,
+      "eval_steps_per_second": 4.369,
+      "step": 99624
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.407,
+      "step": 132832
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5963756177924218,
+      "eval_loss": 1.2722785472869873,
+      "eval_runtime": 9.8374,
+      "eval_samples_per_second": 555.332,
+      "eval_steps_per_second": 4.371,
+      "step": 132832
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.373,
+      "step": 166040
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5938129233022149,
+      "eval_loss": 1.3357822895050049,
+      "eval_runtime": 9.8371,
+      "eval_samples_per_second": 555.345,
+      "eval_steps_per_second": 4.371,
+      "step": 166040
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.349,
+      "step": 199248
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.594911220940875,
+      "eval_loss": 1.2517368793487549,
+      "eval_runtime": 9.8396,
+      "eval_samples_per_second": 555.206,
+      "eval_steps_per_second": 4.37,
+      "step": 199248
+    },
+    {
+      "epoch": 6.0,
+      "step": 199248,
+      "total_flos": 6.717800781950484e+17,
+      "train_loss": 0.4690695021091805,
+      "train_runtime": 107868.9496,
+      "train_samples_per_second": 1970.22,
+      "train_steps_per_second": 15.393
+    }
+  ],
+  "max_steps": 1660400,
+  "num_train_epochs": 50,
+  "total_flos": 6.717800781950484e+17,
+  "trial_name": null,
+  "trial_params": null
+}