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_wnli_256
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.1267605633802817
 ---
 
 <!-- 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_wnli_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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6571
-- Accuracy: 0.0986
+- Loss: 0.5755
+- Accuracy: 0.1268
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.1267605633802817,
+    "eval_loss": 0.5755178928375244,
+    "eval_runtime": 0.1511,
+    "eval_samples": 71,
+    "eval_samples_per_second": 470.012,
+    "eval_steps_per_second": 6.62,
+    "train_loss": 0.2951635601876796,
+    "train_runtime": 1477.2025,
+    "train_samples": 55640,
+    "train_samples_per_second": 1883.29,
+    "train_steps_per_second": 14.724
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.1267605633802817,
+    "eval_loss": 0.5755178928375244,
+    "eval_runtime": 0.1511,
+    "eval_samples": 71,
+    "eval_samples_per_second": 470.012,
+    "eval_steps_per_second": 6.62
+}

logs/events.out.tfevents.1675457898.serv-3331.1281659.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0163860bdd65791fadf45f3b296e14a1d385072eb725319cf9c01f9026fccbb5
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.2951635601876796,
+    "train_runtime": 1477.2025,
+    "train_samples": 55640,
+    "train_samples_per_second": 1883.29,
+    "train_steps_per_second": 14.724
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.5755178928375244,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_wnli_256/checkpoint-435",
+  "epoch": 6.0,
+  "global_step": 2610,
+  "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": 0.337,
+      "step": 435
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1267605633802817,
+      "eval_loss": 0.5755178928375244,
+      "eval_runtime": 0.138,
+      "eval_samples_per_second": 514.394,
+      "eval_steps_per_second": 7.245,
+      "step": 435
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3007,
+      "step": 870
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.11267605633802817,
+      "eval_loss": 0.5814011096954346,
+      "eval_runtime": 0.1376,
+      "eval_samples_per_second": 515.985,
+      "eval_steps_per_second": 7.267,
+      "step": 870
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2921,
+      "step": 1305
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.11267605633802817,
+      "eval_loss": 0.6514396071434021,
+      "eval_runtime": 0.138,
+      "eval_samples_per_second": 514.337,
+      "eval_steps_per_second": 7.244,
+      "step": 1305
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2857,
+      "step": 1740
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.07042253521126761,
+      "eval_loss": 0.6644425392150879,
+      "eval_runtime": 0.1375,
+      "eval_samples_per_second": 516.496,
+      "eval_steps_per_second": 7.275,
+      "step": 1740
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2804,
+      "step": 2175
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.09859154929577464,
+      "eval_loss": 0.6379522681236267,
+      "eval_runtime": 0.1372,
+      "eval_samples_per_second": 517.681,
+      "eval_steps_per_second": 7.291,
+      "step": 2175
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2751,
+      "step": 2610
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.09859154929577464,
+      "eval_loss": 0.6570851802825928,
+      "eval_runtime": 0.1373,
+      "eval_samples_per_second": 517.202,
+      "eval_steps_per_second": 7.285,
+      "step": 2610
+    },
+    {
+      "epoch": 6.0,
+      "step": 2610,
+      "total_flos": 8793729716453376.0,
+      "train_loss": 0.2951635601876796,
+      "train_runtime": 1477.2025,
+      "train_samples_per_second": 1883.29,
+      "train_steps_per_second": 14.724
+    }
+  ],
+  "max_steps": 21750,
+  "num_train_epochs": 50,
+  "total_flos": 8793729716453376.0,
+  "trial_name": null,
+  "trial_params": null
+}