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_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8600917431192661
 ---
 
 <!-- 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_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4965
-- Accuracy: 0.8589
+- Loss: 0.4834
+- Accuracy: 0.8601
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8600917431192661,
+    "eval_loss": 0.4834231436252594,
+    "eval_runtime": 2.1074,
+    "eval_samples": 872,
+    "eval_samples_per_second": 413.789,
+    "eval_steps_per_second": 3.322,
+    "train_loss": 0.25491558645324286,
+    "train_runtime": 66746.3863,
+    "train_samples": 1119619,
+    "train_samples_per_second": 838.711,
+    "train_steps_per_second": 6.553
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8600917431192661,
+    "eval_loss": 0.4834231436252594,
+    "eval_runtime": 2.1074,
+    "eval_samples": 872,
+    "eval_samples_per_second": 413.789,
+    "eval_steps_per_second": 3.322
+}

logs/events.out.tfevents.1675468938.serv-3329.2671356.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcea7d214bb85035c334a29da23e51324da8d5ca2e2923231ef3c2ee02602cea
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.25491558645324286,
+    "train_runtime": 66746.3863,
+    "train_samples": 1119619,
+    "train_samples_per_second": 838.711,
+    "train_steps_per_second": 6.553
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.4834231436252594,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_sst2/checkpoint-43740",
+  "epoch": 10.0,
+  "global_step": 87480,
+  "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": 0.4923,
+      "step": 8748
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.5804396867752075,
+      "eval_runtime": 2.0555,
+      "eval_samples_per_second": 424.236,
+      "eval_steps_per_second": 3.406,
+      "step": 8748
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3226,
+      "step": 17496
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8474770642201835,
+      "eval_loss": 0.5183534622192383,
+      "eval_runtime": 2.0608,
+      "eval_samples_per_second": 423.145,
+      "eval_steps_per_second": 3.397,
+      "step": 17496
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2725,
+      "step": 26244
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8509174311926605,
+      "eval_loss": 0.5340900421142578,
+      "eval_runtime": 2.0579,
+      "eval_samples_per_second": 423.725,
+      "eval_steps_per_second": 3.401,
+      "step": 26244
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2453,
+      "step": 34992
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8520642201834863,
+      "eval_loss": 0.4892486333847046,
+      "eval_runtime": 2.0635,
+      "eval_samples_per_second": 422.583,
+      "eval_steps_per_second": 3.392,
+      "step": 34992
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2278,
+      "step": 43740
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8600917431192661,
+      "eval_loss": 0.4834231436252594,
+      "eval_runtime": 2.0608,
+      "eval_samples_per_second": 423.143,
+      "eval_steps_per_second": 3.397,
+      "step": 43740
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2149,
+      "step": 52488
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8623853211009175,
+      "eval_loss": 0.49795687198638916,
+      "eval_runtime": 2.0894,
+      "eval_samples_per_second": 417.337,
+      "eval_steps_per_second": 3.35,
+      "step": 52488
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2047,
+      "step": 61236
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8532110091743119,
+      "eval_loss": 0.5031076073646545,
+      "eval_runtime": 2.0529,
+      "eval_samples_per_second": 424.765,
+      "eval_steps_per_second": 3.41,
+      "step": 61236
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1963,
+      "step": 69984
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8509174311926605,
+      "eval_loss": 0.5010948777198792,
+      "eval_runtime": 2.0612,
+      "eval_samples_per_second": 423.064,
+      "eval_steps_per_second": 3.396,
+      "step": 69984
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1893,
+      "step": 78732
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.856651376146789,
+      "eval_loss": 0.4899327754974365,
+      "eval_runtime": 2.0597,
+      "eval_samples_per_second": 423.371,
+      "eval_steps_per_second": 3.399,
+      "step": 78732
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4e-05,
+      "loss": 0.1835,
+      "step": 87480
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8589449541284404,
+      "eval_loss": 0.49648550152778625,
+      "eval_runtime": 2.3706,
+      "eval_samples_per_second": 367.844,
+      "eval_steps_per_second": 2.953,
+      "step": 87480
+    },
+    {
+      "epoch": 10.0,
+      "step": 87480,
+      "total_flos": 3.5104824999542784e+17,
+      "train_loss": 0.25491558645324286,
+      "train_runtime": 66746.3863,
+      "train_samples_per_second": 838.711,
+      "train_steps_per_second": 6.553
+    }
+  ],
+  "max_steps": 437400,
+  "num_train_epochs": 50,
+  "total_flos": 3.5104824999542784e+17,
+  "trial_name": null,
+  "trial_params": null
+}