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_wnli_128
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.14084507042253522
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mobilebert_sa_GLUE_Experiment_data_aug_wnli_128
 
-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: 6.9665
+- Loss: 1.9522
 - Accuracy: 0.1408
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.14084507042253522,
+    "eval_loss": 1.952246904373169,
+    "eval_runtime": 0.1394,
+    "eval_samples": 71,
+    "eval_samples_per_second": 509.451,
+    "eval_steps_per_second": 7.175,
+    "train_loss": 0.45706886496123683,
+    "train_runtime": 1646.7328,
+    "train_samples": 55640,
+    "train_samples_per_second": 1689.406,
+    "train_steps_per_second": 13.208
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.14084507042253522,
+    "eval_loss": 1.952246904373169,
+    "eval_runtime": 0.1394,
+    "eval_samples": 71,
+    "eval_samples_per_second": 509.451,
+    "eval_steps_per_second": 7.175
+}

logs/events.out.tfevents.1675442412.serv-3329.2664268.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066c63110c5fefc7f541d64cf797bae304acdd37a9a93d8cf10dabb51568a1b2
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.45706886496123683,
+    "train_runtime": 1646.7328,
+    "train_samples": 55640,
+    "train_samples_per_second": 1689.406,
+    "train_steps_per_second": 13.208
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.952246904373169,
+  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_wnli_128/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": 0.6679,
+      "step": 435
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.14084507042253522,
+      "eval_loss": 1.952246904373169,
+      "eval_runtime": 0.1404,
+      "eval_samples_per_second": 505.649,
+      "eval_steps_per_second": 7.122,
+      "step": 435
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4943,
+      "step": 870
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.11267605633802817,
+      "eval_loss": 3.652181386947632,
+      "eval_runtime": 0.1331,
+      "eval_samples_per_second": 533.553,
+      "eval_steps_per_second": 7.515,
+      "step": 870
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4405,
+      "step": 1305
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.1267605633802817,
+      "eval_loss": 4.511776924133301,
+      "eval_runtime": 0.1324,
+      "eval_samples_per_second": 536.125,
+      "eval_steps_per_second": 7.551,
+      "step": 1305
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4086,
+      "step": 1740
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.11267605633802817,
+      "eval_loss": 6.04368782043457,
+      "eval_runtime": 0.1327,
+      "eval_samples_per_second": 535.177,
+      "eval_steps_per_second": 7.538,
+      "step": 1740
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3818,
+      "step": 2175
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.11267605633802817,
+      "eval_loss": 9.593058586120605,
+      "eval_runtime": 0.1318,
+      "eval_samples_per_second": 538.611,
+      "eval_steps_per_second": 7.586,
+      "step": 2175
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3492,
+      "step": 2610
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.14084507042253522,
+      "eval_loss": 6.966458797454834,
+      "eval_runtime": 0.1319,
+      "eval_samples_per_second": 538.276,
+      "eval_steps_per_second": 7.581,
+      "step": 2610
+    },
+    {
+      "epoch": 6.0,
+      "step": 2610,
+      "total_flos": 7956940701302784.0,
+      "train_loss": 0.45706886496123683,
+      "train_runtime": 1646.7328,
+      "train_samples_per_second": 1689.406,
+      "train_steps_per_second": 13.208
+    }
+  ],
+  "max_steps": 21750,
+  "num_train_epochs": 50,
+  "total_flos": 7956940701302784.0,
+  "trial_name": null,
+  "trial_params": null
+}