End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: hBERTv1_data_aug_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5053999633900788
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +28,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_data_aug_qnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6931
 - Accuracy: 0.5054

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930862069129944,
+    "eval_runtime": 6.9199,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 789.462,
+    "eval_steps_per_second": 3.179,
+    "train_loss": 0.693251175200002,
+    "train_runtime": 91175.0516,
+    "train_samples": 4250511,
+    "train_samples_per_second": 2330.962,
+    "train_steps_per_second": 9.106
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930862069129944,
+    "eval_runtime": 6.9199,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 789.462,
+    "eval_steps_per_second": 3.179
+}

logs/events.out.tfevents.1677844110.serv-9223.249238.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5656778d04ea858e11393a8e4d10c45c0ded88596b9f5cb51ae0053b93780772
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.693251175200002,
+    "train_runtime": 91175.0516,
+    "train_samples": 4250511,
+    "train_samples_per_second": 2330.962,
+    "train_steps_per_second": 9.106
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6930862069129944,
+  "best_model_checkpoint": "hBERTv1_data_aug_qnli/checkpoint-16604",
+  "epoch": 6.0,
+  "global_step": 99624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9000421585160206e-05,
+      "loss": 0.6933,
+      "step": 16604
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930862069129944,
+      "eval_runtime": 6.9764,
+      "eval_samples_per_second": 783.068,
+      "eval_steps_per_second": 3.153,
+      "step": 16604
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800090339677186e-05,
+      "loss": 0.6932,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931231617927551,
+      "eval_runtime": 7.005,
+      "eval_samples_per_second": 779.871,
+      "eval_steps_per_second": 3.141,
+      "step": 33208
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700138520838353e-05,
+      "loss": 0.6932,
+      "step": 49812
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930967569351196,
+      "eval_runtime": 6.9994,
+      "eval_samples_per_second": 780.494,
+      "eval_steps_per_second": 3.143,
+      "step": 49812
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600186701999518e-05,
+      "loss": 0.6932,
+      "step": 66416
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931020617485046,
+      "eval_runtime": 6.9797,
+      "eval_samples_per_second": 782.698,
+      "eval_steps_per_second": 3.152,
+      "step": 66416
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500234883160684e-05,
+      "loss": 0.6932,
+      "step": 83020
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931495070457458,
+      "eval_runtime": 7.0501,
+      "eval_samples_per_second": 774.887,
+      "eval_steps_per_second": 3.121,
+      "step": 83020
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4002830643218504e-05,
+      "loss": 0.6932,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930967569351196,
+      "eval_runtime": 6.9694,
+      "eval_samples_per_second": 783.852,
+      "eval_steps_per_second": 3.157,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "step": 99624,
+      "total_flos": 3.221318655610454e+18,
+      "train_loss": 0.693251175200002,
+      "train_runtime": 91175.0516,
+      "train_samples_per_second": 2330.962,
+      "train_steps_per_second": 9.106
+    }
+  ],
+  "max_steps": 830200,
+  "num_train_epochs": 50,
+  "total_flos": 3.221318655610454e+18,
+  "trial_name": null,
+  "trial_params": null
+}