End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: hBERTv2_data_aug_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_data_aug_wnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on an unknown dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6908
+- Loss: 0.6873
 - Accuracy: 0.5634
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6873350739479065,
+    "eval_runtime": 0.0923,
+    "eval_samples": 71,
+    "eval_samples_per_second": 769.394,
+    "eval_steps_per_second": 10.837,
+    "train_loss": 0.6942421624419886,
+    "train_runtime": 1727.2715,
+    "train_samples": 55640,
+    "train_samples_per_second": 1610.633,
+    "train_steps_per_second": 6.311
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6873350739479065,
+    "eval_runtime": 0.0923,
+    "eval_samples": 71,
+    "eval_samples_per_second": 769.394,
+    "eval_steps_per_second": 10.837
+}

logs/events.out.tfevents.1678029007.serv-3317.65033.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb988ab0bee521a930b9d7b8bf42c902573d70b2270904f1a2c5705956260ecf
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 0.6942421624419886,
+    "train_runtime": 1727.2715,
+    "train_samples": 55640,
+    "train_samples_per_second": 1610.633,
+    "train_steps_per_second": 6.311
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.6873350739479065,
+  "best_model_checkpoint": "hBERTv2_data_aug_wnli/checkpoint-654",
+  "epoch": 8.0,
+  "global_step": 1744,
+  "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": 0.699,
+      "step": 218
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6895423531532288,
+      "eval_runtime": 0.1007,
+      "eval_samples_per_second": 704.868,
+      "eval_steps_per_second": 9.928,
+      "step": 218
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6947,
+      "step": 436
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6886346340179443,
+      "eval_runtime": 0.098,
+      "eval_samples_per_second": 724.276,
+      "eval_steps_per_second": 10.201,
+      "step": 436
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.702752293577982e-05,
+      "loss": 0.6935,
+      "step": 654
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6873350739479065,
+      "eval_runtime": 0.0993,
+      "eval_samples_per_second": 714.989,
+      "eval_steps_per_second": 10.07,
+      "step": 654
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.602752293577982e-05,
+      "loss": 0.6937,
+      "step": 872
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.692121684551239,
+      "eval_runtime": 0.1012,
+      "eval_samples_per_second": 701.584,
+      "eval_steps_per_second": 9.881,
+      "step": 872
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.502752293577982e-05,
+      "loss": 0.6934,
+      "step": 1090
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.689205527305603,
+      "eval_runtime": 0.1019,
+      "eval_samples_per_second": 696.888,
+      "eval_steps_per_second": 9.815,
+      "step": 1090
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.402752293577982e-05,
+      "loss": 0.6932,
+      "step": 1308
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6910760402679443,
+      "eval_runtime": 0.1003,
+      "eval_samples_per_second": 708.197,
+      "eval_steps_per_second": 9.975,
+      "step": 1308
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3027522935779816e-05,
+      "loss": 0.6933,
+      "step": 1526
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.6955257654190063,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 730.321,
+      "eval_steps_per_second": 10.286,
+      "step": 1526
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.202752293577982e-05,
+      "loss": 0.6931,
+      "step": 1744
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6907530426979065,
+      "eval_runtime": 0.0956,
+      "eval_samples_per_second": 742.91,
+      "eval_steps_per_second": 10.464,
+      "step": 1744
+    },
+    {
+      "epoch": 8.0,
+      "step": 1744,
+      "total_flos": 5.544122456316314e+16,
+      "train_loss": 0.6942421624419886,
+      "train_runtime": 1727.2715,
+      "train_samples_per_second": 1610.633,
+      "train_steps_per_second": 6.311
+    }
+  ],
+  "max_steps": 10900,
+  "num_train_epochs": 50,
+  "total_flos": 5.544122456316314e+16,
+  "trial_name": null,
+  "trial_params": null
+}