End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE WNLI
       type: glue
       config: wnli
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5352112676056338
+      value: 0.5633802816901409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_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 the glue 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: 0.6928
-- Accuracy: 0.5352
+- Loss: 0.6833
+- Accuracy: 0.5634
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6832635402679443,
+    "eval_runtime": 0.0951,
+    "eval_samples": 71,
+    "eval_samples_per_second": 746.731,
+    "eval_steps_per_second": 10.517,
+    "train_loss": 0.7138732274373373,
+    "train_runtime": 38.2187,
+    "train_samples": 635,
+    "train_samples_per_second": 830.744,
+    "train_steps_per_second": 3.925
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6832635402679443,
+    "eval_runtime": 0.0951,
+    "eval_samples": 71,
+    "eval_samples_per_second": 746.731,
+    "eval_steps_per_second": 10.517
+}

logs/events.out.tfevents.1677758462.serv-3317.65116.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78d441cb0a6dc9326fc1780a179a113673e75805c72d67e39bd68b7ca6498b6
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.7138732274373373,
+    "train_runtime": 38.2187,
+    "train_samples": 635,
+    "train_samples_per_second": 830.744,
+    "train_steps_per_second": 3.925
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.6832635402679443,
+  "best_model_checkpoint": "hBERTv2_wnli/checkpoint-6",
+  "epoch": 7.0,
+  "global_step": 21,
+  "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": 0.7351,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5211267605633803,
+      "eval_loss": 0.7259640693664551,
+      "eval_runtime": 0.0924,
+      "eval_samples_per_second": 768.523,
+      "eval_steps_per_second": 10.824,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7223,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6832635402679443,
+      "eval_runtime": 0.0917,
+      "eval_samples_per_second": 774.537,
+      "eval_steps_per_second": 10.909,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7189,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.711009681224823,
+      "eval_runtime": 0.0911,
+      "eval_samples_per_second": 778.974,
+      "eval_steps_per_second": 10.971,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.633333333333333e-05,
+      "loss": 0.708,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.7058689594268799,
+      "eval_runtime": 0.0936,
+      "eval_samples_per_second": 758.69,
+      "eval_steps_per_second": 10.686,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.566666666666667e-05,
+      "loss": 0.7032,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.6924964189529419,
+      "eval_runtime": 0.0934,
+      "eval_samples_per_second": 759.999,
+      "eval_steps_per_second": 10.704,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.6987,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4225352112676056,
+      "eval_loss": 0.712141215801239,
+      "eval_runtime": 0.09,
+      "eval_samples_per_second": 788.982,
+      "eval_steps_per_second": 11.112,
+      "step": 18
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.3666666666666666e-05,
+      "loss": 0.7109,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.692805826663971,
+      "eval_runtime": 0.093,
+      "eval_samples_per_second": 763.541,
+      "eval_steps_per_second": 10.754,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "step": 21,
+      "total_flos": 553639999438848.0,
+      "train_loss": 0.7138732274373373,
+      "train_runtime": 38.2187,
+      "train_samples_per_second": 830.744,
+      "train_steps_per_second": 3.925
+    }
+  ],
+  "max_steps": 150,
+  "num_train_epochs": 50,
+  "total_flos": 553639999438848.0,
+  "trial_name": null,
+  "trial_params": null
+}