End of training

README.md

@@ -1,12 +1,30 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: hBERTv2_data_aug_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6318327974276527
+    - name: F1
+      type: f1
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_data_aug_qqp
 
-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 QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.6782
 - Accuracy: 0.6318
 - F1: 0.0
 - Combined Score: 0.3159

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6781896352767944,
+    "eval_runtime": 46.9166,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 861.742,
+    "eval_steps_per_second": 3.368,
+    "train_loss": 0.21557685426156767,
+    "train_runtime": 152441.456,
+    "train_samples": 7595601,
+    "train_samples_per_second": 2491.317,
+    "train_steps_per_second": 9.732
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6781896352767944,
+    "eval_runtime": 46.9166,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 861.742,
+    "eval_steps_per_second": 3.368
+}

logs/events.out.tfevents.1677989929.serv-3317.65033.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a5ba8c5c11969ee34c5266ee4a6822e0802497e0e1d522239574243b99b465
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.21557685426156767,
+    "train_runtime": 152441.456,
+    "train_samples": 7595601,
+    "train_samples_per_second": 2491.317,
+    "train_steps_per_second": 9.732
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.6781896352767944,
+  "best_model_checkpoint": "hBERTv2_data_aug_qqp/checkpoint-29671",
+  "epoch": 6.0,
+  "global_step": 178026,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900040443530721e-05,
+      "loss": 0.6528,
+      "step": 29671
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6781896352767944,
+      "eval_runtime": 48.8385,
+      "eval_samples_per_second": 827.831,
+      "eval_steps_per_second": 3.235,
+      "step": 29671
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800623504431937e-05,
+      "loss": 0.6407,
+      "step": 59342
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 47.7904,
+      "eval_samples_per_second": 845.987,
+      "eval_steps_per_second": 3.306,
+      "step": 59342
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7006235044319366e-05,
+      "loss": 0.0,
+      "step": 89013
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 45.7023,
+      "eval_samples_per_second": 884.639,
+      "eval_steps_per_second": 3.457,
+      "step": 89013
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6006235044319375e-05,
+      "loss": 0.0,
+      "step": 118684
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 45.742,
+      "eval_samples_per_second": 883.87,
+      "eval_steps_per_second": 3.454,
+      "step": 118684
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500623504431937e-05,
+      "loss": 0.0,
+      "step": 148355
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 45.7516,
+      "eval_samples_per_second": 883.686,
+      "eval_steps_per_second": 3.453,
+      "step": 148355
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4006235044319374e-05,
+      "loss": 0.0,
+      "step": 178026
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 45.6649,
+      "eval_samples_per_second": 885.363,
+      "eval_steps_per_second": 3.46,
+      "step": 178026
+    },
+    {
+      "epoch": 6.0,
+      "step": 178026,
+      "total_flos": 5.676348900038935e+18,
+      "train_loss": 0.21557685426156767,
+      "train_runtime": 152441.456,
+      "train_samples_per_second": 2491.317,
+      "train_steps_per_second": 9.732
+    }
+  ],
+  "max_steps": 1483550,
+  "num_train_epochs": 50,
+  "total_flos": 5.676348900038935e+18,
+  "trial_name": null,
+  "trial_params": null
+}