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_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.8122270742358079
 ---
 
 <!-- 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_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6242
+- Loss: 0.6240
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6239516139030457,
+    "eval_runtime": 0.4957,
+    "eval_samples": 408,
+    "eval_samples_per_second": 823.03,
+    "eval_steps_per_second": 4.034,
+    "train_loss": 0.6304825585368076,
+    "train_runtime": 5936.2197,
+    "train_samples": 250736,
+    "train_samples_per_second": 2111.916,
+    "train_steps_per_second": 8.254
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6239516139030457,
+    "eval_runtime": 0.4957,
+    "eval_samples": 408,
+    "eval_samples_per_second": 823.03,
+    "eval_steps_per_second": 4.034
+}

logs/events.out.tfevents.1677673079.kyoto.1079667.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82cc76347ef33f522da19e8a6c172df3df67b0fb23492e7314424a85dff65ab
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.6304825585368076,
+    "train_runtime": 5936.2197,
+    "train_samples": 250736,
+    "train_samples_per_second": 2111.916,
+    "train_steps_per_second": 8.254
+}

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.6239516139030457,
+  "best_model_checkpoint": "hBERTv2_data_aug_mrpc/checkpoint-1960",
+  "epoch": 7.0,
+  "global_step": 6860,
+  "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": 0.6319,
+      "step": 980
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6244884133338928,
+      "eval_runtime": 0.4844,
+      "eval_samples_per_second": 842.316,
+      "eval_steps_per_second": 4.129,
+      "step": 980
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6305,
+      "step": 1960
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6239516139030457,
+      "eval_runtime": 0.4853,
+      "eval_samples_per_second": 840.662,
+      "eval_steps_per_second": 4.121,
+      "step": 1960
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6303,
+      "step": 2940
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6259029507637024,
+      "eval_runtime": 0.4889,
+      "eval_samples_per_second": 834.471,
+      "eval_steps_per_second": 4.091,
+      "step": 2940
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6302,
+      "step": 3920
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6251693964004517,
+      "eval_runtime": 0.4839,
+      "eval_samples_per_second": 843.134,
+      "eval_steps_per_second": 4.133,
+      "step": 3920
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500102040816327e-05,
+      "loss": 0.6302,
+      "step": 4900
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241449117660522,
+      "eval_runtime": 0.4848,
+      "eval_samples_per_second": 841.641,
+      "eval_steps_per_second": 4.126,
+      "step": 4900
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.4001020408163265e-05,
+      "loss": 0.6302,
+      "step": 5880
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241024136543274,
+      "eval_runtime": 0.4821,
+      "eval_samples_per_second": 846.383,
+      "eval_steps_per_second": 4.149,
+      "step": 5880
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.300102040816327e-05,
+      "loss": 0.6301,
+      "step": 6860
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241885423660278,
+      "eval_runtime": 0.4836,
+      "eval_samples_per_second": 843.639,
+      "eval_steps_per_second": 4.135,
+      "step": 6860
+    },
+    {
+      "epoch": 7.0,
+      "step": 6860,
+      "total_flos": 2.1861021041400218e+17,
+      "train_loss": 0.6304825585368076,
+      "train_runtime": 5936.2197,
+      "train_samples_per_second": 2111.916,
+      "train_steps_per_second": 8.254
+    }
+  ],
+  "max_steps": 49000,
+  "num_train_epochs": 50,
+  "total_flos": 2.1861021041400218e+17,
+  "trial_name": null,
+  "trial_params": null
+}