End of training

README.md

@@ -1,12 +1,30 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: hBERTv1_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: 0.8161513727430126
+    - name: F1
+      type: f1
+      value: 0.7679145720798077
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_data_aug_qqp
 
-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 QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Accuracy: 0.6318
-- F1: 0.0
-- Combined Score: 0.3159
+- Loss: 0.5769
+- Accuracy: 0.8162
+- F1: 0.7679
+- Combined Score: 0.7920
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8161513727430126,
+    "eval_combined_score": 0.7920329724114101,
+    "eval_f1": 0.7679145720798077,
+    "eval_loss": 0.5768789649009705,
+    "eval_runtime": 51.637,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 782.966,
+    "eval_steps_per_second": 3.06,
+    "train_loss": 0.0728226451122308,
+    "train_runtime": 160762.5155,
+    "train_samples": 7595601,
+    "train_samples_per_second": 2362.367,
+    "train_steps_per_second": 9.228
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8161513727430126,
+    "eval_combined_score": 0.7920329724114101,
+    "eval_f1": 0.7679145720798077,
+    "eval_loss": 0.5768789649009705,
+    "eval_runtime": 51.637,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 782.966,
+    "eval_steps_per_second": 3.06
+}

logs/events.out.tfevents.1678006024.serv-9223.249238.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2561e2183219b2e0c14d683a9f95b800274088e1ab13c8c4a598239b0dc020a
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.0728226451122308,
+    "train_runtime": 160762.5155,
+    "train_samples": 7595601,
+    "train_samples_per_second": 2362.367,
+    "train_steps_per_second": 9.228
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.5768789649009705,
+  "best_model_checkpoint": "hBERTv1_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": 4.900043813824947e-05,
+      "loss": 0.2419,
+      "step": 29671
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8161513727430126,
+      "eval_combined_score": 0.7920329724114101,
+      "eval_f1": 0.7679145720798077,
+      "eval_loss": 0.5768789649009705,
+      "eval_runtime": 51.7601,
+      "eval_samples_per_second": 781.104,
+      "eval_steps_per_second": 3.053,
+      "step": 29671
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800087627649894e-05,
+      "loss": 0.104,
+      "step": 59342
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8271580509522631,
+      "eval_combined_score": 0.8020066662987143,
+      "eval_f1": 0.7768552816451655,
+      "eval_loss": 0.6326977014541626,
+      "eval_runtime": 51.8347,
+      "eval_samples_per_second": 779.98,
+      "eval_steps_per_second": 3.048,
+      "step": 59342
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700657207374204e-05,
+      "loss": 0.0911,
+      "step": 89013
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 50.4277,
+      "eval_samples_per_second": 801.741,
+      "eval_steps_per_second": 3.133,
+      "step": 89013
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6006572073742036e-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": 50.4722,
+      "eval_samples_per_second": 801.035,
+      "eval_steps_per_second": 3.13,
+      "step": 118684
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500657207374204e-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": 50.4709,
+      "eval_samples_per_second": 801.056,
+      "eval_steps_per_second": 3.131,
+      "step": 148355
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400657207374204e-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": 50.4183,
+      "eval_samples_per_second": 801.892,
+      "eval_steps_per_second": 3.134,
+      "step": 178026
+    },
+    {
+      "epoch": 6.0,
+      "step": 178026,
+      "total_flos": 5.75644928419509e+18,
+      "train_loss": 0.0728226451122308,
+      "train_runtime": 160762.5155,
+      "train_samples_per_second": 2362.367,
+      "train_steps_per_second": 9.228
+    }
+  ],
+  "max_steps": 1483550,
+  "num_train_epochs": 50,
+  "total_flos": 5.75644928419509e+18,
+  "trial_name": null,
+  "trial_params": null
+}