End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 base_model: gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48
 tags:
 - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QNLI
       type: glue
       config: qnli
       split: validation
@@ -21,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.4946000366099213
+      value: 0.5053999633900788
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_w_init_48_ver2_qnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6932
-- Accuracy: 0.4946
+- Loss: 0.6931
+- Accuracy: 0.5054
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930912137031555,
+    "eval_runtime": 27.8378,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 196.244,
+    "eval_steps_per_second": 3.089,
+    "train_loss": 0.6947647454110246,
+    "train_runtime": 15057.6981,
+    "train_samples": 104743,
+    "train_samples_per_second": 104.342,
+    "train_steps_per_second": 1.631
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930912137031555,
+    "eval_runtime": 27.8378,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 196.244,
+    "eval_steps_per_second": 3.089
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.0,
+    "train_loss": 0.6947647454110246,
+    "train_runtime": 15057.6981,
+    "train_samples": 104743,
+    "train_samples_per_second": 104.342,
+    "train_steps_per_second": 1.631
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.6930912137031555,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init_48_ver2_qnli/checkpoint-6548",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 14733,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.7034,
+      "step": 1637
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6952020525932312,
+      "eval_runtime": 28.6895,
+      "eval_samples_per_second": 190.418,
+      "eval_steps_per_second": 2.998,
+      "step": 1637
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.6953,
+      "step": 3274
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6949925422668457,
+      "eval_runtime": 28.691,
+      "eval_samples_per_second": 190.408,
+      "eval_steps_per_second": 2.997,
+      "step": 3274
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.694,
+      "step": 4911
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6932231783866882,
+      "eval_runtime": 28.6639,
+      "eval_samples_per_second": 190.588,
+      "eval_steps_per_second": 3.0,
+      "step": 4911
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9333333333333333e-05,
+      "loss": 0.6934,
+      "step": 6548
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930912137031555,
+      "eval_runtime": 28.6697,
+      "eval_samples_per_second": 190.549,
+      "eval_steps_per_second": 3.0,
+      "step": 6548
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6936,
+      "step": 8185
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6936073899269104,
+      "eval_runtime": 28.678,
+      "eval_samples_per_second": 190.495,
+      "eval_steps_per_second": 2.999,
+      "step": 8185
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.4e-05,
+      "loss": 0.6933,
+      "step": 9822
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930935382843018,
+      "eval_runtime": 28.6784,
+      "eval_samples_per_second": 190.492,
+      "eval_steps_per_second": 2.999,
+      "step": 9822
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.6933,
+      "step": 11459
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931483745574951,
+      "eval_runtime": 28.6596,
+      "eval_samples_per_second": 190.617,
+      "eval_steps_per_second": 3.001,
+      "step": 11459
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.6932,
+      "step": 13096
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931501626968384,
+      "eval_runtime": 28.7157,
+      "eval_samples_per_second": 190.244,
+      "eval_steps_per_second": 2.995,
+      "step": 13096
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6933,
+      "step": 14733
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6932412981987,
+      "eval_runtime": 28.6426,
+      "eval_samples_per_second": 190.73,
+      "eval_steps_per_second": 3.003,
+      "step": 14733
+    },
+    {
+      "epoch": 9.0,
+      "step": 14733,
+      "total_flos": 1.396089008726999e+17,
+      "train_loss": 0.6947647454110246,
+      "train_runtime": 15057.6981,
+      "train_samples_per_second": 104.342,
+      "train_steps_per_second": 1.631
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 24555,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 1.396089008726999e+17,
+  "trial_name": null,
+  "trial_params": null
+}