End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: hBERTv2_data_aug_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5053999633900788
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +28,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_data_aug_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6931
 - Accuracy: 0.5054

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930704116821289,
+    "eval_runtime": 6.3204,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 864.339,
+    "eval_steps_per_second": 3.481,
+    "train_loss": 0.6932406767414228,
+    "train_runtime": 86584.2008,
+    "train_samples": 4250511,
+    "train_samples_per_second": 2454.553,
+    "train_steps_per_second": 9.588
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.6930704116821289,
+    "eval_runtime": 6.3204,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 864.339,
+    "eval_steps_per_second": 3.481
+}

logs/events.out.tfevents.1677836616.serv-3317.65033.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad75302d41961149e60fc3f4394365b37d27b0611bf15bde4e5fb1a4def8d84
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.6932406767414228,
+    "train_runtime": 86584.2008,
+    "train_samples": 4250511,
+    "train_samples_per_second": 2454.553,
+    "train_steps_per_second": 9.588
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.6930704116821289,
+  "best_model_checkpoint": "hBERTv2_data_aug_qnli/checkpoint-16604",
+  "epoch": 6.0,
+  "global_step": 99624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900036135870875e-05,
+      "loss": 0.6934,
+      "step": 16604
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6930704116821289,
+      "eval_runtime": 6.4224,
+      "eval_samples_per_second": 850.613,
+      "eval_steps_per_second": 3.425,
+      "step": 16604
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800078294386895e-05,
+      "loss": 0.6932,
+      "step": 33208
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931126117706299,
+      "eval_runtime": 6.4301,
+      "eval_samples_per_second": 849.596,
+      "eval_steps_per_second": 3.421,
+      "step": 33208
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700114430257769e-05,
+      "loss": 0.6932,
+      "step": 49812
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931178569793701,
+      "eval_runtime": 6.4408,
+      "eval_samples_per_second": 848.182,
+      "eval_steps_per_second": 3.416,
+      "step": 49812
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.6001565887737896e-05,
+      "loss": 0.6932,
+      "step": 66416
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931198239326477,
+      "eval_runtime": 6.3591,
+      "eval_samples_per_second": 859.08,
+      "eval_steps_per_second": 3.46,
+      "step": 66416
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500204769934956e-05,
+      "loss": 0.6932,
+      "step": 83020
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6931706070899963,
+      "eval_runtime": 6.3657,
+      "eval_samples_per_second": 858.199,
+      "eval_steps_per_second": 3.456,
+      "step": 83020
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400252951096122e-05,
+      "loss": 0.6932,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6931073069572449,
+      "eval_runtime": 6.4132,
+      "eval_samples_per_second": 851.84,
+      "eval_steps_per_second": 3.43,
+      "step": 99624
+    },
+    {
+      "epoch": 6.0,
+      "step": 99624,
+      "total_flos": 3.1764944527640494e+18,
+      "train_loss": 0.6932406767414228,
+      "train_runtime": 86584.2008,
+      "train_samples_per_second": 2454.553,
+      "train_steps_per_second": 9.588
+    }
+  ],
+  "max_steps": 830200,
+  "num_train_epochs": 50,
+  "total_flos": 3.1764944527640494e+18,
+  "trial_name": null,
+  "trial_params": null
+}