End of training

README.md

@@ -3,12 +3,27 @@ library_name: transformers
 license: mit
 base_model: microsoft/deberta-v3-large
 tags:
+- single_label_classification
+- question-answering
+- text-classification
 - generated_from_trainer
+datasets:
+- beavertails
 metrics:
 - accuracy
 model-index:
 - name: QA-DeBERTa-v3-large-binary-3
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: saiteki-kai/Beavertails-it
+      type: beavertails
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8621618924044315
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,20 +31,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # QA-DeBERTa-v3-large-binary-3
 
-This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the saiteki-kai/Beavertails-it dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3452
-- Accuracy: 0.8607
-- Unsafe Precision: 0.8860
-- Unsafe Recall: 0.8604
-- Unsafe F1: 0.8730
-- Unsafe Fpr: 0.1389
-- Unsafe Aucpr: 0.9542
-- Safe Precision: 0.8310
-- Safe Recall: 0.8611
-- Safe F1: 0.8458
-- Safe Fpr: 0.1396
-- Safe Aucpr: 0.9216
+- Loss: 0.3184
+- Accuracy: 0.8622
+- Unsafe Precision: 0.8690
+- Unsafe Recall: 0.8859
+- Unsafe F1: 0.8773
+- Unsafe Fpr: 0.1676
+- Unsafe Aucpr: 0.9546
+- Safe Precision: 0.8533
+- Safe Recall: 0.8324
+- Safe F1: 0.8427
+- Safe Fpr: 0.1141
+- Safe Aucpr: 0.9201
 
 ## Model description
 

all_results.json

@@ -0,0 +1,38 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8621618924044315,
+    "eval_loss": 0.3183589279651642,
+    "eval_runtime": 44.2839,
+    "eval_safe_aucpr": 0.9201221570494966,
+    "eval_safe_f1": 0.8426927896115731,
+    "eval_safe_fpr": 0.1141072015784278,
+    "eval_safe_precision": 0.8532543923724578,
+    "eval_safe_recall": 0.8323894535498632,
+    "eval_samples_per_second": 1357.468,
+    "eval_steps_per_second": 2.665,
+    "eval_unsafe_aucpr": 0.9545945000895971,
+    "eval_unsafe_f1": 0.8773425703881339,
+    "eval_unsafe_fpr": 0.1676105464501363,
+    "eval_unsafe_precision": 0.8689558103392664,
+    "eval_unsafe_recall": 0.8858927984215719,
+    "test_accuracy": 0.855072463768116,
+    "test_loss": 0.3393045961856842,
+    "test_runtime": 48.0452,
+    "test_safe_aucpr": 0.9087695866810538,
+    "test_safe_f1": 0.8328325216730563,
+    "test_safe_fpr": 0.11715447589491113,
+    "test_safe_precision": 0.8463077355047031,
+    "test_safe_recall": 0.8197796967430475,
+    "test_samples_per_second": 1390.191,
+    "test_steps_per_second": 2.727,
+    "test_unsafe_aucpr": 0.9500140548816017,
+    "test_unsafe_f1": 0.8720896429609662,
+    "test_unsafe_fpr": 0.18022030325695187,
+    "test_unsafe_precision": 0.8615926892950392,
+    "test_unsafe_recall": 0.8828455241050885,
+    "total_flos": 6.9801745919039e+17,
+    "train_loss": 0.297589662237823,
+    "train_runtime": 10703.6605,
+    "train_samples_per_second": 505.453,
+    "train_steps_per_second": 1.975
+}

eval_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8621618924044315,
+    "eval_loss": 0.3183589279651642,
+    "eval_runtime": 44.2839,
+    "eval_safe_aucpr": 0.9201221570494966,
+    "eval_safe_f1": 0.8426927896115731,
+    "eval_safe_fpr": 0.1141072015784278,
+    "eval_safe_precision": 0.8532543923724578,
+    "eval_safe_recall": 0.8323894535498632,
+    "eval_samples_per_second": 1357.468,
+    "eval_steps_per_second": 2.665,
+    "eval_unsafe_aucpr": 0.9545945000895971,
+    "eval_unsafe_f1": 0.8773425703881339,
+    "eval_unsafe_fpr": 0.1676105464501363,
+    "eval_unsafe_precision": 0.8689558103392664,
+    "eval_unsafe_recall": 0.8858927984215719
+}

test_results.json

@@ -0,0 +1,17 @@
+{
+    "test_accuracy": 0.855072463768116,
+    "test_loss": 0.3393045961856842,
+    "test_runtime": 48.0452,
+    "test_safe_aucpr": 0.9087695866810538,
+    "test_safe_f1": 0.8328325216730563,
+    "test_safe_fpr": 0.11715447589491113,
+    "test_safe_precision": 0.8463077355047031,
+    "test_safe_recall": 0.8197796967430475,
+    "test_samples_per_second": 1390.191,
+    "test_steps_per_second": 2.727,
+    "test_unsafe_aucpr": 0.9500140548816017,
+    "test_unsafe_f1": 0.8720896429609662,
+    "test_unsafe_fpr": 0.18022030325695187,
+    "test_unsafe_precision": 0.8615926892950392,
+    "test_unsafe_recall": 0.8828455241050885
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 6.9801745919039e+17,
+    "train_loss": 0.297589662237823,
+    "train_runtime": 10703.6605,
+    "train_samples_per_second": 505.453,
+    "train_steps_per_second": 1.975
+}