Update README.md

README.md

@@ -7,6 +7,39 @@ language:
 tags:
 - bart
 - question-answering
+model-index:
+- name: sjrhuschlee/bart-base-squad2
+  results:
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: squad_v2
+      type: squad_v2
+      config: squad_v2
+      split: validation
+    metrics:
+    - type: exact_match
+      value: 75.223
+      name: Exact Match
+    - type: f1
+      value: 78.443
+      name: F1
+  - task:
+      type: question-answering
+      name: Question Answering
+    dataset:
+      name: squad
+      type: squad
+      config: plain_text
+      split: validation
+    metrics:
+    - type: exact_match
+      value: 83.406
+      name: Exact Match
+    - type: f1
+      value: 90.377
+      name: F1
 ---
 
 # bart-base for Extractive QA
@@ -39,23 +72,59 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 ```
 
 ## Metrics
-More information needed.
+
+```bash
+# Squad v2
+{
+    "eval_HasAns_exact": 76.45074224021593,
+    "eval_HasAns_f1": 82.88605283171232,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 74.01177460050462,
+    "eval_NoAns_f1": 74.01177460050462,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 75.23793481007327,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 78.45098300230696,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 75.22951233892024,
+    "eval_f1": 78.44256053115387,
+    "eval_runtime": 131.875,
+    "eval_samples": 11955,
+    "eval_samples_per_second": 90.654,
+    "eval_steps_per_second": 3.784,
+    "eval_total": 11873
+}
+
+# Squad
+{
+    "eval_exact_match": 83.40586565752129,
+    "eval_f1": 90.37706849113668,
+    "eval_runtime": 117.2093,
+    "eval_samples": 10619,
+    "eval_samples_per_second": 90.599,
+    "eval_steps_per_second": 3.78
+}
+```
 
 ## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
+- max_seq_length 512
+- doc_stride 128
 - learning_rate: 2e-06
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 6
 - total_train_batch_size: 96
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Adam8Bit with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 4.0
+- gradient_checkpointing: True
+- tf32: True
 
 
 ### Framework versions