Update README.md

README.md

@@ -12,15 +12,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # DLL888/bert-base-uncased-squad
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on [SQuAD](https://huggingface.co/datasets/squad) dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.8072
-- Train End Logits Accuracy: 0.7735
-- Train Start Logits Accuracy: 0.7320
-- Validation Loss: 0.9990
-- Validation End Logits Accuracy: 0.7302
-- Validation Start Logits Accuracy: 0.6983
-- Epoch: 1
+- Exact Match: 80.21759697256385
+- F1: 87.77849998885436
 
 ## Model description
 
@@ -36,6 +31,22 @@ More information needed
 
 ## Training procedure
 
+### Training Machine
+
+Trained in Google Colab Pro with the following specs:
++-----------------------------------------------------------------------------+
+| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
+|-------------------------------+----------------------+----------------------+
+| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
+| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
+|                               |                      |               MIG M. |
+|===============================+======================+======================|
+|   0  A100-SXM4-40GB      Off  | 00000000:00:04.0 Off |                    0 |
+| N/A   34C    P0    56W / 400W |      0MiB / 40536MiB |      0%      Default |
+|                               |                      |             Disabled |
++-------------------------------+----------------------+----------------------+
+Training took about 26 minutes for two epochs.
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: