update model card README.md

README.md

@@ -1,6 +1,9 @@
 ---
+license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: bert-base-uncased-sst2
   results: []
@@ -11,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-sst2
 
-This model is a fine-tuned version of [./bert-base-uncased-finetuned-sst2](https://huggingface.co/./bert-base-uncased-finetuned-sst2) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2241
+- Accuracy: 0.9230
 
 ## Model description
 
@@ -30,18 +36,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 8
+- learning_rate: 9e-05
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - distributed_type: IPU
-- total_train_batch_size: 1024
-- total_eval_batch_size: 1024
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 2048
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3.0
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
 - training precision: Mixed Precision
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.25.1