update model card README.md

README.md

@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5516
-- eval_accuracy: {'accuracy': 0.782}
-- eval_f1score: {'f1': 0.7815175501754029}
-- eval_runtime: 65.761
-- eval_samples_per_second: 30.413
-- eval_steps_per_second: 3.802
+- eval_loss: 0.5453
+- eval_accuracy: {'accuracy': 0.7915}
+- eval_f1score: {'f1': 0.790972084150606}
+- eval_runtime: 68.7486
+- eval_samples_per_second: 29.092
+- eval_steps_per_second: 3.636
 - step: 0
 
 ## Model description
@@ -38,12 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 2e-07
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-09
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
 - lr_scheduler_warmup_steps: 1399
 - num_epochs: 7