Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: PhucDanh/Bartpho-fine-tuning-model-for-question-answering
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # checkpoints
 
-This model is a fine-tuned version of [PhucDanh/Bartpho-fine-tuning-model-for-question-answering](https://huggingface.co/PhucDanh/Bartpho-fine-tuning-model-for-question-answering) on the None dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 
 ## Model description
 
@@ -33,15 +33,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results