update model card README.md

README.md

@@ -13,6 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
 # fias_NER
 
 This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.0011
+- eval_precision: 0.9993
+- eval_recall: 0.9994
+- eval_f1: 0.9994
+- eval_accuracy: 0.9996
+- eval_runtime: 783.8012
+- eval_samples_per_second: 2551.667
+- eval_steps_per_second: 19.935
+- epoch: 1.12
+- step: 1200000
 
 ## Model description
 
@@ -32,12 +43,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 1000000
+- training_steps: 2000000
 
 ### Framework versions